4 papers
Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models
Wenjing Hong, Zhonghua Rong, Li Wang +5
Large Language Models (LLMs) have been widely deployed, especially through free Web-based applications that expose them to diverse user-generated inputs, including those from long-…
ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation
Haoqi Wu, Wei Dai, Ming Xu +2
Diffusion Models have gained significant popularity due to their remarkable capabilities in image generation, albeit at the cost of intensive computation requirement. Meanwhile, de…
Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models
Jiahao Chen, Yu Pan, Yi Du +2
Recently, the diffusion model has gained significant attention as one of the most successful image generation models, which can generate high-quality images by iteratively sampling…
Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy
Haoqi Wu, Wei Dai, Li Wang +1
Large Language Models (LLMs) have gained significant popularity due to their remarkable capabilities in text understanding and generation. However, despite their widespread deploym…