Safety Of LLMs: Training Data Attribution And Efficient Search
Anastasiia Kucherenko investigates Safety Of LLMs: Training Data Attribution And Efficient Search.
Summary
No summary yet — watch the video above, or open it on YouTube.
Related talks
Videos·46 min
Jérémie AMSELLEM
Jérémie AMSELLEM analyzes 🇫🇷 Enhancing Training and Pentesting tasks with LLMs: what can and can’t be done.
trainingpentestingenhancing+2
Briefings·32 min
Kyle Avery
Engineers share architectures for fine-tuning open source language models to uncover zero-day vulnerabilities across binary targets.
aimalware-analysisevasion+2
Black Hat·39 min
Jason Stanley
Industry experts analyze emerging threats surrounding SecTor 2025 | Security and Safety Testing for Agentic AI.
safetysectoragentic