Persistent memory enables LLM agents to reuse prior experience, but creates a new security boundary: what an agent may remember is not what it should act on. We expose an unauthorized control path where edited low-trust evidence is consolidated into persistent memory, retrieved on a clean task, and used to drive a prot...
Kai-Sheng Fan, Yi-Shu Gao, Xun-Zhu Tang et al.· 0 citations
Retrieval-augmented generation (RAG) aggregates evidence from multiple external documents, yet this joint integration creates an underexamined vulnerability: attack effects absent in individual documents can emerge through set-level composition. Existing coordinated attacks do not explicitly enforce that every proper s...
Kai-Sheng Fan, Yi-Shu Gao, Xun-Zhu Tang et al.· 0 citations
It is argued that AI coding assistants should not only be evaluated by the code they generate, but also by how they mediate the transfer of that code into software artifacts, and soft barriers are proposed as one class of handoff-aware mechanisms.
I. E. Olatunji, Albérick Euraste Djiré, Jacques Klein et al.· 1 citation
It is revealed that scaled encoders successfully absorb substantial representation load while still converging on the correct family of solutions, and this ability to adapt to varying surface forms is what truly matters for usability and generalizability in LLM and agentic applications.
P. Rajput, Abdoul Aziz Bonkoungou, Albérick Euraste Djiré et al.· 0 citations
The results recast package hallucination as both a measurement problem and a decoding-time control problem, and they demonstrate that the choice of defense must be matched to the threat model and recommendation utility.
Albérick Euraste Djiré, I. E. Olatunji, Melissa Tessa et al.· Proceedings of the 41st IEEE...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
