Adversarial Content

S4E23 – AI Agents Escape the Lab, Anubis Hits Fair | RSS.com 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 Implic

There's no need to reprise the Hugging Face incident. The press has the narrative, and Hugging Face published an excellent technical timeline. OpenAI models running with their guardrails deliberately lowered for a cybersecurity capability evaluation broke out of their sandbox, reached the open Internet, and hacked Hugging Face to steal the answers to their own test. The only detail that really needs to be clarified for those of you of my age is that "Hugging Face" is a successful startup valued

Adversarial Podcast Ep. 27 - Is AI necessary for c | RSS.com Episode 27: AI Hype, Cyber Stocks, and the End of Trust Jerry Perullo, Mario Duarte, and Sounil Yu dive into the tension between AI buzz and cybersecurity substance in this wide-ranging episode covering everything from investing trends to browser hygiene. Topics include: * The AI fundraising filter If you’re pitching a cybersecurity startup today, you’d better have an AI story—even if your product doesn’t need it. The hosts