7 papers
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…
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…
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…
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…