collaborators

5 papers

cs.CV2025

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

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…

cs.CL2025

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…

cs.CV2025

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…

cs.AI2024

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…