1 citations · 2 across the 7 of their papers we have counts for
8 papers
RedEdit: Agentic Red-Teaming of Image Safety Classifiers via MCTS-Guided Photo-Editing
Weilin Lin, Ziqi Lin, Zhenxing Zhou +4
Image safety classifiers serve as a critical component of contemporary content moderation systems on the internet. However, their resilience against user-style malicious image edit…
PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
Tianxin Xie, Wentao Lei, Kai Jiang +27
Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to produce physically plausible sounds. P…
SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering
Weilin Lin, Jianze Li, Hui Xiong +1
Large Audio-Language Models (LALMs) are becoming essential as a powerful multimodal backbone for real-world applications. However, recent studies show that audio inputs can more ea…
Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognition
Nanjun Zhou, Weilin Lin, Li Liu
Backdoor attacks have posed a significant threat to the security of deep neural networks (DNNs). Despite considerable strides in developing defenses against backdoor attacks in the…
BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
Weilin Lin, Nanjun Zhou, Yanyun Wang +3
Backdoor learning is a critical research topic for understanding the vulnerabilities of deep neural networks. While the diffusion model (DM) has been broadly deployed in public ove…
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
Weilin Lin, Li Liu, Jianze Li +1
Backdoor attacks present a serious security threat to deep neuron networks (DNNs). Although numerous effective defense techniques have been proposed in recent years, they inevitabl…
Segment Anything for Videos: A Systematic Survey
Chunhui Zhang, Yawen Cui, Weilin Lin +4
The recent wave of foundation models has witnessed tremendous success in computer vision (CV) and beyond, with the segment anything model (SAM) having sparked a passion for explori…
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
Weilin Lin, Li Liu, Shaokui Wei +2
The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a…