99 citations · 145 across the 41 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
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…
cs.CR2026
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…