9 citations · 18 across the 34 of their papers we have counts for
3 papers · 1 filter
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…
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…
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
Charbel El Feghali, Arkil Patel, Nicholas Meade +3
Open-weight Large Language Models (LLMs) enable scientific progress and broad deployment. However, they make it difficult to control access to sensitive capabilities. Current pract…