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.CR2026
Bit-Exact AI Inference Verification Without Performance Tradeoffs
Naci Cankaya
Verifying claims about AI workloads is a prerequisite for credible AI governance of covert adversaries (who comply with monitoring only when detection likelihood is high), yet the…