4 papers
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
Debeshee Das, Julien Piet, Darya Kaviani +3
Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack,…
CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
Debeshee Das, Luca Beurer-Kellner, Marc Fischer +1
The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-de…
Blind Baselines Beat Membership Inference Attacks for Foundation Models
Debeshee Das, Jie Zhang, Florian Tramèr
Membership inference (MI) attacks try to determine if a data sample was used to train a machine learning model. For foundation models trained on unknown Web data, MI attacks are of…
Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
Jie Zhang, Debeshee Das, Gautam Kamath +1
We consider the problem of a training data proof, where a data creator or owner wants to demonstrate to a third party that some machine learning model was trained on their data. Tr…