In this episode, security researcher Nicholas Carlini of Google DeepMind delves into his extensive work on adversarial machine learning and cybersecurity.

Watch Episode Here

Read Episode Description

In this episode, security researcher Nicholas Carlini of Google DeepMind delves into his extensive work on adversarial machine learning and cybersecurity. He discusses his pioneering contributions, which include developing attacks that have challenged the defenses of image classifiers and exploring the robustness of neural networks. Carlini details the inherent difficulties of defending against adversarial attacks, the role of human intuition in his work, and the potential of scaling attack methodologies using language models. He also addresses the broader implications of open-source AI and the complexities of balancing security with accessibility in emerging AI technologies.

SPONSORS:
SafeBase: SafeBase is the leading trust-centered platform for enterprise security. Streamline workflows, automate questionnaire responses, and integrate with tools like Slack and Salesforce to eliminate friction in the review process. With rich analytics and customizable settings, SafeBase scales to complex use cases while showcasing security's impact on deal acceleration. Trusted by companies like OpenAI, SafeBase ensures value in just 16 days post-launch. Learn more at https://safebase.io/podcast

Oracle Cloud Infrastructure (OCI): Oracle's next-generation cloud platform delivers blazing-fast AI and ML performance with 50% less for compute and 80% less for outbound networking compared to other cloud providers. OCI powers industry leaders like Vodafone and Thomson Reuters with secure infrastructure and application development capabilities. New U.S. customers can get their cloud bill cut in half by switching to OCI before March 31, 2024 at https://oracle.com/cognitive

Shopify: Shopify is revolutionizing online selling with its market-leading checkout system and robust API ecosystem. Its exclusive library of cutting-edge AI apps empowers e-commerce businesses to thrive in a competitive market. Cognitive Revolution listeners can try Shopify for just $1 per month at https://shopify.com/cognitive

NetSuite: Over 41,000 businesses trust NetSuite by Oracle, the #1 cloud ERP, to future-proof their operations. With a unified platform for accounting, financial management, inventory, and HR, NetSuite provides real-time insights and forecasting to help you make quick, informed decisions. Whether you're earning millions or hundreds of millions, NetSuite empowers you to tackle challenges and seize opportunities. Download the free CFO's guide to AI and machine learning at https://netsuite.com/cognitive


RECOMMENDED PODCAST: Second Opinion
Join Christina Farr, Ash Zenooz and Luba Greenwood as they bring influential entrepreneurs, experts and investors into the ring for candid conversations at the frontlines of healthcare and digital health every week.
Spotify: https://open.spotify.com/show/...
Apple: https://podcasts.apple.com/us/...
YouTube: https://www.youtube.com/@Secon...

CHAPTERS:
(00:00) Teaser
(00:55) About the Episode
(04:54) Introduction and Guest Welcome
(05:32) Nicholas Carlini's Contributions to Cybersecurity
(07:15) Breaking Defenses: Techniques and Challenges
(09:08) Adversarial Examples and Optimization
(11:22) Exploring Unfine Tunable Models
(13:25) Understanding Attack Strategies (Part 1)
(18:22) Sponsors: SafeBase | Oracle Cloud Infrastructure (OCI)
(20:58) Understanding Attack Strategies (Part 2)
(30:39) Compute Requirements for Different Attacks
(32:51) Sponsors: Shopify | NetSuite
(35:39) Data Poisoning in Machine Learning
(39:39) High-Dimensional Spaces and Attack Intuitions
(54:50) Understanding Loss Surfaces and Robustness
(55:35) Distillation and Gradient Masking Defenses
(57:24) Breaking Gradient-Based Defenses
(01:01:05) Challenges in Open Source Model Safety
(01:10:16) Unlearning and Fact Editing in Models
(01:20:59) Adversarial Examples and Human Robustness
(01:42:28) Long-Term Memory and Model Robustness
(01:45:44) Preventing Unauthorized Actions in AI Systems
(01:46:19) Challenges in Building Robust AI Systems
(01:48:25) Exploring Cryptography and AI Robustness
(02:00:13) Human Factors in Security Systems
(02:05:55) The Future of AI Security and Open Source
(02:06:45) Scaling AI Security Research
(02:23:28) Balancing Security and Open Source in AI
(02:31:28) Final Thoughts on AI Security and Policy
(02:33:16) Outro

SOCIAL LINKS:
Website: https://www.cognitiverevolutio...
Twitter (Podcast): https://x.com/cogrev_podcast
Twitter (Nathan): https://x.com/labenz
LinkedIn: https://linkedin.com/in/nathan...
Youtube: https://youtube.com/@Cognitive...
Apple: https://podcasts.apple.com/de/...
Spotify: https://open.spotify.com/show/...

PRODUCED BY:
https://aipodcast.ing