54 citations · 59 across the 7 of their papers we have counts for
10 papers
RATION: Towards Quantitative Risk-Based Access Control for AI Agents
Yuntao Du, Harsh Chaudhari, Yuetian Chen +8
AI agents increasingly interact with external environments to complete complex user tasks. These interactions can lead to unexpected behavior and expose agents to security threats…
BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views
Yuetian Chen, Kaiyuan Zhang, Yuntao Du +6
Browser agents need to make decisions and execute actions on behalf of users while consuming untrusted webpages, creating opportunities for malicious instructions embedded in webpa…
Privacy Leakage from a Thousand Words: Millipixel Location Recovery from Dot Maps
Yuntao Du, Tanishq Pauskar, Hao Wang +2
Dot maps, which visualize individual data points as dots over a geographic region, are widely used across diverse domains to represent spatial patterns in sensitive data. However,…
PII-TRACE: A Benchmark for Context-Aware PII Detection in Multi-Turn LLM Conversations
Kaiyuan Zhang, Chuan Wang, Joey Zhong +4
LLM assistants and agentic systems log long multi-turn conversations. AI providers often scan these conversations for Personally Identifiable Information (PII) and mask the PII bef…
Window-based Membership Inference Attacks Against Fine-tuned Large Language Models
Yuetian Chen, Yuntao Du, Kaiyuan Zhang +4
Most membership inference attacks (MIAs) against Large Language Models (LLMs) rely on global signals, like average loss, to identify training data. This approach, however, dilutes…
BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley +3
The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has ide…
Cascading and Proxy Membership Inference Attacks
Yuntao Du, Jiacheng Li, Yuetian Chen +5
A Membership Inference Attack (MIA) assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included…
CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling
Kaiyuan Zhang, Siyuan Cheng, Guangyu Shen +5
Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (g…
The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
Joshua C. Zhao, Saurabh Bagchi, Salman Avestimehr +7
Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data…
MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training
Jiacheng Li, Ninghui Li, Bruno Ribeiro
In Member Inference (MI) attacks, the adversary try to determine whether an instance is used to train a machine learning (ML) model. MI attacks are a major privacy concern when usi…