Publications (13)
When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
Shiqian Zhao, Jiayang Liu, Yiming Li +9
Modern text-to-image (T2I) generation systems (e.g., DALLE 3) exploit the memory mechanism, which captures key information in multi-turn interactions for faithful generation…
Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers
Viet-Anh Nguyen, Shiqian Zhao, Gia Dao +3
Recently, Large Reasoning Models (LRMs) have demonstrated superior logical capabilities compared to traditional Large Language Models (LLMs), gaining significant attention. Despite…
Emage: Non-Autoregressive Text-to-Image Generation
Zhangyin Feng, Runyi Hu, Liangxin Liu +7
Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming…
Unifying Watermarking via Dimension-Aware Mapping
Jiale Meng, Runyi Hu, Jie Zhang +3
Deep watermarking methods often share similar encoder-decoder architectures, yet differ substantially in their functional behaviors. We propose DiM, a new multi-dimensional waterma…
TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking
Jiale Meng, Jie Zhang, Runyi Hu +3
We propose TRACE, a structure-aware framework leveraging diffusion models for localized character encoding to embed data. Unlike existing methods that rely on edge features or pre-…
SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution
Runyi Hu, Jie Zhang, Yiming Li +4
In today's digital landscape, the blending of AI-generated and authentic content has underscored the need for copyright protection and content authentication. Watermarking has beco…
Inference-time Alignment via Sparse Junction Steering
Runyi Hu, Jie Zhang, Shiqian Zhao +7
Token-level steering has emerged as a pivotal approach for inference-time alignment, enabling fine grained control over large language models by modulating their output distributio…
Reinforcement Learning Enhanced LLMs: A Survey
Shuhe Wang, Shengyu Zhang, Jie Zhang +7
Reinforcement learning (RL) enhanced large language models (LLMs), particularly exemplified by DeepSeek-R1, have exhibited outstanding performance. Despite the effectiveness in imp…
Instruction Tuning for Large Language Models: A Survey
Shengyu Zhang, Linfeng Dong, Xiaoya Li +8
This paper surveys research works in the quickly advancing field of instruction tuning (IT), which can also be referred to as supervised fine-tuning (SFT)\footnote{In this paper, u…
Robust-Wide: Robust Watermarking against Instruction-driven Image Editing
Runyi Hu, Jie Zhang, Ting Xu +2
Instruction-driven image editing allows users to quickly edit an image according to text instructions in a forward pass. Nevertheless, malicious users can easily exploit this techn…
Mask Image Watermarking
Runyi Hu, Jie Zhang, Shiqian Zhao +5
We present MaskWM, a simple, efficient, and flexible framework for image watermarking. MaskWM has two variants: (1) MaskWM-D, which supports global watermark embedding, watermark l…
Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
Jie Zhang, Ting Xu, Gelei Deng +5
Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fr…
VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
Runyi Hu, Jie Zhang, Yiming Li +4
Artificial Intelligence Generated Content (AIGC) has advanced significantly, particularly with the development of video generation models such as text-to-video (T2V) models and ima…