This document proposes a method called learnable image encryption that allows deep learning to be performed on encrypted images while protecting privacy. It works by applying weak block-wise encryption to images before training deep learning models. The models can still learn meaningful patterns from the encrypted images. This approach could help shopping malls analyze customer behavior from security camera footage or allow companies to develop AI systems using encrypted data without compromising privacy. The method achieves comparable accuracy to training on plain images while keeping the encrypted images unintelligible to humans. Code and details on the block-wise encryption and decryption algorithms are available online.
The presentation covers the following:
Basic Terms
Cryptography
The General Goals of Cryptography
Common Types of Attacks
Substitution Ciphers
Transposition Cipher
Steganography- “Concealed Writing”
Symmetric Secret Key Encryption
Types of Symmetric Algorithms
Common Symmetric Algorithms
Asymmetric Secret Key Encryption
Common Asymmetric Algorithms
Public Key Cryptography
Hashing Techniques
Hashing Algorithms
Digital Signatures
Transport Layer Security
Public key infrastructure (PKI)
The presentation describes basics of cryptography and information security. It covers goals of cryptography, history of cipher symmetric and public key cryptography
Slides for a college cryptography course at CCSF. Instructor: Sam Bowne
Based on: Understanding Cryptography: A Textbook for Students and Practitioners by Christof Paar, Jan Pelzl, and Bart Preneel, ISBN: 3642041000 ASIN: B014P9I39Q
See https://samsclass.info/141/141_F17.shtml
This presentation contains the contents pertaining to the undergraduate course on Cryptography and Network Security (UITC203) at Sri Ramakrishna Institute of Technology. This covers the Elliptic Curve Cryptography and the basis of elliptic curve arithmetics.
The presentation covers the following:
Basic Terms
Cryptography
The General Goals of Cryptography
Common Types of Attacks
Substitution Ciphers
Transposition Cipher
Steganography- “Concealed Writing”
Symmetric Secret Key Encryption
Types of Symmetric Algorithms
Common Symmetric Algorithms
Asymmetric Secret Key Encryption
Common Asymmetric Algorithms
Public Key Cryptography
Hashing Techniques
Hashing Algorithms
Digital Signatures
Transport Layer Security
Public key infrastructure (PKI)
The presentation describes basics of cryptography and information security. It covers goals of cryptography, history of cipher symmetric and public key cryptography
Slides for a college cryptography course at CCSF. Instructor: Sam Bowne
Based on: Understanding Cryptography: A Textbook for Students and Practitioners by Christof Paar, Jan Pelzl, and Bart Preneel, ISBN: 3642041000 ASIN: B014P9I39Q
See https://samsclass.info/141/141_F17.shtml
This presentation contains the contents pertaining to the undergraduate course on Cryptography and Network Security (UITC203) at Sri Ramakrishna Institute of Technology. This covers the Elliptic Curve Cryptography and the basis of elliptic curve arithmetics.
Today in modern era of internet we share some sensitive data to information transmission. but need to ensure security. So we focus on Cryptography modern technique for secure transmission of information over network.
This is a project dealing with securing images over a network.
Image is a delicate piece of information shared between clients across the world.Cryptography plays a huge role during secure connections.Applying simple Gaussian elimination to achieve highly secured image encryption decryption technique is a interesting challenge.
This presentation contains the contents pertaining to the undergraduate course on Cryptography and Network Security (UITC203) at Sri Ramakrishna Institute of Technology. This covers the ElGamal Cryptosystem.
This is a Presentation On use of AES Algorithm To Encrypt Or Decrypt a Text File. This Algorithm is the latest and better than DES. It is a Networking Presentation. Thank You.
This presentation is based on the paper :
"A Method for Obtaining Digital Signatures and Public-Key Cryptosystems" by R.L. Rivest, A. Shamir, and L. Adleman
Project consists of individual modules of encryption and decryption units. Standard T-DES algorithm is implemented. Presently working on to integrate DES with AES to develop stronger crypto algorithm and test the same against Side Channel Attacks and compare different algorithms.
Today in modern era of internet we share some sensitive data to information transmission. but need to ensure security. So we focus on Cryptography modern technique for secure transmission of information over network.
This is a project dealing with securing images over a network.
Image is a delicate piece of information shared between clients across the world.Cryptography plays a huge role during secure connections.Applying simple Gaussian elimination to achieve highly secured image encryption decryption technique is a interesting challenge.
This presentation contains the contents pertaining to the undergraduate course on Cryptography and Network Security (UITC203) at Sri Ramakrishna Institute of Technology. This covers the ElGamal Cryptosystem.
This is a Presentation On use of AES Algorithm To Encrypt Or Decrypt a Text File. This Algorithm is the latest and better than DES. It is a Networking Presentation. Thank You.
This presentation is based on the paper :
"A Method for Obtaining Digital Signatures and Public-Key Cryptosystems" by R.L. Rivest, A. Shamir, and L. Adleman
Project consists of individual modules of encryption and decryption units. Standard T-DES algorithm is implemented. Presently working on to integrate DES with AES to develop stronger crypto algorithm and test the same against Side Channel Attacks and compare different algorithms.
Reversible Data Hiding In Encrypted Images And Its Application To Secure Miss...CSCJournals
This paper proposes reversible data hiding in encrypted images for secure missile launching. The work is presented in two stages: one involves encryption of cover image by block cipher algorithm and other is embedding secure data related to missile launching. For embedding data, vacant pixels are identified by Slepian-Wolf encoding method along with embedding key to hide the data. At the other end by using decryption algorithm the original cover image is recovered and the secret data is extracted. The performance analysis is presented by calculating parameters MSE, PSNR and SSIM.
A Survey on Different Data Hiding Techniques in Encrypted Imagesijsrd.com
In this paper, we are going to have survey on different data hiding techniques and our main focus is on†Reversible data hiding in encrypted imagesâ€Â. In recent year the security of the sensitive data has become of prime and supreme importance and concern. To protect this data or secret information from unauthorized person we use many data hiding techniques like stegnography, cryptography and RDH. In this paper we will discuss on one such data hiding technique called Reversible Data Hiding (RDH). In this instead of embedding data in encrypted images directly, some pixels are estimated before encryption so that additional data can be embedded in the estimating errors. Without the encryption key, one cannot get access to the original image. A RC4 algorithm is applied on the rest pixels of the image and a special encryption scheme is designed to encrypt the estimating errors.Our paper presents a survey on various data hiding techniques and their comparative analysis.
separable reversible data hiding in encrypted imageZTech Proje
FINAL YEAR IEEE PROJECTS,
EMBEDDED SYSTEMS PROJECTS,
ENGINEERING PROJECTS,
MCA PROJECTS,
ROBOTICS PROJECTS,
ARM PIC BASED PROJECTS, MICRO CONTROLLER PROJECTS Z Technologies, Chennai
Protecting the data in a safe and secure way which does not impede the access of an authorized authority is an immensely difficult and very interesting research problem. image cryptography is a special type of encryption technique to obscure image-based secret information which can be decrypted by Human Visual System. Communication is the process of transmitting information from source to destination. The exchanging information should not be stolen by unauthorized parties like hackers while sending or receiving via channel. To avoid this stealing of the information visual cryptography techniques are used. This paper proposes a novel method for key generation by using nearest prime pixels. Further 2’s complement and logical operations are performed to generate decrypted image. The final decrypted image is generated by representing pixels in matrix form and data is retrieved in column wise.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Reversible Data Hiding in Encrypted Image: A ReviewEditor IJMTER
Recently, more and more attention is paid to reversible data hiding (RDH) in encrypted
images, since it maintains the excellent property that the original cover can be losslessly recovered
after embedded data is extracted while protecting the image content’s confidentiality. All previous
methods embed data by reversibly vacating room from the encrypted images, which may be subject
to some errors on data extraction and/or image restoration. In this survey paper, we discuss about
various methods and algorithms which were used for reversible data hiding (RDH) in encrypted
image to make data hiding process effortless. We also use visual cryptographic approach for
encryption which helps to protect the image during transmission. The scheme is suitable for
authentication based application where collective acceptance and decision making plays an important
role. The main goal is to retrieve the original image with lossless process and minimum computation
during image encryption /decryption by using keyless approach.
Machine learning_ Replicating Human BrainNishant Jain
Slides will make you realize how humans makes decision and following the same pattern how Machines are trained to learn and make decisions. Slides gives an overview of all the steps involved in designing an efficient decision making machine.
International Journal of Computational Engineering Research(IJCER)ijceronline
International Journal of Computational Engineering Research(IJCER) is an intentional online Journal in English monthly publishing journal. This Journal publish original research work that contributes significantly to further the scientific knowledge in engineering and Technology.
Visual Cryptography is a special encryption technique that encrypts the secret image into n
number of shares to hide information in images in such a way that it can be decrypted by the
human visual system. It is imperceptible to reveal the secret information unless a certain
number of shares (k) or more are superimposed. Simple visual cryptography is very insecure.
Variable length key based visual cryptography for color image uses a variable length Symmetric
Key based Visual Cryptographic Scheme for color images where a secret key is used to encrypt
the image and division of the encrypted image is done using Random Number. Unless the secret
key, the original image will not be decrypted. Here secret key ensures the security of image.
This paper describes the overall process of above scheme. Encryption process encrypts the
Original Image using variable length Symmetric Key, gives encrypted image. Share generation
process divides the encrypted image into n number of shares using random number. Decryption process stacks k number of shares out of n to reconstruct encrypted image and uses the same key for decryption.
Scalable Image Encryption Based Lossless Image CompressionIJERA Editor
Present days processing of the image compression is the main protective representation with considerable data
process on each image progression. Traditionally more number of techniques were introduced for during
efficient progression in image compression on the data set representation process of application development. A
content owner encrypts the original uncompressed image using an encryption key. Then, a data hider may
compress the least significant bits of the encrypted image using a data hiding key to create a sparse space to
accommodate some additional data. With an encrypted image containing additional data, if a receiver has the
data hiding key, receiver can extract the additional data though receiver does not know the image content. If the
receiver has the encryption key, can decrypt the received data to obtain an image similar to the original one. If
the receiver has both the data hiding key and the encryption key, can extract the additional data and recover the
original content.\
Enhancement of Payload Capacity for Image Steganography based on LSBEditor IJCATR
In this result paper we will show the implementation result of our proposed method. Steganography is an art and
science of Hide the data in a cover image using some techniques that it remains undetected by the unauthorized access. We hide
the data in a manner that the stego image looks like a single entry by any third person. No one has doubt that the image is the
stego image. We use some different methods that keep data to be secret. It is a powerful tool for security with which we can
keep the data secret behind an object. An object may be Text, Audio, Video, and Image. The factor that affects the steganography
methods are PSNR, MSE, Payload Capacity and BER. Security of data will be shown by the Histogram of picture.
The protection of multimedia data is becoming very
important. The protection of this multimedia data can be done
with encryption or data hiding algorithms. To decrease
transmissions time the data transmission necessary.
Recently, more and more attention is paid to reversible data
hiding (RDH) in encrypted image. It maintains original area
could be perfectly restored after extraction of the hidden
message. In previous method embed data by reversibly vacating
area from the encrypted images, which may be subject to some
errors on data extraction and/or image restoration. A novel
method by reserving area before encryption with a traditional
RDH algorithm, and thus it is easy for the data hider to
reversibly embed data in the encrypted image. The proposed
method can achieve real reversibility, that is data extraction and
image recovery are free of any error. The hidden data can be
retrieved as and when required. The methods that are used in
reversible data hiding techniques like Lossless embedding and
encryption.
This deals with the image steganography as well as with the
different security issues, general overview of cryptography
approaches and about the different steganography
algorithms like Least Significant Bit (LSB) algorithm ,
JSteg, F5 algorithms. It also compares those algorithms in
means of speed, accuracy and security.
Material of year-end seminar of Social Intelligence Research Team of artificial intelligence research center of National Institute of Advanced Industrial Science and Technology.
Nutraceutical market, scope and growth: Herbal drug technologyLokesh Patil
As consumer awareness of health and wellness rises, the nutraceutical market—which includes goods like functional meals, drinks, and dietary supplements that provide health advantages beyond basic nutrition—is growing significantly. As healthcare expenses rise, the population ages, and people want natural and preventative health solutions more and more, this industry is increasing quickly. Further driving market expansion are product formulation innovations and the use of cutting-edge technology for customized nutrition. With its worldwide reach, the nutraceutical industry is expected to keep growing and provide significant chances for research and investment in a number of categories, including vitamins, minerals, probiotics, and herbal supplements.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.Sérgio Sacani
The return of a sample of near-surface atmosphere from Mars would facilitate answers to several first-order science questions surrounding the formation and evolution of the planet. One of the important aspects of terrestrial planet formation in general is the role that primary atmospheres played in influencing the chemistry and structure of the planets and their antecedents. Studies of the martian atmosphere can be used to investigate the role of a primary atmosphere in its history. Atmosphere samples would also inform our understanding of the near-surface chemistry of the planet, and ultimately the prospects for life. High-precision isotopic analyses of constituent gases are needed to address these questions, requiring that the analyses are made on returned samples rather than in situ.
Cancer cell metabolism: special Reference to Lactate PathwayAADYARAJPANDEY1
Normal Cell Metabolism:
Cellular respiration describes the series of steps that cells use to break down sugar and other chemicals to get the energy we need to function.
Energy is stored in the bonds of glucose and when glucose is broken down, much of that energy is released.
Cell utilize energy in the form of ATP.
The first step of respiration is called glycolysis. In a series of steps, glycolysis breaks glucose into two smaller molecules - a chemical called pyruvate. A small amount of ATP is formed during this process.
Most healthy cells continue the breakdown in a second process, called the Kreb's cycle. The Kreb's cycle allows cells to “burn” the pyruvates made in glycolysis to get more ATP.
The last step in the breakdown of glucose is called oxidative phosphorylation (Ox-Phos).
It takes place in specialized cell structures called mitochondria. This process produces a large amount of ATP. Importantly, cells need oxygen to complete oxidative phosphorylation.
If a cell completes only glycolysis, only 2 molecules of ATP are made per glucose. However, if the cell completes the entire respiration process (glycolysis - Kreb's - oxidative phosphorylation), about 36 molecules of ATP are created, giving it much more energy to use.
IN CANCER CELL:
Unlike healthy cells that "burn" the entire molecule of sugar to capture a large amount of energy as ATP, cancer cells are wasteful.
Cancer cells only partially break down sugar molecules. They overuse the first step of respiration, glycolysis. They frequently do not complete the second step, oxidative phosphorylation.
This results in only 2 molecules of ATP per each glucose molecule instead of the 36 or so ATPs healthy cells gain. As a result, cancer cells need to use a lot more sugar molecules to get enough energy to survive.
Unlike healthy cells that "burn" the entire molecule of sugar to capture a large amount of energy as ATP, cancer cells are wasteful.
Cancer cells only partially break down sugar molecules. They overuse the first step of respiration, glycolysis. They frequently do not complete the second step, oxidative phosphorylation.
This results in only 2 molecules of ATP per each glucose molecule instead of the 36 or so ATPs healthy cells gain. As a result, cancer cells need to use a lot more sugar molecules to get enough energy to survive.
introduction to WARBERG PHENOMENA:
WARBURG EFFECT Usually, cancer cells are highly glycolytic (glucose addiction) and take up more glucose than do normal cells from outside.
Otto Heinrich Warburg (; 8 October 1883 – 1 August 1970) In 1931 was awarded the Nobel Prize in Physiology for his "discovery of the nature and mode of action of the respiratory enzyme.
WARNBURG EFFECT : cancer cells under aerobic (well-oxygenated) conditions to metabolize glucose to lactate (aerobic glycolysis) is known as the Warburg effect. Warburg made the observation that tumor slices consume glucose and secrete lactate at a higher rate than normal tissues.
What is greenhouse gasses and how many gasses are there to affect the Earth.moosaasad1975
What are greenhouse gasses how they affect the earth and its environment what is the future of the environment and earth how the weather and the climate effects.
Richard's aventures in two entangled wonderlandsRichard Gill
Since the loophole-free Bell experiments of 2020 and the Nobel prizes in physics of 2022, critics of Bell's work have retreated to the fortress of super-determinism. Now, super-determinism is a derogatory word - it just means "determinism". Palmer, Hance and Hossenfelder argue that quantum mechanics and determinism are not incompatible, using a sophisticated mathematical construction based on a subtle thinning of allowed states and measurements in quantum mechanics, such that what is left appears to make Bell's argument fail, without altering the empirical predictions of quantum mechanics. I think however that it is a smoke screen, and the slogan "lost in math" comes to my mind. I will discuss some other recent disproofs of Bell's theorem using the language of causality based on causal graphs. Causal thinking is also central to law and justice. I will mention surprising connections to my work on serial killer nurse cases, in particular the Dutch case of Lucia de Berk and the current UK case of Lucy Letby.
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...University of Maribor
Slides from:
11th International Conference on Electrical, Electronics and Computer Engineering (IcETRAN), Niš, 3-6 June 2024
Track: Artificial Intelligence
https://www.etran.rs/2024/en/home-english/
Slide 1: Title Slide
Extrachromosomal Inheritance
Slide 2: Introduction to Extrachromosomal Inheritance
Definition: Extrachromosomal inheritance refers to the transmission of genetic material that is not found within the nucleus.
Key Components: Involves genes located in mitochondria, chloroplasts, and plasmids.
Slide 3: Mitochondrial Inheritance
Mitochondria: Organelles responsible for energy production.
Mitochondrial DNA (mtDNA): Circular DNA molecule found in mitochondria.
Inheritance Pattern: Maternally inherited, meaning it is passed from mothers to all their offspring.
Diseases: Examples include Leber’s hereditary optic neuropathy (LHON) and mitochondrial myopathy.
Slide 4: Chloroplast Inheritance
Chloroplasts: Organelles responsible for photosynthesis in plants.
Chloroplast DNA (cpDNA): Circular DNA molecule found in chloroplasts.
Inheritance Pattern: Often maternally inherited in most plants, but can vary in some species.
Examples: Variegation in plants, where leaf color patterns are determined by chloroplast DNA.
Slide 5: Plasmid Inheritance
Plasmids: Small, circular DNA molecules found in bacteria and some eukaryotes.
Features: Can carry antibiotic resistance genes and can be transferred between cells through processes like conjugation.
Significance: Important in biotechnology for gene cloning and genetic engineering.
Slide 6: Mechanisms of Extrachromosomal Inheritance
Non-Mendelian Patterns: Do not follow Mendel’s laws of inheritance.
Cytoplasmic Segregation: During cell division, organelles like mitochondria and chloroplasts are randomly distributed to daughter cells.
Heteroplasmy: Presence of more than one type of organellar genome within a cell, leading to variation in expression.
Slide 7: Examples of Extrachromosomal Inheritance
Four O’clock Plant (Mirabilis jalapa): Shows variegated leaves due to different cpDNA in leaf cells.
Petite Mutants in Yeast: Result from mutations in mitochondrial DNA affecting respiration.
Slide 8: Importance of Extrachromosomal Inheritance
Evolution: Provides insight into the evolution of eukaryotic cells.
Medicine: Understanding mitochondrial inheritance helps in diagnosing and treating mitochondrial diseases.
Agriculture: Chloroplast inheritance can be used in plant breeding and genetic modification.
Slide 9: Recent Research and Advances
Gene Editing: Techniques like CRISPR-Cas9 are being used to edit mitochondrial and chloroplast DNA.
Therapies: Development of mitochondrial replacement therapy (MRT) for preventing mitochondrial diseases.
Slide 10: Conclusion
Summary: Extrachromosomal inheritance involves the transmission of genetic material outside the nucleus and plays a crucial role in genetics, medicine, and biotechnology.
Future Directions: Continued research and technological advancements hold promise for new treatments and applications.
Slide 11: Questions and Discussion
Invite Audience: Open the floor for any questions or further discussion on the topic.
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...Ana Luísa Pinho
Functional Magnetic Resonance Imaging (fMRI) provides means to characterize brain activations in response to behavior. However, cognitive neuroscience has been limited to group-level effects referring to the performance of specific tasks. To obtain the functional profile of elementary cognitive mechanisms, the combination of brain responses to many tasks is required. Yet, to date, both structural atlases and parcellation-based activations do not fully account for cognitive function and still present several limitations. Further, they do not adapt overall to individual characteristics. In this talk, I will give an account of deep-behavioral phenotyping strategies, namely data-driven methods in large task-fMRI datasets, to optimize functional brain-data collection and improve inference of effects-of-interest related to mental processes. Key to this approach is the employment of fast multi-functional paradigms rich on features that can be well parametrized and, consequently, facilitate the creation of psycho-physiological constructs to be modelled with imaging data. Particular emphasis will be given to music stimuli when studying high-order cognitive mechanisms, due to their ecological nature and quality to enable complex behavior compounded by discrete entities. I will also discuss how deep-behavioral phenotyping and individualized models applied to neuroimaging data can better account for the subject-specific organization of domain-general cognitive systems in the human brain. Finally, the accumulation of functional brain signatures brings the possibility to clarify relationships among tasks and create a univocal link between brain systems and mental functions through: (1) the development of ontologies proposing an organization of cognitive processes; and (2) brain-network taxonomies describing functional specialization. To this end, tools to improve commensurability in cognitive science are necessary, such as public repositories, ontology-based platforms and automated meta-analysis tools. I will thus discuss some brain-atlasing resources currently under development, and their applicability in cognitive as well as clinical neuroscience.
Seminar of U.V. Spectroscopy by SAMIR PANDASAMIR PANDA
Spectroscopy is a branch of science dealing the study of interaction of electromagnetic radiation with matter.
Ultraviolet-visible spectroscopy refers to absorption spectroscopy or reflect spectroscopy in the UV-VIS spectral region.
Ultraviolet-visible spectroscopy is an analytical method that can measure the amount of light received by the analyte.
2. Big data for deep learning
1
Deep network
The deep learning is a very powerful tool.
Efficient algorithms High performance
computer
Big data
3. Big Data includes a Big Privacy Issue
2
Surveillance camera Big data
We cannot use those data
for learning.
Privacy protection
Only owner and police can access
with limited purpose.
Motivation:
How can we take advantage of
the big data
with privacy protection?
4. Practical Case
3
Shopping mall owner:
They want to analyze customer’s behavior.
They have a big data, but they don’t have
enough knowledge to develop software.
They have to protect customer’s privacy.
Engineering company:
They want to develop analysis system.
They have enough knowledge to develop
software, but they don’t have a big data.
They face privacy issue.
Police:
They don’t care about customer’s behavior.
5. Image Encryption
4
Image encryption helps to protect the privacy.
Original data Encrypted data
Key
Encryption
Decryption
Image encryption can protect the privacy.
But, we cannot use the encrypted data for the learning.
Human understandable
Machine learnable
Human non-understandable
Machine non-learnable
6. Homomorphic Encryption
5 𝐸𝑛𝑐 𝑋 + 𝐸𝑛𝑐 𝑌 = 𝐸𝑛𝑐(𝑋 + 𝑌)
Homomorphic Encryption will solve that problem.
Original data Encrypted data
Homomorphic
encryption
+ − × ÷ + − × ÷
Calculation after encryption
Encryption after calculation
=
Human non-understandable
Machine calculable
Still developing
Very limited calculation
Very heavy computation
7. Learnable Image Encryption
6
We propose a novel concept of a learnable image encryption.
Original data
Relatively weak
encryption
Powerful calculation
(Deep learning)
Encrypted data
Human non-understandable
Machine learnable
This combination allows us
the deep learning with the encrypted data.
It means that we can avoid the privacy issue.
8. Summary of learning frameworks
7
Traditional learning framework
Naive combination of image encryption and learning
Proposed learnable image encryption
Training with
human understandable
data
Training with
human understandable
data
Training with
humannon-understandable
data
13. Summary
12
Proposed learnable image encryption
Training with
humannon-understandable
data
We have proposed a novel concept of learnable image encryption.
It has potential to learn with encrypted image data.
Keys: Block-wise relatively weak image encryption.
Powerful calculation with the deep learning.
Code available:
http://www.ok.sc.e.titech.ac.jp/~mtanaka/proj/imagescramble/
Google by “learnable image encryption”
Human non-understandable and machine learnable
Editor's Notes
I’m Masayuki Tanaka from Japan.
Today, I will introduce a new concept of a learnable image encryption.
Now a day, a big data based learning or the deep learning is know as very powerful tool.
We can find the deep learning in everywhere.
Here is three key components for the deep learning: Big data, high performance computer, and efficient algorithm.
For the high performance computer, many companies are investing a lot of money to get many many GPUs.
We also need the efficient algorithms, in other words, we need talented and smart young researchers.
OK, those two components are, of course, important. However, in this presentation, I will be focusing on the big data.
We can get billions or trillions of mages everyday.
However, we cannot utilize those billions of images for the deep learning.
There are several challenges. But, one of those challenges is privacy issue.
I can say big data includes big privacy issue.
For example, let’s consider the surveillance camera case. As I said, each surveillance camera produces a lot of images everyday.
However, almost all images are just threw away without using for the deep learning.
The reason is the privacy protection. Usually, we cannot access those data. Only surveillance camera owner or the police can access those data, but with very limited purpose.
So, my motivation is: How can we take advantage of the big data with the privacy protection.
Let’s consider more practical case.
First is the shopping mall owner.
They want to analyze customer’s behavior. They already have a big data, but they don’t have enough knowledge to develop software which analyze customer’s behavior.
Of course, they have to protect customer’s privacy.
Second is engineering company. Usually, we are in those categories.
They want to develop analysis system for business. They have enough knowledge to develop software, but they don’t have a big data.
They have tried to access the big data which the shopping mall owner has. However, they faced privacy issue.
Third is police or other authorized association. It is very simple. They might be able to access any kind of data, may be.
But, they don’t care about customer’s behavior and to develop the software.
Now, I will move to technical aspect.
Image encryption is very helpful to protect the privacy.
There are already a lot of encryption algorithms. Here, I’d like to introduce very simple case.
The original data is encrypted with the special key. Then, only the person who knows that key can reconstruct or decrypted to the original image.
We have good news in terms of the privacy. The encrypted data is human non-understandable. It means the privacy can be protected.
However, nobody can utilized those encrypted data for the deep learning.
To overcome this problem.
Homomorphic encryption algorithm has been intensively researched.
Homomorphic encryption has very good properties. We can apply arithmetic operation or we can calculate in encrypted domain.
Namely, it is guaranteed that Calculation after Encryption equals Encryption after Calculation.
It is very very good property. I can say the encrypted data by the homomorphic encryption is human non-understandable and machine calculable.
That is great properties and many people want to use. However, this technique is still developing, and very very limited calculation and very heavy computation.
I hope that this homomorphic encryption will work soon, however, right now, we can not use this homomorphic encryption is very challenge to apply the deep learning.
演算 Arithmetic operation
Then, in this presentation, I’d like to propose a new concept of the learnable image encryption.
The learnable image encryption consists of two components: relatively weak encryption and powerful calculation like deep learning.
Even if the encryption is relatively weak, human cannot understand the encrypted data.
In addition, the powerful calculation algorithm like the deep learning can lean the encrypted data.
This is the proposed concept. If we can find that kind of balance, this combination allows us the deep learning with the encrypted data.
Again, human cannot understand the encrypted data. So, we can avoid the privacy issue.
Here is summary of learning frameworks with privacy issues.
First is the traditional learning framework without considering the privacy issue.
Plain images are directly used for the network learning. It is normal case, but in terms of the privacy, it is not good because every data is human understandable.
Second is the naive combination of the image encryption and the learning. It apply image encryption. In this sense, the stored data is human non-understandable.
However, of course, original data or the plain images should be reconstructed for the network learning. Actually, it is same as the traditional learning framework.
Third, this is my proposal, is the learnable image encryption. We can learn with the encrypted and human non-understandable data. So, once we apply the learnable image encryption,
we are free from the privacy issue.
Now, I will explain processing pipeline of the proposed encryption algorithm.
First and it is very important, the proposed algorithm is block-wise operation. We apply following operation block-by-block.
I picked two-by-two bock for example. Those intensity data is rearrange into a single row.
Then, apply the shuffling and reverse several values. This process corresponds to the key.
Then, we have the encrypted single row data. This single row data is rearrange into the RGB image block.
This encrypted image block is stored back.
Again, the point is the block wise operation. Even if we apply the shuffling and the reverse operation to each block, each block still have the original information.
It is the point.
The image decryption is simple reverse process of the image encryption.
Each block of encrypted image is rearranged into a single row data.
Then, apply the reverse operation and the inverse shuffling. This operation is associated the key.
If the person knows the shuffling algorithm and the position of the reverse, that person easily can reconstruct data.
However, if the person don’t know those information, it is difficult to reconstruct the data.
Next, I will show the network structure for the encrypted data.
The image encryption is performed block-by-block. As I told you, each block includes original information.
So, first, the network extracts those information block-wise operation manner.
Then, the extracted features are upsampled to obtain the same size of input data. After that, we can apply the classical network.
For this reason, the block-wise operation is very important and the key of this algorithm.
I will show kind of the preliminary results.
We have evaluated with cifar-10 and cifar-100 dataset.
There are four approach,
first, training with the plain image, it is the classical approach,
second, is existing image shuffling algorithm,
third, is the naive block wise pixel shuffling algorithm,
fourth, is the proposed algorithm.
As you can see, the plain image is human understandable, it is bad in terms of the privacy.
However, the validation accuracy of the plain image is very good.
Exsiting image shuffling algorithm, in terms of the privacy, it is done pretty good job. Human cannot understand the data. But, in the same time, machine cannot learn. As a result, we can get very lower validation accuracies compared with the results of the plain image.
Naive block wise pixel shuffling, the performance or the validation accuracy of this is comparable to results of the plain image case.
However, human can get some information from shuffled image.
Compared to those encrypted image, I think that human cannot get meaningfull information from the data encrypted by the proposed algorithm.
However, the machine can learn with those data. Actually, the performance is very comparable to the results of the plain image.
Finally, I’d like to conclude as follows:
We have propose the novel concept of the learning image encryption.
Key components of the proposed algorithm are block-wise relatively weak image encryption and powerful calculation with the deep learning.
The important properties of the proposed framework is human non-understandable and machine learnable.
The code if available online, if you have interests, please try by yourself.
Thanks,