Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security risk from attackers who plant poisoned content in the pretraining data. We show for the first time that such poisoning can plant a remote code execution backdoor in an agent, causing it to execute attack...
Xin Hu, Ping-Bang Hu, Chloe Loughridge et al.· 0 citations
Agent4Sci is introduced, a long-horizon testbed for measuring how far today's agents can improve the published best models on scientific ML benchmarks, spanning 20 benchmarks across 11 domains and gives the community a way to track and push frontier agents from ML engineering toward domain insight on real-world ML-for-...
Ming Zhong, Stacy Li, Nicholas Carlini et al.· 0 citations
This paper introduces CryptanalysisBench, 191 tasks across six families of cryptographic primitives drawn primarily from four NIST standardization competitions, and releases CryptanalysisBench as a tool to help track if (or when) AI cryptanalysis becomes a serious factor and as a scaffold for stress-testing candidate s...
Lukas Fluri, Avital Shafran, Nicholas Carlini et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.