13 papers
Cost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests
Qikun Cai, Tao Huang, Chen Hou
LLM agents now act as delegated communication intermediaries: they read private context, draft messages, and send externally visible emails on behalf of a user. Existing checker-re…
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…
A Lightweight Plug-in Gate for Transformer-Based Time-Series Forecasters
Hongkai Zhuang, Tao Huang, Chen Hou
Covariate-rich time-series forecasting requires deciding how external variables enter the target forecasting path. Existing Transformer-based forecasters usually build a covariate…
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…
Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelines
Tao Huang, Chen Hou, Guosen Wu +1
Privacy leakage in LLM agents is often studied through individual storage or execution components, such as memory modules, retrieval pipelines, or tool-mediated artifacts. However,…
DP-aware AdaLN-Zero: Taming Conditioning-Induced Heavy-Tailed Gradients in Differentially Private Diffusion
Tao Huang, Jiayang Meng, Xu Yang +2
Condition injection enables diffusion models to generate context-aware outputs, which is essential for many time-series tasks. However, heterogeneous conditional contexts (e.g., ob…
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…
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…
Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
Jiayang Meng, Tao Huang, Hong Chen +3
The widespread deployment of deep learning models in privacy-sensitive domains has amplified concerns regarding privacy risks, particularly those stemming from gradient leakage dur…
Intermediate Outputs Are More Sensitive Than You Think
Tao Huang, Qingyu Huang, Jiayang Meng
The increasing reliance on deep computer vision models that process sensitive data has raised significant privacy concerns, particularly regarding the exposure of intermediate resu…
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…
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…
Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
Tao Huang, Ziyang Chen, Jiayang Meng +4
In the context of machine unlearning, the primary challenge lies in effectively removing traces of private data from trained models while maintaining model performance and security…