13 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…
ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization
Jiaming He, Jiashu Zhang, Guanyu Hou +4
Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization techniques allow such model…
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…
STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillation
Shuhan Ye, Yi Yu, Qixin Zhang +5
SNNs promise energy-efficient and low-latency inference, but their performance still trails that of ANNs. ANN-to-SNN knowledge distillation helps narrow this gap, yet the original…
Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting
Yang Chen, Yi Yu, Jiaming He +3
Recent advances in 3D Gaussian Splatting (3DGS) deliver high-quality rendering, yet the Gaussian representation exposes a new attack surface, the resource-targeting attack. This at…
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…