4 papers
Dependency-Aware Privacy for Multi-turn Agents
Divyam Anshumaan, Sarthak Choudhary, Nils Palumbo +1
LLM agents release private data across multi-service interactions. Existing prompt sanitizers based on metric differential privacy treat each release independently, so adversaries…
How Not to Detect Prompt Injections with an LLM
Sarthak Choudhary, Divyam Anshumaan, Nils Palumbo +1
LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate t…
Prmpt: Sanitizing Sensitive Prompts for LLMs
Amrita Roy Chowdhury, David Glukhov, Divyam Anshumaan +4
The rise of large language models (LLMs) has introduced new privacy challenges, particularly during inference where sensitive information in prompts may be exposed to proprietary L…
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
Zi Wang, Divyam Anshumaan, Ashish Hooda +2
Optimization methods are widely employed in deep learning to identify and mitigate undesired model responses. While gradient-based techniques have proven effective for image models…