99 citations · 145 across the 41 of their papers we have counts for
47 papers
Visual Memory Attacks Can Persist Through The KV Cache
David Dobre, Leo Schwinn, Gauthier Gidel +3
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input continue to steer a model even aft…
Continual Enterprise World Model Discovery in Dynamic Systems
Shambhavi Mishra, David Vazquez, Perouz Taslakian +3
In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business rules that are not built into the platfor…
Backdoor Decontamination Dynamics in LLM Agents
Gabriel Huang, Abhay Puri, Léo Boisvert +4
Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defender…
PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
Shubham Gupta, Nazanin Mohammadi Sepahvand, Abhinav Kumar +6
As LLM agents evolve from single-user assistants into shared organizational infrastructure, new privacy risks emerge: inappropriate information may not only be exposed through outp…
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3
AI agents acting on behalf of users are constantly making decisions, and for users to trust their agents, those decisions must align with what they actually want. Privacy is an imp…
MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research Agents
Alexander Gurung, Spandana Gella, Alexandre Drouin +3
Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external queries may leak sensitive in…