7 citations · 12 across the 22 of their papers we have counts for
25 papers
Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics
Qingjie Zhang, Ziqi Tang, Jie Zhang +7
Chinese web pollution has surfaced in LLMs, motivating audits of upstream Chinese corpora. However, auditing such corpora faces three challenges: (1) their web-scale size makes ful…
DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
Haoran Ou, Kangjie Chen, Gelei Deng +4
Fact-checking systems with search-enabled large language models (LLMs) have shown strong potential for verifying claims by dynamically retrieving external evidence. However, the ro…
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…
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…
SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
Renyang Liu, Kangjie Chen, Han Qiu +4
Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from their training data, leading to…
When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
Haoran Ou, Kangjie Chen, Xingshuo Han +4
Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Inte…
Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models
Shiqian Zhao, Chong Wang, Yiming Li +7
Text-to-Image (T2I) models, represented by DALLE and Midjourney, have gained huge popularity for creating realistic images. The quality of these images relies on the careful…
Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking
Haoran Ou, Gelei Deng, Xingshuo Han +4
The increasing multimodal disinformation, where deceptive claims are reinforced through coordinated text and visual content, poses significant challenges to automated fact-checking…
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…
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…
SSD: A State-based Stealthy Backdoor Attack For Navigation System in UAV Route Planning
Zhaoxuan Wang, Yang Li, Jie Zhang +6
Unmanned aerial vehicles (UAVs) are increasingly employed to perform high-risk tasks that require minimal human intervention. However, UAVs face escalating cybersecurity threats, p…
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…
Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
Guanlin Li, Kangjie Chen, Shangwei Guo +6
Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-sp…
An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems
Haoxiang Tian, Xingshuo Han, Guoquan Wu +5
Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep…
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…
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…
FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention
Zhongyi Zhang, Jie Zhang, Wenbo Zhou +5
Face-swapping techniques have advanced rapidly with the evolution of deep learning, leading to widespread use and growing concerns about potential misuse, especially in cases of fr…
Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
Boheng Li, Yanhao Wei, Yankai Fu +5
Text-to-image diffusion models are pushing the boundaries of what generative AI can achieve in our lives. Beyond their ability to generate general images, new personalization techn…
Oedipus: LLM-enchanced Reasoning CAPTCHA Solver
Gelei Deng, Haoran Ou, Yi Liu +3
CAPTCHAs have become a ubiquitous tool in safeguarding applications from automated bots. Over time, the arms race between CAPTCHA development and evasion techniques has led to incr…
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Guanlin Li, Kangjie Chen, Shudong Zhang +2
Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content. Meanwhile, safeguards for these generative models ar…
PRIME: Protect Your Videos From Malicious Editing
Guanlin Li, Shuai Yang, Jie Zhang +1
With the development of generative models, the quality of generated content keeps increasing. Recently, open-source models have made it surprisingly easy to manipulate and edit pho…
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…
SAME: Sample Reconstruction against Model Extraction Attacks
Yi Xie, Jie Zhang, Shiqian Zhao +2
While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solutio…
Singular Regularization with Information Bottleneck Improves Model's Adversarial Robustness
Guanlin Li, Naishan Zheng, Man Zhou +2
Adversarial examples are one of the most severe threats to deep learning models. Numerous works have been proposed to study and defend adversarial examples. However, these works la…