Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Upcoming SlideShare
What to Upload to SlideShare
Next

0

Share

AI Security : Machine Learning, Deep Learning and Computer Vision Security

http://deeplab.co
cihan [ at ] deeplab.co

Related Books

Free with a 30 day trial from Scribd

See all

Related Audiobooks

Free with a 30 day trial from Scribd

See all
  • Be the first to like this

AI Security : Machine Learning, Deep Learning and Computer Vision Security

  1. 1. Cihan Özhan Founder of DeepLab, http://deeplab.co
  2. 2. DeepLab : Technologies ML/DL/CV Based • Technologies – Go, Python, C/C++, Rust, C# – PyTorch, TensorFlow, Keras, scikit-learn • As Web, Mobile, IoT/Edge ve Back-End… – OpenCV – … and dozens of different tools and equipment… • Cloud Computing – AWS Machine Learning – Google Cloud Machine Learning – IBM Watson Machine Learning – Microsoft Azure Machine Learning – … and various cloud solutions… • Distributed Systems – Distributed Databases – Distributed Deep Learning
  3. 3. AI Security Machine Learning, Deep Learning and Computer Vision Security Cihan Özhan | Founder of DeepLab | Developer, AI Engineer, AI Hacker, Data Master
  4. 4. OWASP Top 10 List OWASP (Open Web Application Security Project)
  5. 5. AI Data Objects • Image • Text • File • Voice • Video • Data • 3D Object
  6. 6. ML/DL Applications • Image Classification • Pose Estimation • Face Recognition • Face Detection • Object Detection • Question Answering System • Semantic Segmentation • Text Classification • Text Recognition • Sentiment Analysis • Industrial AI • Autonomous Systems • and more…
  7. 7. ML/DL Algorithms • Classification (Supervised) • Clustering (Unsupervised) • Regression (Supervised) • Generative Models (Semi-Supervised) • Dimensionality Reduction (Unsupervised) • Reinforcement Learning (Reinforcement)
  8. 8. MLaaS? Machine Learning as a Service MLaaS is the method in which ML/DL algorithms and software are offered as a component of cloud computing services. MLaaS = (SaaS + [ML/DL/CV])
  9. 9. Hidden Technical Debt in Machine Learning Systems https://papers.nips.cc/paper/2015/file/86df7dcfd896fcaf2674f757a2463eba-Paper.pdf Usually the whole team, focus and area where resources are directed!
  10. 10. Model Lifecycle Machine Learning Model Development Lifecycle
  11. 11. Model Lifecycle Machine Learning Model Development Lifecycle We start here! ML model preparation process The chore but the imperative: Preparing the data! We prepared the model! We train the model with data. Cloud or On-Premise We tested the trained model with test data! The trained model is packaged for the programmatic environment. Post release: The model is constantly monitored.
  12. 12. How to Publish a Machine Learning project?
  13. 13. MartinFowler.com
  14. 14. MartinFowler.com
  15. 15. Machine Learning Security
  16. 16. Basic Security Issues Intentional Issues Unintentional Issues Perturbation Attack Reward Hacking Poisoning Attack Side Effects Model Inversion Distributional Shifts Membership Inference Natural Adversarial Examples Model Stealing Common Corruption Reprogramming ML system Incomplete Testing Adversarial Example in Pyhsical Domain Malicious ML provider recovering training data Attacking the ML supply chain Backdoor ML Exploit Software Dependencies
  17. 17. Adversarial Attack : Image (https://adversarial.io/)
  18. 18. https://openai.com/blog/adversarial-example-research/
  19. 19. https://hackernoon.com/adversarial-attacks-how-to-trick-computer-vision-7484c4e85dc0
  20. 20. Adversarial Attack : Speech-to-Text (https://people.eecs.berkeley.edu/~daw/papers/audio-dls18.pdf)
  21. 21. https://arxiv.org/pdf/2006.03575.pdf
  22. 22. Adversarial Attack : NLP https://arxiv.org/pdf/2005.05909.pdf https://github.com/QData/TextAttack
  23. 23. Adversarial Attack : Remote Sensing (https://arxiv.org/pdf/1805.10997.pdf)
  24. 24. Adversarial Attack : Satellite (https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8823003)
  25. 25. Adversarial Attack : Military https://spectrum.ieee.org/automaton/artificial-intelligence/embedded-ai/adversarial-attacks-and-ai-systems
  26. 26. Adversarial Attack : Military https://www.sto.nato.int/publications/STO%20Meeting%20Proceedings/STO-MP-IST-160/MP-IST-160-S1-5.pdf
  27. 27. Adversarial Attack : Autonomous Driving https://web.cs.ucla.edu/~miryung/Publications/percom2020-autonomousdriving.pdf https://github.com/ITSEG-MQ/Adv-attack-and-defense-on-driving-model
  28. 28. Security Research of Tesla Autopilot (40 Pages) https://keenlab.tencent.com/en/whitepapers/Experimental_Security_Research_of_Tesla_Autopilot.pdf
  29. 29. Industrial AI and Autonomous Systems - Cihan Özhan (Turkish) https://www.youtube.com/watch?v=ID_tw5iq6Xs
  30. 30. https://medium.com/@ml.at.berkeley/tricking-neural-networks-create-your-own-adversarial-examples-a61eb7620fd8
  31. 31. Exploit Software Dependencies • It takes advantage of the vulnerabilities of the software the system is connected to, not algorithms. • Prevention: – Security Scan – Security Reports – Be Careful : Wrappers ve Pre-Build Environment – Use Less Dependency – Dependency Management Tools • Synk : Synk.io • Python Poetry : python-poetry.org • Bandit : – Bandit is a tool designed to find common security issues in Python code. – https://github.com/PyCQA/bandit • pyup.io/safety • requires.io – etc…
  32. 32. Tool/Library Security (TensorFlow) • TensorFlow (tools like) is designed for internal communication, not for running on untrusted networks. • These tools (ModelServer etc.) do not have built-in authorization. • It can read and write files, send and receive data over the network… • (!) TensorFlow Models as Programs • (!) Running Untrusted Models • (!) Accepting Untrusted Inputs https://github.com/tensorflow/tensorflow/blob/master/SECURITY.md
  33. 33. https://www.tensorflow.org/tutorials/generative/adversarial_fgsm
  34. 34. Cihan Özhan Links • cihanozhan.com • linkedin.com/in/cihanozhan • medium.com/@cihanozhan • youtube.com/user/OracleAdam • twitter.com/UnmannedCode • github.com/cihanozhan Contact • cihan@deeplab.co

http://deeplab.co cihan [ at ] deeplab.co

Views

Total views

115

On Slideshare

0

From embeds

0

Number of embeds

1

Actions

Downloads

1

Shares

0

Comments

0

Likes

0

×