5 papers
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
Changyue Li, Jiaming He, Youliang Yuan +4
Fine-Tuning-as-a-Service (FTaaS) platforms let users train large language models (LLMs) on customized tasks, but this pipeline could erode models' safety alignment. In practice, se…
Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
Changyue Li, Jiaying Li, Youliang Yuan +3
Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-A…
Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
Jialin Wu, Wei Shi, Han Shen +5
Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textu…
TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
Jiaming He, Guanyu Hou, Hongwei Li +6
Text-to-Video (T2V) models are capable of synthesizing high-quality, temporally coherent dynamic video content, but the diverse generation also inherently introduces critical safet…
Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment
Fei Zhou, Tianhao Gu, Zhicong Huang +1
The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightn…