SlideShare a Scribd company logo
1 of 30
1 © 2022 Anaconda
What Vulnerabilities?
How (And Why) to Secure Your ML/AI Solutions
Kevin Goldsmith, CTO
October 7, 2022
2 © 2022 Anaconda
We all (hopefully) understand that security is
important for our production systems
3 © 2022 Anaconda
While hardening our production data and systems,
we don’t often think about our ML and AI pipelines
because they are not directly consumed by users.
EDW
Backoffice
Systems
Data Scientists
Data Models
Production Customers
4 © 2022 Anaconda
While hardening our production data and systems,
we often don’t think about our ML and AI pipelines
because they are not directly consumed by users.
EDW
Backoffice
Systems
Data Scientists
Data Models
Production Customers
5 © 2022 Anaconda
While hardening our production data and systems,
we often don’t think about our ML and AI pipelines
because they are not directly consumed by users.
EDW
Backoffice
Systems
Data Scientists
Data Models
Production Customers
6 © 2022 Anaconda
While hardening our production data and systems,
we often don’t think about our ML and AI pipelines
because they are not directly consumed by users.
EDW
Backoffice
Systems
Data Scientists
Data Models
Production Customers
EVASION ATTACKS
POISONING ATTACKS
INFERENCE ATTACKS
TROJAN ATTACKS
SUPPLY CHAIN ATTACKS
7 © 2022 Anaconda
Protecting your systems
8 © 2022 Anaconda
Evasion/Adversarial Attacks
Protecting your systems
Designing an input to trick ML classification
9 © 2022 Anaconda
Evasion/Adversarial Attacks
Protecting your systems
● Formal methods
○ Good for mission-critical systems where attacks can mean significant costs or life-threatening
outcomes
○ Expensive and time-consuming
● Empirical defenses
○ Adversarial training
○ Input Modification (aka: input cleansing)
○ Drift/generalized detection
10 © 2022 Anaconda
Protecting your systems
Membership Inference Attacks
Devine the input data by observing the output of the model against a set of inputs.
Training
data
11 © 2022 Anaconda
Protecting your systems
Membership Inference Attacks
● Adversarial Training
● Avoid overfitting
○ Use Regularization Techniques
12 © 2022 Anaconda
Protecting your systems
Poisoning Attacks
Injecting bad training data to change model predictions/classifications
Training
data
13 © 2022 Anaconda
Protecting your systems
Poisoning Attacks
● Establish data provenance
○ Manual curation / known-good training data sets
● Robustify models
○ Iteratively minimize trimmed loss and retrain on random sets of clean and poisoned data
14 © 2022 Anaconda
Protecting your systems
Trojan Attacks
Embedding malicious weights into a Neural Network to create a pre-defined output
for certain inputs and expected outputs otherwise.
15 © 2022 Anaconda
Protecting your systems
Trojan Attacks
● Establish training data provenance
○ Create policies around using publicly available data sets
● Establish model provenance
○ Discourage use of pre-trained models for critical applications
16 © 2022 Anaconda
Supply Chain Attacks
17 © 2022 Anaconda
79%
OSS provides flexibility to customize
solutions to meet company’s needs
77%
OSS ensures my
organization has access to
the latest innovations
76%
OSS simplifies the process of
adopting a hybrid cloud
infrastructure
Advantages of Open-Source Software
92%
of all applications contain open-source
software
97%
of codebases contain open-
source software
95%
of IT organizations rely on
open-source software
From a RedHat survey of IT professionals:
From leading OSS security research:
Sources: RedHat, Linux Foundation, Synopsys, Snyk, Sonatype
18 © 2022 Anaconda
650%
Increase in cyberattacks targeting
open-source
$1.4MM
Average ransomware remediation
costs
49%
of organizations have a security
policy addressing open-source
Risks and Challenges
73%
of organizations are searching for
best practices to improve their
open-source security
Sources: Linux Foundation, NVD, Snyk, Sonatype, Sophos
19 © 2022 Anaconda
>395,000
Projects
46%
With Vulnerabilities
20 © 2022 Anaconda
46%
With Vulnerabilities
>395,000
Projects
11%
With Critical Vulnerabilities
21 © 2022 Anaconda
It’s never just the packages you are installing
22 © 2022 Anaconda
15,980
Unique Data Science Packages
Downloaded in August
1949
Had Known Vulnerabilities
556
Of the vulnerabilities were scored as
critical
We looked at the top 10 Canadian Companies
by Market Capitalization
4-202
Number of packages downloaded
per company with critical
vulnerabilities
23 © 2022 Anaconda
Avoiding Supply Chain Attacks
● Know what you are using
○ Inventory not only the root packages, but also all their dependencies
● Monitor new Common Vulnerabilities and Exposures (CVEs)
○ Identify new vulnerabilities in existing packages
● Use trusted repositories
○ Avoid typosquating and account hijack attacks
● Use trusted builds of packages
○ Build yourself or use a trusted build partner that signs their artifacts
24 © 2022 Anaconda
CVE growth
25,000
20,000
15,000
10,000
5,000
0
2016 2017 2018 2019 2020 2021
75% FALSE POSITIVES
25 © 2022 Anaconda
Anaconda - CVE Curation Flow
The National Institute of
Standards and
Technology(NIST) National
Vulnerability Database
(NVD)
CVE Data Source
Associating NVD CVE data
with packages in the
Anaconda Repository
Automated Matching
Anaconda staff review
NVD CVE data for accuracy
and then categorize, refine
and improve the reported
information. If possible,
CVEs are patched
Human Curation
Accurate CVE metadata
allows organizations to
filter out OSS packages
that don’t meet their
security requirements
Refined CVE Metadata
Goal: high-quality, accurate, and dependable CVE information
Performed by Anaconda Distribution Team
26 © 2022 Anaconda
Elements of OSS Security and Governance
Are you able to proactively keep high-risk
components out of your pipeline?
Do you have a trusted repository?
Do you know what is in your open-source pipeline?
Are you able to identify high-risk components in
your pipeline?
27 © 2022 Anaconda
Bringing open-source innovation
securely to the enterprise
✓ Centralized, secure, and trusted source for OSS
✓ Visibility into the software components of your pipeline
✓ Access to Anaconda-curated vulnerability data
✓ Automate enforcement of security and licensing requirements
✓ Create and maintain an audit trail
Act on high-risk components with access
to curated vulnerability data and details
Block high-risk components with
customizable and automated
security policy enforcement
Questions?
Thank You!
Kevin Goldsmith
Chief Technology Officer
About Anaconda
With more than 30 million users, Anaconda is the world’s most
popular data science platform and the foundation of modern
machine learning. We pioneered the use of Python for data
science, champion its vibrant community, and continue to
steward open-source projects that make tomorrow’s
innovations possible. Our enterprise-grade solutions enable
corporate, research, and academic institutions around the world
to harness the power of open-source for competitive
advantage, groundbreaking research, and a better world.
Visit https://www.anaconda.com to learn more.

More Related Content

Similar to What Vulnerabilities? How and why to secure your ML/AI Solutions

2017-07-12 GovLoop: New Era of Digital Security
2017-07-12 GovLoop: New Era of Digital Security2017-07-12 GovLoop: New Era of Digital Security
2017-07-12 GovLoop: New Era of Digital SecurityShawn Wells
 
Mobile Threat Protection: A Holistic Approach to Securing Mobile Data and Dev...
Mobile Threat Protection: A Holistic Approach to Securing Mobile Data and Dev...Mobile Threat Protection: A Holistic Approach to Securing Mobile Data and Dev...
Mobile Threat Protection: A Holistic Approach to Securing Mobile Data and Dev...Skycure
 
ECMDay2015 - Kent Agerlund - Secunia - 10 minutes is all it takes – Managing ...
ECMDay2015 - Kent Agerlund - Secunia - 10 minutes is all it takes – Managing ...ECMDay2015 - Kent Agerlund - Secunia - 10 minutes is all it takes – Managing ...
ECMDay2015 - Kent Agerlund - Secunia - 10 minutes is all it takes – Managing ...Kenny Buntinx
 
Rise of software supply chain attack
Rise of software supply chain attackRise of software supply chain attack
Rise of software supply chain attackYadnyawalkya Tale
 
Cyber security course in Kerala , Kochi
Cyber security course in Kerala ,  KochiCyber security course in Kerala ,  Kochi
Cyber security course in Kerala , Kochiamallblitz0
 
Protecting Pipeline DevOps and IaC
Protecting Pipeline DevOps and IaCProtecting Pipeline DevOps and IaC
Protecting Pipeline DevOps and IaCFernando Cardoso
 
TrendMicro - Security Designed for the Software-Defined Data Center
TrendMicro - Security Designed for the Software-Defined Data CenterTrendMicro - Security Designed for the Software-Defined Data Center
TrendMicro - Security Designed for the Software-Defined Data CenterVMUG IT
 
QRadar-XDR-Solution.pdf
QRadar-XDR-Solution.pdfQRadar-XDR-Solution.pdf
QRadar-XDR-Solution.pdfssuserf5beb3
 
PCI Compliance in the Cloud
PCI Compliance in the CloudPCI Compliance in the Cloud
PCI Compliance in the CloudControlCase
 
PCI Compliance in Cloud
PCI Compliance in CloudPCI Compliance in Cloud
PCI Compliance in CloudControlCase
 
PCI Compliance in Cloud
PCI Compliance in CloudPCI Compliance in Cloud
PCI Compliance in CloudControlCase
 
Keep Ahead of Evolving Cyberattacks with OPSWAT and F5 NGINX
Keep Ahead of Evolving Cyberattacks with OPSWAT and F5 NGINXKeep Ahead of Evolving Cyberattacks with OPSWAT and F5 NGINX
Keep Ahead of Evolving Cyberattacks with OPSWAT and F5 NGINXNGINX, Inc.
 
CONFidence2015: Real World Threat Hunting - Martin Nystrom
CONFidence2015: Real World Threat Hunting - Martin NystromCONFidence2015: Real World Threat Hunting - Martin Nystrom
CONFidence2015: Real World Threat Hunting - Martin NystromPROIDEA
 
HMI/SCADA 리스크 감소
HMI/SCADA 리스크 감소HMI/SCADA 리스크 감소
HMI/SCADA 리스크 감소GE코리아
 
Rombit LSEC IoTSecurity IoTSBOM CyberSec Europe 2022
Rombit LSEC IoTSecurity IoTSBOM CyberSec Europe 2022Rombit LSEC IoTSecurity IoTSBOM CyberSec Europe 2022
Rombit LSEC IoTSecurity IoTSBOM CyberSec Europe 2022Ulrich Seldeslachts
 
8 Top Cybersecurity Tools.pptx
8 Top Cybersecurity Tools.pptx8 Top Cybersecurity Tools.pptx
8 Top Cybersecurity Tools.pptxMetaorange
 

Similar to What Vulnerabilities? How and why to secure your ML/AI Solutions (20)

2017-07-12 GovLoop: New Era of Digital Security
2017-07-12 GovLoop: New Era of Digital Security2017-07-12 GovLoop: New Era of Digital Security
2017-07-12 GovLoop: New Era of Digital Security
 
Mobile Threat Protection: A Holistic Approach to Securing Mobile Data and Dev...
Mobile Threat Protection: A Holistic Approach to Securing Mobile Data and Dev...Mobile Threat Protection: A Holistic Approach to Securing Mobile Data and Dev...
Mobile Threat Protection: A Holistic Approach to Securing Mobile Data and Dev...
 
ECMDay2015 - Kent Agerlund - Secunia - 10 minutes is all it takes – Managing ...
ECMDay2015 - Kent Agerlund - Secunia - 10 minutes is all it takes – Managing ...ECMDay2015 - Kent Agerlund - Secunia - 10 minutes is all it takes – Managing ...
ECMDay2015 - Kent Agerlund - Secunia - 10 minutes is all it takes – Managing ...
 
Rise of software supply chain attack
Rise of software supply chain attackRise of software supply chain attack
Rise of software supply chain attack
 
Cyber security course in Kerala , Kochi
Cyber security course in Kerala ,  KochiCyber security course in Kerala ,  Kochi
Cyber security course in Kerala , Kochi
 
Protecting Pipeline DevOps and IaC
Protecting Pipeline DevOps and IaCProtecting Pipeline DevOps and IaC
Protecting Pipeline DevOps and IaC
 
TrendMicro - Security Designed for the Software-Defined Data Center
TrendMicro - Security Designed for the Software-Defined Data CenterTrendMicro - Security Designed for the Software-Defined Data Center
TrendMicro - Security Designed for the Software-Defined Data Center
 
QRadar-XDR-Solution.pdf
QRadar-XDR-Solution.pdfQRadar-XDR-Solution.pdf
QRadar-XDR-Solution.pdf
 
PCI Compliance in the Cloud
PCI Compliance in the CloudPCI Compliance in the Cloud
PCI Compliance in the Cloud
 
PCI Compliance in the Cloud
PCI Compliance in the CloudPCI Compliance in the Cloud
PCI Compliance in the Cloud
 
PCI Compliance in the Cloud
PCI Compliance in the CloudPCI Compliance in the Cloud
PCI Compliance in the Cloud
 
Partner Welcome Kit
Partner Welcome KitPartner Welcome Kit
Partner Welcome Kit
 
PCI Compliance in Cloud
PCI Compliance in CloudPCI Compliance in Cloud
PCI Compliance in Cloud
 
PCI Compliance in Cloud
PCI Compliance in CloudPCI Compliance in Cloud
PCI Compliance in Cloud
 
Keep Ahead of Evolving Cyberattacks with OPSWAT and F5 NGINX
Keep Ahead of Evolving Cyberattacks with OPSWAT and F5 NGINXKeep Ahead of Evolving Cyberattacks with OPSWAT and F5 NGINX
Keep Ahead of Evolving Cyberattacks with OPSWAT and F5 NGINX
 
CONFidence2015: Real World Threat Hunting - Martin Nystrom
CONFidence2015: Real World Threat Hunting - Martin NystromCONFidence2015: Real World Threat Hunting - Martin Nystrom
CONFidence2015: Real World Threat Hunting - Martin Nystrom
 
IoT Security
IoT SecurityIoT Security
IoT Security
 
HMI/SCADA 리스크 감소
HMI/SCADA 리스크 감소HMI/SCADA 리스크 감소
HMI/SCADA 리스크 감소
 
Rombit LSEC IoTSecurity IoTSBOM CyberSec Europe 2022
Rombit LSEC IoTSecurity IoTSBOM CyberSec Europe 2022Rombit LSEC IoTSecurity IoTSBOM CyberSec Europe 2022
Rombit LSEC IoTSecurity IoTSBOM CyberSec Europe 2022
 
8 Top Cybersecurity Tools.pptx
8 Top Cybersecurity Tools.pptx8 Top Cybersecurity Tools.pptx
8 Top Cybersecurity Tools.pptx
 

More from Kevin Goldsmith

It's teams all the way down - Design patterns for technology organizations
It's teams all the way down - Design patterns for technology organizationsIt's teams all the way down - Design patterns for technology organizations
It's teams all the way down - Design patterns for technology organizationsKevin Goldsmith
 
Raising the subject of raises
Raising the subject of raisesRaising the subject of raises
Raising the subject of raisesKevin Goldsmith
 
Managing partly distributed teams
Managing partly distributed teamsManaging partly distributed teams
Managing partly distributed teamsKevin Goldsmith
 
The (near) future of personal computers
The (near) future of personal computersThe (near) future of personal computers
The (near) future of personal computersKevin Goldsmith
 
Pixel Bender - 2011 AMD Fusion Conference
Pixel Bender - 2011 AMD Fusion ConferencePixel Bender - 2011 AMD Fusion Conference
Pixel Bender - 2011 AMD Fusion ConferenceKevin Goldsmith
 
It Is All About the Benjamins: the Real World Economics of HPC
It Is All About the Benjamins: the Real World Economics of HPCIt Is All About the Benjamins: the Real World Economics of HPC
It Is All About the Benjamins: the Real World Economics of HPCKevin Goldsmith
 
Parallelism, the Cloud, and the Tools of the Future for the next generation o...
Parallelism, the Cloud, and the Tools of the Future for the next generation o...Parallelism, the Cloud, and the Tools of the Future for the next generation o...
Parallelism, the Cloud, and the Tools of the Future for the next generation o...Kevin Goldsmith
 
Innovation and organization
Innovation and organizationInnovation and organization
Innovation and organizationKevin Goldsmith
 
Image and Video Processing Using Adobe Image Foundation's Toolkit For Flash -...
Image and Video Processing Using Adobe Image Foundation's Toolkit For Flash -...Image and Video Processing Using Adobe Image Foundation's Toolkit For Flash -...
Image and Video Processing Using Adobe Image Foundation's Toolkit For Flash -...Kevin Goldsmith
 
A Software Career (2017)
A Software Career (2017)A Software Career (2017)
A Software Career (2017)Kevin Goldsmith
 
When why and how to stop coding as your day job
When why and how to stop coding as your day jobWhen why and how to stop coding as your day job
When why and how to stop coding as your day jobKevin Goldsmith
 
Presenting to executives
Presenting to executivesPresenting to executives
Presenting to executivesKevin Goldsmith
 
Crafting a Mission and Vision For Your Team
Crafting a Mission and Vision For Your TeamCrafting a Mission and Vision For Your Team
Crafting a Mission and Vision For Your TeamKevin Goldsmith
 
You Are Doing Autonomy Wrong
You Are Doing Autonomy WrongYou Are Doing Autonomy Wrong
You Are Doing Autonomy WrongKevin Goldsmith
 
Organization, Architecture, Autonomy and Accountability (2020)
Organization, Architecture, Autonomy and Accountability (2020)Organization, Architecture, Autonomy and Accountability (2020)
Organization, Architecture, Autonomy and Accountability (2020)Kevin Goldsmith
 
Leading Distributed Teams - Stretch Conference 2020
Leading Distributed Teams - Stretch Conference 2020Leading Distributed Teams - Stretch Conference 2020
Leading Distributed Teams - Stretch Conference 2020Kevin Goldsmith
 

More from Kevin Goldsmith (20)

It's teams all the way down - Design patterns for technology organizations
It's teams all the way down - Design patterns for technology organizationsIt's teams all the way down - Design patterns for technology organizations
It's teams all the way down - Design patterns for technology organizations
 
Raising the subject of raises
Raising the subject of raisesRaising the subject of raises
Raising the subject of raises
 
Managing partly distributed teams
Managing partly distributed teamsManaging partly distributed teams
Managing partly distributed teams
 
Steal from the best
Steal from the bestSteal from the best
Steal from the best
 
What is Agile?
What is Agile?What is Agile?
What is Agile?
 
The (near) future of personal computers
The (near) future of personal computersThe (near) future of personal computers
The (near) future of personal computers
 
Pixel Bender - 2011 AMD Fusion Conference
Pixel Bender - 2011 AMD Fusion ConferencePixel Bender - 2011 AMD Fusion Conference
Pixel Bender - 2011 AMD Fusion Conference
 
It Is All About the Benjamins: the Real World Economics of HPC
It Is All About the Benjamins: the Real World Economics of HPCIt Is All About the Benjamins: the Real World Economics of HPC
It Is All About the Benjamins: the Real World Economics of HPC
 
Parallelism, the Cloud, and the Tools of the Future for the next generation o...
Parallelism, the Cloud, and the Tools of the Future for the next generation o...Parallelism, the Cloud, and the Tools of the Future for the next generation o...
Parallelism, the Cloud, and the Tools of the Future for the next generation o...
 
Innovation and organization
Innovation and organizationInnovation and organization
Innovation and organization
 
Image and Video Processing Using Adobe Image Foundation's Toolkit For Flash -...
Image and Video Processing Using Adobe Image Foundation's Toolkit For Flash -...Image and Video Processing Using Adobe Image Foundation's Toolkit For Flash -...
Image and Video Processing Using Adobe Image Foundation's Toolkit For Flash -...
 
My CMU alumni journey
My CMU alumni journeyMy CMU alumni journey
My CMU alumni journey
 
Building Lean
Building LeanBuilding Lean
Building Lean
 
A Software Career (2017)
A Software Career (2017)A Software Career (2017)
A Software Career (2017)
 
When why and how to stop coding as your day job
When why and how to stop coding as your day jobWhen why and how to stop coding as your day job
When why and how to stop coding as your day job
 
Presenting to executives
Presenting to executivesPresenting to executives
Presenting to executives
 
Crafting a Mission and Vision For Your Team
Crafting a Mission and Vision For Your TeamCrafting a Mission and Vision For Your Team
Crafting a Mission and Vision For Your Team
 
You Are Doing Autonomy Wrong
You Are Doing Autonomy WrongYou Are Doing Autonomy Wrong
You Are Doing Autonomy Wrong
 
Organization, Architecture, Autonomy and Accountability (2020)
Organization, Architecture, Autonomy and Accountability (2020)Organization, Architecture, Autonomy and Accountability (2020)
Organization, Architecture, Autonomy and Accountability (2020)
 
Leading Distributed Teams - Stretch Conference 2020
Leading Distributed Teams - Stretch Conference 2020Leading Distributed Teams - Stretch Conference 2020
Leading Distributed Teams - Stretch Conference 2020
 

Recently uploaded

9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home ServiceSapana Sha
 
办理(UWIC毕业证书)英国卡迪夫城市大学毕业证成绩单原版一比一
办理(UWIC毕业证书)英国卡迪夫城市大学毕业证成绩单原版一比一办理(UWIC毕业证书)英国卡迪夫城市大学毕业证成绩单原版一比一
办理(UWIC毕业证书)英国卡迪夫城市大学毕业证成绩单原版一比一F La
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...soniya singh
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...Boston Institute of Analytics
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubaihf8803863
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfLars Albertsson
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一F La
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queensdataanalyticsqueen03
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样vhwb25kk
 
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degreeyuu sss
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfBoston Institute of Analytics
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 

Recently uploaded (20)

9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service
 
办理(UWIC毕业证书)英国卡迪夫城市大学毕业证成绩单原版一比一
办理(UWIC毕业证书)英国卡迪夫城市大学毕业证成绩单原版一比一办理(UWIC毕业证书)英国卡迪夫城市大学毕业证成绩单原版一比一
办理(UWIC毕业证书)英国卡迪夫城市大学毕业证成绩单原版一比一
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdf
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queens
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
 
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
办美国阿肯色大学小石城分校毕业证成绩单pdf电子版制作修改#真实留信入库#永久存档#真实可查#diploma#degree
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 

What Vulnerabilities? How and why to secure your ML/AI Solutions

  • 1. 1 © 2022 Anaconda What Vulnerabilities? How (And Why) to Secure Your ML/AI Solutions Kevin Goldsmith, CTO October 7, 2022
  • 2. 2 © 2022 Anaconda We all (hopefully) understand that security is important for our production systems
  • 3. 3 © 2022 Anaconda While hardening our production data and systems, we don’t often think about our ML and AI pipelines because they are not directly consumed by users. EDW Backoffice Systems Data Scientists Data Models Production Customers
  • 4. 4 © 2022 Anaconda While hardening our production data and systems, we often don’t think about our ML and AI pipelines because they are not directly consumed by users. EDW Backoffice Systems Data Scientists Data Models Production Customers
  • 5. 5 © 2022 Anaconda While hardening our production data and systems, we often don’t think about our ML and AI pipelines because they are not directly consumed by users. EDW Backoffice Systems Data Scientists Data Models Production Customers
  • 6. 6 © 2022 Anaconda While hardening our production data and systems, we often don’t think about our ML and AI pipelines because they are not directly consumed by users. EDW Backoffice Systems Data Scientists Data Models Production Customers EVASION ATTACKS POISONING ATTACKS INFERENCE ATTACKS TROJAN ATTACKS SUPPLY CHAIN ATTACKS
  • 7. 7 © 2022 Anaconda Protecting your systems
  • 8. 8 © 2022 Anaconda Evasion/Adversarial Attacks Protecting your systems Designing an input to trick ML classification
  • 9. 9 © 2022 Anaconda Evasion/Adversarial Attacks Protecting your systems ● Formal methods ○ Good for mission-critical systems where attacks can mean significant costs or life-threatening outcomes ○ Expensive and time-consuming ● Empirical defenses ○ Adversarial training ○ Input Modification (aka: input cleansing) ○ Drift/generalized detection
  • 10. 10 © 2022 Anaconda Protecting your systems Membership Inference Attacks Devine the input data by observing the output of the model against a set of inputs. Training data
  • 11. 11 © 2022 Anaconda Protecting your systems Membership Inference Attacks ● Adversarial Training ● Avoid overfitting ○ Use Regularization Techniques
  • 12. 12 © 2022 Anaconda Protecting your systems Poisoning Attacks Injecting bad training data to change model predictions/classifications Training data
  • 13. 13 © 2022 Anaconda Protecting your systems Poisoning Attacks ● Establish data provenance ○ Manual curation / known-good training data sets ● Robustify models ○ Iteratively minimize trimmed loss and retrain on random sets of clean and poisoned data
  • 14. 14 © 2022 Anaconda Protecting your systems Trojan Attacks Embedding malicious weights into a Neural Network to create a pre-defined output for certain inputs and expected outputs otherwise.
  • 15. 15 © 2022 Anaconda Protecting your systems Trojan Attacks ● Establish training data provenance ○ Create policies around using publicly available data sets ● Establish model provenance ○ Discourage use of pre-trained models for critical applications
  • 16. 16 © 2022 Anaconda Supply Chain Attacks
  • 17. 17 © 2022 Anaconda 79% OSS provides flexibility to customize solutions to meet company’s needs 77% OSS ensures my organization has access to the latest innovations 76% OSS simplifies the process of adopting a hybrid cloud infrastructure Advantages of Open-Source Software 92% of all applications contain open-source software 97% of codebases contain open- source software 95% of IT organizations rely on open-source software From a RedHat survey of IT professionals: From leading OSS security research: Sources: RedHat, Linux Foundation, Synopsys, Snyk, Sonatype
  • 18. 18 © 2022 Anaconda 650% Increase in cyberattacks targeting open-source $1.4MM Average ransomware remediation costs 49% of organizations have a security policy addressing open-source Risks and Challenges 73% of organizations are searching for best practices to improve their open-source security Sources: Linux Foundation, NVD, Snyk, Sonatype, Sophos
  • 19. 19 © 2022 Anaconda >395,000 Projects 46% With Vulnerabilities
  • 20. 20 © 2022 Anaconda 46% With Vulnerabilities >395,000 Projects 11% With Critical Vulnerabilities
  • 21. 21 © 2022 Anaconda It’s never just the packages you are installing
  • 22. 22 © 2022 Anaconda 15,980 Unique Data Science Packages Downloaded in August 1949 Had Known Vulnerabilities 556 Of the vulnerabilities were scored as critical We looked at the top 10 Canadian Companies by Market Capitalization 4-202 Number of packages downloaded per company with critical vulnerabilities
  • 23. 23 © 2022 Anaconda Avoiding Supply Chain Attacks ● Know what you are using ○ Inventory not only the root packages, but also all their dependencies ● Monitor new Common Vulnerabilities and Exposures (CVEs) ○ Identify new vulnerabilities in existing packages ● Use trusted repositories ○ Avoid typosquating and account hijack attacks ● Use trusted builds of packages ○ Build yourself or use a trusted build partner that signs their artifacts
  • 24. 24 © 2022 Anaconda CVE growth 25,000 20,000 15,000 10,000 5,000 0 2016 2017 2018 2019 2020 2021 75% FALSE POSITIVES
  • 25. 25 © 2022 Anaconda Anaconda - CVE Curation Flow The National Institute of Standards and Technology(NIST) National Vulnerability Database (NVD) CVE Data Source Associating NVD CVE data with packages in the Anaconda Repository Automated Matching Anaconda staff review NVD CVE data for accuracy and then categorize, refine and improve the reported information. If possible, CVEs are patched Human Curation Accurate CVE metadata allows organizations to filter out OSS packages that don’t meet their security requirements Refined CVE Metadata Goal: high-quality, accurate, and dependable CVE information Performed by Anaconda Distribution Team
  • 26. 26 © 2022 Anaconda Elements of OSS Security and Governance Are you able to proactively keep high-risk components out of your pipeline? Do you have a trusted repository? Do you know what is in your open-source pipeline? Are you able to identify high-risk components in your pipeline?
  • 27. 27 © 2022 Anaconda Bringing open-source innovation securely to the enterprise ✓ Centralized, secure, and trusted source for OSS ✓ Visibility into the software components of your pipeline ✓ Access to Anaconda-curated vulnerability data ✓ Automate enforcement of security and licensing requirements ✓ Create and maintain an audit trail Act on high-risk components with access to curated vulnerability data and details Block high-risk components with customizable and automated security policy enforcement
  • 29. Thank You! Kevin Goldsmith Chief Technology Officer
  • 30. About Anaconda With more than 30 million users, Anaconda is the world’s most popular data science platform and the foundation of modern machine learning. We pioneered the use of Python for data science, champion its vibrant community, and continue to steward open-source projects that make tomorrow’s innovations possible. Our enterprise-grade solutions enable corporate, research, and academic institutions around the world to harness the power of open-source for competitive advantage, groundbreaking research, and a better world. Visit https://www.anaconda.com to learn more.