activity
20182025
most citedTraining a Tokenizer for Free with Private Federated Learning

1 citations · 1 across the 8 of their papers we have counts for

collaborators
Showing cs.CRShow all

12 papers · 1 filter

cs.CR2025

Network-Level Prompt and Trait Leakage in Local Research Agents

Hyejun Jeong, Mohammadreza Teymoorianfard, Abhinav Kumar +2

We show that Web and Research Agents (WRAs) -- language-model-based systems that investigate complex topics on the Internet -- are vulnerable to inference attacks by passive networ…

cs.CR2025

Can Large Language Models Really Recognize Your Name?

Dzung Pham, Peter Kairouz, Niloofar Mireshghallah +3

Large language models (LLMs) are increasingly being used in privacy pipelines to detect and remedy sensitive data leakage. These solutions often rely on the premise that LLMs can r…

cs.CR2025

Firewalls to Secure Dynamic LLM Agentic Networks

Sahar Abdelnabi, Amr Gomaa, Eugene Bagdasarian +2

The emergence of agent-to-agent communication protocols mirrors the early internet: powerful connectivity with minimal security infrastructure. When AI agents communicate on behalf…

cs.CR2025

Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography

Ilia Shumailov, Daniel Ramage, Sarah Meiklejohn +4

We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private data.…

cs.CR2024

AirGapAgent: Protecting Privacy-Conscious Conversational Agents

Eugene Bagdasarian, Ren Yi, Sahra Ghalebikesabi +5

The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understandi…

cs.CR2023

Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models

Sze Jue Yang, Chinh D. La, Quang H. Nguyen +4

Backdoor attacks, representing an emerging threat to the integrity of deep neural networks, have garnered significant attention due to their ability to compromise deep learning sys…