2 citations · 2 across the 11 of their papers we have counts for
13 papers
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…
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…
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…
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…
Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
Yixiang Qiu, Yanhan Liu, Hongyao Yu +4
The growing complexity of Deep Neural Networks (DNNs) has led to the adoption of Split Inference (SI), a collaborative paradigm that partitions computation between edge devices and…
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…
Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs
Jiawei Kong, Hao Fang, Xiaochen Yang +5
Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revis…
Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP
Jiawei Kong, Hao Fang, Sihang Guo +5
While pre-trained Vision-Language Models (VLMs) such as CLIP exhibit impressive representational capabilities for multimodal data, recent studies have revealed their vulnerability…
Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models
Kuofeng Gao, Shu-Tao Xia, Ke Xu +2
Large Audio-Language Models (LALMs), such as GPT-4o, have recently unlocked audio dialogue capabilities, enabling direct spoken exchanges with humans. The potential of LALMs broade…
Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering
Hongyao Yu, Yixiang Qiu, Hao Fang +6
Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models…
MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense
Yixiang Qiu, Hongyao Yu, Hao Fang +6
Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising critical concerns regarding the priva…
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…
GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search
Wenbo Yu, Hao Fang, Bin Chen +5
Gradient Inversion Attacks invert the transmitted gradients in Federated Learning (FL) systems to reconstruct the sensitive data of local clients and have raised considerable priva…