conftrace_

safety filter

8 papers

Explore in graph

Co-occurring keywords

control barrier function (39) large language model (13587) adversarial prompt (65) unsupervised feedback (1) log perplexity (1) collaborative optimization (6) safe control (24) disinformation detection (66) reachability analysis (35) system level synthesis (4)

Papers

TombRaider: Entering the Vault of History to Jailbreak Large Language Models EMNLP 2025
Resolving Conflicting Constraints in Multi-Agent Reinforcement Learning with Layered Safety RSS 2025
Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation ACL 2025
Dynamic Safety in Complex Environments: Synthesizing Safety Filters with Poisson’s Equation RSS 2025
Safety filters for black-box dynamical systems by learning discriminating hyperplanes L4DC 2024
ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-Image Deep Generation NIPS 2024
Time-Reversal Provides Unsupervised Feedback to LLMs NIPS 2024
Predictive safety filter using system level synthesis L4DC 2023