Dmitrijs Trizna
dtrizna.bsky.social
Dmitrijs Trizna
@dtrizna.bsky.social
Cyber-security and AI research | ex-Microsoft | Founding AI Researcher @ Stealth | Agentic AI and adversarial ML for cyber-threat detection
Reposted by Dmitrijs Trizna
Presenting *Ensemble Everything Everywhere* at NeurIPS AdvML'24 workshop today! 🔥

Come by today at 10.40-12.00 in East Ballroom C to ask me about:
1) 🏰 bio-inspired naturally robust models
2) 🎓 Interpretability & robustness
3) 🖼️ building a generator for free
4) 😵‍💫 attacking GPT-4, Claude & Gemini
December 14, 2024 at 4:04 PM
Today the term "AI #redteam" almost exclusively means "security testing of LLM-powered applications". While this focus is important, it seems too narrow, especially when considering the scope of conventional Red Teaming. #infosec
November 20, 2024 at 10:05 AM