CogniDir is introduced, an adaptive distributional learning framework that reformulates robust detection as a dynamic data mixture optimization problem for social media content safety by formalizing mechanism-specific cognitive adversarial paradigms to systematically expose deep-seated detector vulnerabilities.
Zhao Tong, Chun-Lin Gong, Yimeng Gu et al.· 3 citations
This work introduces \textsc{JailbreakSkill}, a skill-centric framework for scaling automated red-teaming through reusable and continuously evolving attack capabilities, which packages existing attack strategies into modular, agent-ready skills that can be directly reused and adaptively selected across tasks and target...
Xiaoyu Wen, Jiajia Li, Zhida He et al.· 2 citations
This work argues that agentic risk is progressive: it can enter at four loci of the agent control loop--skill admission, invocation-time intent, execution-time effect, and post-action consequence--while a denied dangerous objective can reappear across surface forms, tools, or turns.
Kai Wang, Zeming Wei, Biaojie Zeng et al.· 0 citations
This work presents SkillSafetyBench, a runnable benchmark for evaluating skill-facing safety failures, and suggests that agent safety depends not only on model-level alignment, but also on how agents interpret skills, trust workflow context, and act through executable environments.
RLShield is a dynamic jailbreak detection framework that employs reinforcement learning for adaptive threshold selection and incorporates three key innovations: a dynamic retrieval and LLM-based rewriting module to simulate diverse adversarial contexts; a cross-layer representation analysis to pinpoint safety-critical...
Zhao Tong, Pengfei Yang, Yimeng Gu et al.· Annual Meeting of the Associ...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
