3 citations · 7 across the 20 of their papers we have counts for
23 papers
Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?
Qingjie Zhang, Xingzhang Ren, Zixuan Chen +6
Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus mixtures or traced specific…
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…
State-Dependent Safety Failures in Multi-Turn Language Model Interaction
Pengcheng Li, Jie Zhang, Tianwei Zhang +5
Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically…
What Makes a Good LLM Agent for Real-world Penetration Testing?
Gelei Deng, Yi Liu, Yuekang Li +5
LLM-based agents show promise for automating penetration testing, yet reported performance varies widely across systems and benchmarks. We analyze 28 LLM-based penetration testing…
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…
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…
When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
Cheng Wang, Gelei Deng, Xianglin Yang +2
Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and te…
ObfusBFA: A Holistic Approach to Safeguarding DNNs from Different Types of Bit-Flip Attacks
Xiaobei Yan, Han Qiu, Tianwei Zhang
Bit-flip attacks (BFAs) represent a serious threat to Deep Neural Networks (DNNs), where flipping a small number of bits in the model parameters or binary code can significantly de…
BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
Xiaobei Yan, Yiming Li, Hao Wang +2
Large language models (LLMs) are widely deployed, but their substantial compute demands make them vulnerable to inference cost attacks that aim to deliberately maximize the output…
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…
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…
FaceID-6M: A Large-Scale, Open-Source FaceID Customization Dataset
Shuhe Wang, Xiaoya Li, Jiwei Li +8
Due to the data-driven nature of current face identity (FaceID) customization methods, all state-of-the-art models rely on large-scale datasets containing millions of high-quality…
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…
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…
Understanding the Dark Side of LLMs' Intrinsic Self-Correction
Qingjie Zhang, Di Wang, Haoting Qian +7
Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic se…
Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
Rongwu Xu, Zi'an Zhou, Tianwei Zhang +5
The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access t…
Course-Correction: Safety Alignment Using Synthetic Preferences
Rongwu Xu, Yishuo Cai, Zhenhong Zhou +6
The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability…
Rethinking Adversarial Training with Neural Tangent Kernel
Guanlin Li, Han Qiu, Shangwei Guo +2
Adversarial training (AT) is an important and attractive topic in deep learning security, exhibiting mysteries and odd properties. Recent studies of neural network training dynamic…
The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
Rongwu Xu, Brian S. Lin, Shujian Yang +6
Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility beha…
A Unified Hardware-based Threat Detector for AI Accelerators
Xiaobei Yan, Han Qiu, Tianwei Zhang
The proliferation of AI technology gives rise to a variety of security threats, which significantly compromise the confidentiality and integrity of AI models and applications. Exis…
Warfare:Breaking the Watermark Protection of AI-Generated Content
Guanlin Li, Yifei Chen, Jie Zhang +5
AI-Generated Content (AIGC) is rapidly expanding, with services using advanced generative models to create realistic images and fluent text. Regulating such content is crucial to p…