3 papers
cs.CV2025
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…
cs.CR2025
BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
Zihan Wang, Hongwei Li, Rui Zhang +5
In this paper, we present a new form of backdoor attack against Large Language Models (LLMs): lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the lang…
cs.CR2025
The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning
Kunlan Xiang, Haomiao Yang, Meng Hao +5
In Federated Learning (FL), clients share gradients with a central server while keeping their data local. However, malicious servers could deliberately manipulate the models to rec…