Showing 2026Show all
2 papers · 1 filter
cs.CL2026
TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling
Jiaqian Li, Yanshu Li, Boxuan Zhang +2
LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long before they surface in the fin…
cs.CL2026
RTD-Guard: A Black-Box Textual Adversarial Detection Framework via Replacement Token Detection
He Zhu, Yanshu Li, Wen Liu +1
Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead deep learning models…