9 papers
Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures
Zeyao Liu, Zhendong Zhao, Xiaojun Chen +3
Existing ViT backdoor attacks based on backbone-overwriting full-tuning are computationally expensive and inflict performance degradation. This has forced adversaries towards the V…
Value-Aligned Prompt Moderation via Zero-Shot Agentic Rewriting for Safe Image Generation
Xin Zhao, Xiaojun Chen, Bingshan Liu +3
Generative vision-language models like Stable Diffusion demonstrate remarkable capabilities in creative media synthesis, but they also pose substantial risks of producing unsafe, o…
DeepTracer: Tracing Stolen Model via Deep Coupled Watermarks
Yunfei Yang, Xiaojun Chen, Yuexin Xuan +3
Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing wate…
Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
Xin Zhao, Xiaojun Chen, Bingshan Liu +3
Large language models (LLMs) with Mixture-of-Experts (MoE) architectures achieve impressive performance and efficiency by dynamically routing inputs to specialized subnetworks, kno…
AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
Xiaoshuang Ji, Zhendong Zhao, Xiaoyan Gu +3
Parameter-efficient finetuning (PEFT) aims to mitigate the substantial computational and memory overhead involved in adapting large-scale pretrained models to diverse downstream ta…
Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models
Xiaoshuang Ji, Zhendong Zhao, Xiaojun Chen +2
Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes in…
Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation
Xin Zhao, Xiaojun Chen, Yuexin Xuan +4
The rise of deep learning models in the digital era has raised substantial concerns regarding the generation of Not-Safe-for-Work (NSFW) content. Existing defense methods primarily…
Antelope: Potent and Concealed Jailbreak Attack Strategy
Xin Zhao, Xiaojun Chen, Haoyu Gao
Due to the remarkable generative potential of diffusion-based models, numerous researches have investigated jailbreak attacks targeting these frameworks. A particularly concerning…
CipherDM: Secure Three-Party Inference for Diffusion Model Sampling
Xin Zhao, Xiaojun Chen, Xudong Chen +3
Diffusion Models (DMs) achieve state-of-the-art synthesis results in image generation and have been applied to various fields. However, DMs sometimes seriously violate user privacy…