collaborators

13 papers

cs.CV2026

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models

Yi Sun, Zhiqi Zhang, Xinhao Zhong +5

Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or un…

cs.CL2026

Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective

Hao Fang, Tianyi Zhang, Tianqu Zhuang +6

Proprietary large language models (LLMs) embody substantial economic value and are generally exposed only as black-box APIs, yet adversaries can still exploit their outputs to extr…

cs.CL2026

Emergent Hierarchical Structure in Large Language Models: An Information-Theoretic Framework for Multi-Scale Representation

Yukin Zhang, Qi Dong, Kemu Xu

Why do language models from different architecture families respond so differently to the same perturbation? We argue that the answer is not scale, but \emph{how architecture shape…

cs.CV2026

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization

Hao Fang, Wenbo Yu, Bin Chen +4

Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model…

cs.CV2026

Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models

Xinhao Zhong, Yimin Zhou, Zhiqi Zhang +6

The rapid progress of visual autoregressive (VAR) models has brought new opportunities for text-to-image generation, but also heightened safety concerns. Existing concept erasure t…

cs.CV2025

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

Hao Fang, Jiawei Kong, Wenbo Yu +5

Vision-Language Pre-training (VLP) models have exhibited unprecedented capability in many applications by taking full advantage of the multimodal alignment. However, previous studi…