7 papers · 1 filter
Erase the Mark, Preserve the Motion: Temporally Consistent Removal of Video Watermarks
Yifan Liao, Zhen Sun, Zhicong Huang +6
Recent advances in video generation have increased the demand for reliable watermarking for copyright protection, yet the robustness of video watermarks against removal attacks rem…
Robustness of Vision Foundation Models to Common Perturbations
Hongbin Liu, Zhengyuan Jiang, Cheng Hong +1
A vision foundation model outputs an embedding vector for an image, which can be affected by common editing operations (e.g., JPEG compression, brightness, contrast adjustments). T…
Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs
Yiyang Lu, Jinwen He, Yue Zhao +4
Large Language Models (LLMs) are increasingly deployed as multi-turn assistants and customized through instruction tuning with project-specific training components. This practice c…
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
Wei Wan, Yuxuan Ning, Zhicong Huang +7
Federated Learning (FL) is a distributed paradigm aimed at protecting participant data privacy by exchanging model parameters to achieve high-quality model training. However, this…
Fingerprinting LLMs via Prompt Injection
Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li +4
Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one mod…
GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
Kecen Li, Zhicong Huang, Xinwen Hou +1
As Diffusion Models (DM) generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising sol…
VideoMarkBench: Benchmarking Robustness of Video Watermarking
Zhengyuan Jiang, Moyang Guo, Kecen Li +5
The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringem…