Machine Learning and Artificial Intelligence Security Risk: Categorizing Attacks and Failure Modes

Focused View

Diana Kelley

1:11:36

302 View

1. Introduction

001. Machine learning security concerns.mp4

01:21

002. What you should know.mp4

00:25

2. Machine Learning Foundations

003. How systems can fail and how to protect th.mp4

03:22

004. Why does ML security matter.mp4

05:41

005. Attacks vs. unintentional failure modes.mp4

02:59

006. Security goals for ML CIA.mp4

02:45

3. Intentional Failure Modes Attacks

007. Perturbation attacks and AUPs.mp4

03:31

008. Poisoning attacks.mp4

03:11

009. Reprogramming neural nets.mp4

01:39

010. Physical domain (3D adversarial objec.mp4

02:34

011. Supply chain attacks.mp4

02:42

012. Model inversion.mp4

03:12

013. System manipulation.mp4

03:02

014. Membership inference and model steali.mp4

02:03

015. Backdoors and existing exploits.mp4

02:19

4. Unintentional Failure Modes Intrinsic Design Flaws

016. Reward hacking.mp4

02:16

017. Side effects in rein.mp4

02:30

018. Distributional shift.mp4

03:01

019. Overfitting underfit.mp4

02:46

020. Data bias considerat.mp4

04:48

5. Building Resilient ML

021. Effective techniques for building resilience in M.mp4

02:33

022. ML dataset hygiene.mp4

04:26

023. ML adversarial training.mp4

04:02

024. ML access control to APIs.mp4

02:56

6. Conclusion

025. Next steps.mp4

01:32

Description

From predicting medical outcomes to managing retirement funds, we put a lot of trust in machine learning (ML) and artificial intelligence (AI) technology, even though we know they are vulnerable to attacks, and that sometimes they can completely fail us. In this course, instructor Diana Kelley pulls real-world examples from the latest ML research and walks through ways that ML and AI can fail, providing pointers on how to design, build, and maintain resilient systems.

Learn about intentional failures caused by attacks and unintentional failures caused by design flaws and implementation issues. Security threats and privacy risks are serious, but with the right tools and preparation you can set yourself up to reduce them. Diana explains some of the most effective approaches and techniques for building robust and resilient ML, such as dataset hygiene, adversarial training, and access control to APIs.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Machine Learning

Artificial Intelligence

Cyber Security

Diana Kelley

Instructor's Courses

Diana Kelley is the CSO2 (Chief Strategy Officer/Chief Security Officer) and co-founder of Cybrize. She also serves on the boards of Cyber Future Foundation, WiCyS, and The Executive Women’s Forum (EWF). Diana was Cybersecurity Field CTO for Microsoft, Global Executive Security Advisor at IBM Security, GM at Symantec, VP at Burton Group (now Gartner), a Manager at KPMG, CTO and co-founder of SecurityCurve, and Chief vCISO at SaltCybersecurity Her extensive volunteer work has included serving on the ACM Ethics & Plagiarism Committee, Cybersecurity Committee Advisor at CompTIA, CTO and Board Member at Sightline Security, Advisory Board Chair at WOPLLI Technologies, Advisory Council member Bartlett College of Science and Mathematics, Bridgewater State University, and RSAC US Program Committee. She is a sought-after keynote speaker, the host of BrightTALK’s The (Security) Balancing Act, co-author of the books Practical Cybersecurity Architecture and Cryptographic Libraries for Developers, has been a lecturer at Boston College's Masters program in cybersecurity, the EWF 2020 Executive of the Year and EWF Conference Chair 2021 and 2022, an SCMedia Power Player, and one of Cybersecurity Ventures 100 Fascinating Females Fighting Cybercrime.

Linkedin Learning

View courses Linkedin Learning

LinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications. It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.