- DEF CON 34 Notes: 15 Talks on AI Security, Agentic Systems, and Red Teaming
Almost every talk had a similar throughline: agents attacking, agents getting attacked, and agents standing between an alert and the human who has…
- Zealot — An Autonomous Cloud Offensive Multi-Agent System
In November 2025, Anthropic disclosed a state-sponsored operation where AI didn't assist human attackers — it was the attacker, executing 80-90% of…
- X-Ray Your Agents — Pentesting MCPs, Skills, and the Plugin Supply Chain
Agents now run with thousands of third-party plugins — MCP servers, Claude skills, GPT actions, IDE extensions — and the prevailing trust model is…
- Vibe Coding Your Way to a Fully Functional Open-Source Intelligence Platform
Most vibe-coding demos stop at TODO apps and landing pages. This 150-minute workshop went further: participants used modern AI coding agents to…
- This Wasn't AI Generated — Principles for Breaking Generative Watermarks
Google's SynthID watermark invisibly tags content generated by its models (Nano Banana, Gemini, etc.) — when asked whether an image is AI-generated,…
- Remote Badge Cloning with the Flipper Zero
Traditional RFID badge cloning methods require you to be within 3 feet of your target. So how do you conduct a physical penetration test and clone a…
- Reconstructing Red Team Engagements — Developing Your Own Red Agent
With recent advances in AI, LLMs are increasingly applied to red team engagements — but mostly just to automate operations during the engagement…
- Pwning Agentic Browsers with PleaseFix — A New Vulnerability Class for 0-Click Takeover
Stav Cohen's research focuses on breaking, and then fixing, AI agents — security vulnerabilities across agentic AI systems, LLM-powered…
- Overcast — Video OSINT Agent. Point It at 100 Videos, Ask Anything.
Conference talks, earnings calls, product demos, training videos — organizations put hours of footage online every week, full of things they didn't…
- Hacking the Human-in-the-Loop
AI defenses are only as good as the analysts training them. This session exposes how attackers manipulate SOC analyst behavior to silently degrade…
- Evading LLM Detection
From OKX (fintech and crypto company). Software supply chain attacks are no longer a distant threat — they're happening at scale and are extremely…
- Can AI do Novel Security Research
We all know AI can find bugs. After a decade of research, the harder question: can an autonomous system invent new attack techniques, and use them…
- A Billion-User Blast Radius — Owning ChatGPT's Secure Sandbox
OpenAI designed ChatGPT's container sandbox as a secure runtime environment, enforcing full network isolation, strict execution timeouts, and an AI…
- Automated Discovery of Prompt Injection Vulnerabilities via Mutated Prompt Generation
Finding one prompt injection isn't the end goal; checking how many variants still bypass your safeguarding layers is the new target. This talk…
- AOBTD — AI-Driven DAST Scanner
Most DAST tools fire payloads at parameters with no idea what the app is — they catch the obvious stuff but miss what actually needs context. Newer…
- AI Pipeline for N-days Weaponization
Most agentic exploit pipelines stall when there's no public PoC — they search, find nothing, and spin. This talk demos a multi-agent system that…