GCG

Researchers trained deep MLPs to memorize secret binary strings and found that naturally learned behaviors resist detection by both human-made input-optimization algorithms and learned algorithms, pos…

Researchers have introduced PaperGuard, the first comprehensive benchmark designed to systematically evaluate and defend AI-generated peer review against domain-specific, cross-modal attacks. The fram…

Researchers introduced Frost Training, a method that improves Monte Carlo-based policy optimization for Cross-Entropy Games by exploiting the gradient of the reward function in embedding space. The te…