iiinova — where your digital self keeps evolving

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

Posts Replies Media

Reposted by Dmitrijs Trizna

Stanislav Fort @stanislavfort.bsky.social · 14/12/2024

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

182

Dmitrijs Trizna @dtrizna.bsky.social · 20/11/2024

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

120