S4E23 – AI Agents Escape Multiple...
S4E23 – AI Agents Escape Multiple Frontier Labs

The Adversarial Podcast di Jerry Perullo, Sounil Yu, Mario Duarte

Note sull'episodio

Chapters

00:00 Introduction to AI security challenges

02:05 Recent hacking incidents involving Hugging Face and Anthropic

04:01 How AI models find ways to cheat and bypass constraints

05:56 The challenge of containment and governance in AI safety

08:00 Lessons from recent AI security breaches

10:01 The role of human oversight in AI security testing

12:03 Cost and effectiveness of offensive AI security measures

13:54 Implications for critical infrastructure and national security

16:03 Policy and regulatory impacts on AI safety

17:52 Future strategies for AI containment and defense

20:11 Conclusion and key takeaways

HuggingFace: Anatomy of a Frontier La ... 

Leggi dettagli
Parole chiave
cybercybersecurityciso