95 citations · 221 across the 15 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CR2024★ 2 cited
Defending Against Unforeseen Failure Modes with Latent Adversarial Training
Stephen Casper, Lennart Schulze, Oam Patel +1
Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack sur…
cs.CY2024★ 72 cited
Black-Box Access is Insufficient for Rigorous AI Audits
Stephen Casper, Carson Ezell, Charlotte Siegmann +18
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of access granted to a…