activity
20242026
collaborators

8 papers

cs.CV2026

IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off

Linyan Dai, Xinwei Zhang, Haoyang Li +2

Personalized text-to-image diffusion models (e.g., DreamBooth, LoRA) enable users to synthesize high-fidelity avatars from a few reference photos for social expression. However, on…

cs.CR2026

DPAgent-in-the-Middle: Agentic Defense and Repair Against AI-Groomed Deceptive Patterns

Zewei Shi, Ruoxi Sun, Haoyang Li +4

Privacy deceptive patterns in web interfaces systematically manipulate users into disclosing personal data, yet existing defenses are fragmented, static, and increasingly vulnerabl…

cs.CR2025

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks

Yaxin Xiao, Qingqing Ye, Zi Liang +4

Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through…

cs.LG2025

Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy

Yaxin Xiao, Qingqing Ye, Li Hu +5

Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to…

cs.CR2025

What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift

Jiamin Chang, Haoyang Li, Hammond Pearce +3

The growing adoption of artificial intelligence (AI) has amplified concerns about trustworthiness, including integrity, privacy, robustness, and bias. To assess and attribute these…

cs.LG2025

A Sample-Level Evaluation and Generative Framework for Model Inversion Attacks

Haoyang Li, Li Bai, Qingqing Ye +4

Model Inversion (MI) attacks, which reconstruct the training dataset of neural networks, pose significant privacy concerns in machine learning. Recent MI attacks have managed to re…