conftrace_

runtime safety

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

safety-utility balance (1) reach-avoid probability (1) large language model (1) stochastic dynamical system (1) barrier function (1) hidden representation (1) jailbreak attack (1) uncertainty quantification (1) sparse representation (1)

Papers

Runtime Safety and Reach-avoid Prediction of Stochastic Systems via Observation-aware Barrier Functions AAAI 2026 Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models ICLR 2025