2 papers
cs.LG2026
Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode
Zeyuan He, Yupeng Chen, Lang Lin +7
Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation efficiency. Beyond the utility benefit…
cs.CV2023
A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications
Donghua Wang, Wen Yao, Tingsong Jiang +3
Wide deployment of deep neural networks (DNNs) based applications (e.g., style transfer, cartoonish), stimulating the requirement of copyright protection of such application's prod…