Floating-point arithmetic under the IEEE-754 standard is the foundation of modern numerical computing, yet as computation increasingly migrates to untrusted environments—such as outsourced HPC—verifying that floating-point operations are executed faithfully becomes critical. Succinct non-interactive arguments of knowle...
Wen-Jie Qu, Zi-Hao Zhang, Jia-Heng Zhang· Proceedings of the 2026 ACM...· 0 citations
This paper presents MetaPI, an extensible toolkit that automatically identifies plausible injection points, generates realistic attack objectives, optimizes adaptive payloads, and validates attacks in the real environment, and enables scalable and consistent security evaluation across diverse and evolving agent ecosyst...
Pei-Ran Wang, Chong Xiang, Wen-Jie Qu et al.· 0 citations
Wide adoption of machine learning has created growing policy and regulatory demand for protecting sensitive training data, with differential privacy (DP) emerging as a key mechanism. Yet a less-studied problem is how to certify the faithful execution of DP during training: an external verifier should be able to check t...
SafeClawArena is developed, a benchmark of 406 adversarial tasks executed in containerized replicas of real agent platforms with canary-marked credentials and evaluated via automated taint tracking across nine output channels, exposing the inadequacy of current defenses and suggesting directions for future hardening.