134 citations · 152 across the 20 of their papers we have counts for
16 papers · 1 filter
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
Ziqing Yang, Rui Wen, Xinlei He +3
Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy. Despite its growing adoption, the security vulnerab…
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
Rui Zhang, Hongwei Li, Yun Shen +6
The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthines…
Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks
Junjie Chu, Yiting Qu, Ye Leng +4
Large Language Models (LLMs) are increasingly trained to align with human values, primarily focusing on task level, i.e., refusing to execute directly harmful tasks. However, a sub…
Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks
Junjie Chu, Xinyue Shen, Ye Leng +3
The rapid expansion of research in LLM safety presents challenges in tracking advancements, making benchmarks important evaluation infrastructures for identifying key trends and fa…
JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring
Junjie Chu, Mingjie Li, Ziqing Yang +6
Accurately determining whether a jailbreak attempt has succeeded is a fundamental yet unresolved challenge. Existing evaluation methods rely on misaligned proxy indicators or naive…
When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs
Xinyue Shen, Yun Shen, Michael Backes +1
Knowledge files have been widely used in large language model (LLM) agents, such as GPTs, to improve response quality. However, concerns about the potential leakage of knowledge fi…
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
Rui Zhang, Yun Shen, Hongwei Li +5
Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however,…
The Challenge of Identifying the Origin of Black-Box Large Language Models
Ziqing Yang, Yixin Wu, Yun Shen +3
The tremendous commercial potential of large language models (LLMs) has heightened concerns over their unauthorized use. To address this, we focus on the task of identifying the or…
Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution
Yixin Wu, Yun Shen, Michael Backes +1
Text-to-image models, such as Stable Diffusion (SD), undergo iterative updates to improve image quality and address concerns such as safety. Improvements in image quality are strai…
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
Boyang Zhang, Yicong Tan, Yun Shen +4
Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can exten…
Instruction Backdoor Attacks Against Customized LLMs
Rui Zhang, Hongwei Li, Rui Wen +5
The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural la…
FAKEPCD: Fake Point Cloud Detection via Source Attribution
Yiting Qu, Zhikun Zhang, Yun Shen +2
To prevent the mischievous use of synthetic (fake) point clouds produced by generative models, we pioneer the study of detecting point cloud authenticity and attributing them to th…
Quantifying Privacy Risks of Prompts in Visual Prompt Learning
Yixin Wu, Rui Wen, Michael Backes +4
Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not upda…
Prompt Backdoors in Visual Prompt Learning
Hai Huang, Zhengyu Zhao, Michael Backes +2
Fine-tuning large pre-trained computer vision models is infeasible for resource-limited users. Visual prompt learning (VPL) has thus emerged to provide an efficient and flexible al…
On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
Yixin Wu, Ning Yu, Michael Backes +2
Malicious or manipulated prompts are known to exploit text-to-image models to generate unsafe images. Existing studies, however, focus on the passive exploitation of such harmful c…
Composite Backdoor Attacks Against Large Language Models
Hai Huang, Zhengyu Zhao, Michael Backes +2
Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and…