The Threat Intelligence Podcast
av The GenAI Security Project
Anthropic's Eval Escapes + AI Finds HAWK Flaw + OWASP Quantum…
Om denne podkasten
Real-world threat intelligence for the age of generative AI—without the hype. Hosted by Rachel James and Dr. Bryan Nakayama of the GenAI Security Project, this show cuts through vendor marketing to explain what's actually happening when threat actors use AI—from ransomware crews wiring malware to AI models, to nation-states building agent-driven attacks. For security practitioners and anyone tracking how AI is really reshaping the threat landscape.
Produced by the Gen AI Security Project with help from RumRunner Media.
Episoder
De 20 nyeste av 24 episoder
- Anthropic's Eval Escapes + AI Finds HAWK Flaw + OWASP Quantum Security Project | Ep 13 · 24 min · Episode 13**Originally Recorded August 11, 2026** An AI found a real flaw in a post-quantum signature scheme that human experts missed for years. So what should defenders do on Monday?…
- PHP Flaw Hype + What Insurance Claims Show | Ep 23 · 21 min · Episode 23Did AI really find the PHP vulnerabilities that put roughly 70% of websites in the spotlight, or was it the human experts behind the discovery? Rachel James and Dr. Bryan…
- Is the 80/20 Rule of AI Hacking Flipping? | Ep 22 · 26 min · Episode 22Does an attacker still need to be 80% expert to get a 20% boost from AI? After almost three years of hands-on research, the answer may be changing. Rachel James talks with Andrea…
- Hunting AI Malware: CAIRN, Closed Quorum & Anti-Analysis Prompt Injection | Ep21 · 25 min · Episode 21The attacker deploys the malware, then sits back and lets AI models vote on what it does next. Ryan Fetterman, AI and security researcher at Cisco Talos and author of The Threat…
- When AI Models Vote on the Attack | Ep 20 · 26 min · Episode 20One AI model can be rate-limited, blocked, or refuse to cooperate. So what if the attacker uses four? Rachel James and Dr. Bryan Nakayama break down Cisco Talos's research on…
- Malicious Agent Skills: Authorized Actions, Hidden Intent & the Skills Factory | Ep 19 · 27 min · Episode 19AI agents are only as trustworthy as the skills they load. Yi Liu, AI research engineer at Common Defense and PhD researcher at Nanyang Technological University, joins Rachel…
- Rogue AI Agents: Reward Hacking, Not Rebellion | Ep 18 · 19 min · Episode 18OpenAI and Anthropic both disclosed incidents where AI models being tested for offensive cybersecurity capability broke out of their sandboxes and hacked real companies. It…
- We Don't See Autonomy Yet: Nation-States, AI Agents & the New Threat Intelligence Reports | Ep 17 · 30 min · Sesong 17 Episode 17Anthropic and Google Threat Intelligence just released landmark reports on how nation-state and criminal groups are actually using AI right now. The headline finding: it's not…
- Threat Actors Don't Trust AI Either: ICS Exploits & the Botnet That Waits for Permission | Ep 16 · 18 min · Episode 16Five federal agencies just issued a joint advisory: threat actors are using AI to write exploit scripts targeting the industrial controllers that run water, power, and…
- AI Malware Reality Check: Aurora, Fake Criminal AI & the Hype Gap | Ep 15 · 24 min · Episode 15Three threat intel stories that contradict each other—and that's exactly the point. We expose the Aurora ransomware crew's hands-on use of Cursor AI, break down why vendor…
- Weaponizing Trust: How Nation-States and Criminals Are Hiding Inside the Tools You Already Use | Episode 14 · 17 min · Episode 14Two reports, one uncomfortable theme: attackers aren't doing new things — they're doing old things inside the tools we already trust. Rachel James and Dr. Bryan Nakayama read the…
- AI Just Cracked Post-Quantum Crypto. Is Your Security Team Ready? | Episode 13 · 24 minTwo frontier AI labs had autonomous agents attack real-world systems without their knowledge — one incident went undetected for three months. On this episode of the OWASP GenAI…
- The AI Hacker Myth: 3 Days, 6 Minutes, and One Very Buggy Botnet | Episode 12 · 31 min · Episode 12Three headlines, one question: is AI doing something new, or just typing faster? Rachel James and Dr. Brian Nakayama read the fine print with host Dave Hatt. 72-hour AWS…
- Open AI’s Hack of Hugging Face | Episode 11 · 32 min · Sesong 1 Episode 11A model was asked to prove how good it was at hacking. It decided the fastest route was to break out of its sandbox and steal the answer sheet. That's the Hugging Face incident…
- Supply Chain Attacks, Vibe Coding Risks & the Five Eyes AI Warning | Episode 10 · 27 minHosts Rachel James and Dr. Bryan Nakayama unpack why supply chain attacks are exploding in the age of vibe coding — when AI writes code faster than anyone can security-review it…
- The First AI-Run Ransomware Attack & How to Tell a Bot Is Attacking You | Episode 9 · 16 minHosts Rachel James and Dr. Bryan Nakayama break down "Jade Puffer" — what researchers at Sysdig call the first end-to-end agentic ransomware operation, with an LLM driving every…
- Inside Anthropic's Threat Report: The AI Risk Enablement Score & the Rise of Orchestration | Episode 8 · 27 minHosts Rachel James and Dr. Bryan Nakayama dig into Anthropic's June threat report and its first-ever AI Risk Enablement Score (ARES) — built from 832 banned accounts and 14,000…
- Anthropic's Fable & Mythos Shutdown | Episode 7 · 24 minHosts Rachel James and Dr. Bryan Nakayama unpack a world first: on June 12th the US government had Anthropic pull Fable 5 and Mythos 5 worldwide — not banning a chip or a weapon…
- Meta AI Account Takeovers & AI-Discovered Zero-Days | Episode 6 · 23 minHosts Rachel James and Dr. Bryan Nakayama break down a prompt-injection flaw that let attackers hijack Instagram accounts through Meta's AI support assistant — and a new Google…
- MITRE ATLAS and the OWASP Top Ten: The What and the How of AI Security | Ep 5 · 22 min · Episode 5Told to defend your company's GenAI, and not sure which framework to start with? Rachel James and Dr. Bryan Nakayama explain MITRE ATLAS and the OWASP Top Ten for LLM…








