5 papers
Loose Lips: Understanding Privacy Leakage in Agentic Dialogue
Soumya Sharma, Ayana Hussain, Heber Hwang Arcolezi +4
As LLM agents are increasingly deployed in high-stakes enterprise settings, understanding how they handle sensitive information in agentic dialogue has become critical. Privacy lea…
IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts
Ayana Hussain, Soumya Sharma, Golnoosh Farnadi +3
Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challenge for their design and evalua…
Optimizer Dynamics at the Edge of Stability with Differential Privacy
Ayana Hussain, Ricky Fang
Deep learning models can reveal sensitive information about individual training examples, and while differential privacy (DP) provides guarantees restricting such leakage, it also…
Open WebUI: An Open, Extensible, and Usable Interface for AI Interaction
Jaeryang Baek, Ayana Hussain, Danny Liu +2
While LLMs enable a range of AI applications, interacting with multiple models and customizing workflows can be challenging, and existing LLM interfaces offer limited support for c…
An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs
Ayana Hussain, Patrick Zhao, Nicholas Vincent
Large Language Models (LLMs) are a double-edged sword capable of generating harmful misinformation -- inadvertently, or when prompted by "jailbreak" attacks that attempt to produce…