2 papers
cs.CR2026
Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors
Naci Cankaya, Jakub KryÅ, Jonathan Ng +2
In preparation for potential international agreements on artificial intelligence, the development of verification infrastructure for AI data centres is vital. We propose a method f…
cs.CR2024
Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities
Andrey Anurin, Jonathan Ng, Kibo Schaffer +2
LLM agents have the potential to revolutionize defensive cyber operations, but their offensive capabilities are not yet fully understood. To prepare for emerging threats, model dev…