Stanford AI Security Conference Videos Released
wunderwuzzi23 · x · 2026-07-20
All talks from the Stanford Real-World AI Security Conference have been uploaded to YouTube. The author highlights a few must-watch sessions: - **AI Agents Enable Adaptive Computer Worms** (Nicolas Papernot) - **The Road to Hell Is Paved with Helpful Agents** (Vitaly Shmatikov) - **Evaluating and Defending Against Prompt Injection Attacks** (Edoardo Debenedetti) Overall, the conference covers multiple facets of AI security, including novel attack surfaces introduced by agents, prompt injection defenses, and broader real-world security research.
More from Safety
- Judge approves Anthropic’s $1.5 billion copyright settlement, a U.S. record — Polymarket · 2026-07-21
- New MCP directory RepoAI scores servers on trust, auth, and dangerous tools — Low_Location1261 · 2026-07-21
- Sriram Krishnan says open-weight models are easier to secure because anyone can inspect them — pstAsiatech · 2026-07-21
- Anthropic’s $1.5B copyright settlement gets final court approval — TechCrunch AI · 2026-07-21
- A Berlin workshop linked crypto, security, and AI safety to tackle misbehaving agents — allisondman · 2026-07-21
- AI systems are pushing data governance from datasets to live flows — ProfChesterman · 2026-07-21