activity
20242026
collaborators

7 papers

cs.CR2026

CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents

Tao Huang, Guosen Wu, Guolong Zheng +5

Privacy leakage in LLM agents is commonly evaluated within individual components such as memory, retrieval, or tool-use pipelines, which makes it difficult to distinguish internal…

cs.CR2026

PAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated Workflows

Tao Huang, Guosen Wu, Chen Hou +1

AI-mediated platforms coordinate work through LLM agents acting for different principals. In these workflows, privacy loss can be created before a final answer appears: a memory wr…

cs.LG2026

Mitigating Membership Inference in Intermediate Representations with Differentially Private Training

Jiayang Meng, Tao Huang, Chen Hou +2

In Embedding-as-an-Interface (EaaI) settings, pre-trained models are queried for Intermediate Representations (IRs). The distributional properties of IRs can leak training-set memb…

cs.CR2025

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models

Jiayang Meng, Tao Huang, Hong Chen +2

Federated learning synchronizes models through gradient transmission and aggregation. However, these gradients pose significant privacy risks, as sensitive training data is embedde…

cs.LG2024

Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight

Tao Huang, Qingyu Huang, Xin Shi +4

In the domain of deep learning, the challenge of protecting sensitive data while maintaining model utility is significant. Traditional Differential Privacy (DP) techniques such as…

cs.CV2024

Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising

Tao Huang, Jiayang Meng, Hong Chen +4

We investigate the construction of gradient-guided conditional diffusion models for reconstructing private images, focusing on the adversarial interplay between differential privac…