EASE (Entropy-Adaptive Distribution Shaping for Evasion), a training-free and detector-agnostic framework for evading AIGT detectors that computes predictive entropy directly from the source LLM's next-token distribution and uses it to adapt both logit perturbation and sampling temperature, without detector feedback or...
Ji-Cheng Zhou, Kahim Wong, Jia-Long Wang et al.· 0 citations
Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer the next call. Vetting an artifact before admission does not settle this. A safe variant and a leaking variant can produce the same admission evidenc...
Feng-Peng Li, Qi-Zhou Wang, Yu-Ke Hu et al.· 1 citation
Alg is introduced, an end-to-end multi-agent simulacra framework for studying reviewer assignment integrity by holding the conference environment fixed and configuring LLM-driven reviewer agents with honest or collusive policies, and an affinity-guided collusive bidding strategy that uses mutual reviewer-paper affiniti...
Ji-Cheng Zhou, Ke-Mou Li, Kahim Wong et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.