12 citations · 46 across the 52 of their papers we have counts for
47 papers · 1 filter
SADRA: Sound Capability-based Access Control System for Resource-Disaggregated Architectures
Hamed Rasifard, Amir Farahani Khojasteh, Hamed Nemati +1
Resource disaggregation separates memory and accelerators from compute nodes and makes them remotely accessible. This improves resource sharing, but also removes the local kernel f…
"Shut Up and Let Me Enjoy My Otome": Understanding and Measuring the Toxicity in Otome Game Communities
Yage Zhang, Xinyue Shen, Yukun Jiang +2
Otome games, a romance simulation genre primarily targeting female, have emerged as a major force in the global gaming market, attracting hundreds of millions of players and billio…
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…
Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
Zeyuan Chen, Yihan Ma, Xinyue Shen +2
Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. W…
HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
Yukun Jiang, Yage Zhang, Michael Backes +2
Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Exis…
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…
Real Money, Fake Models: Deceptive Model Claims in Shadow APIs
Yage Zhang, Yukun Jiang, Zeyuan Chen +3
Access to frontier large language models (LLMs), such as GPT-5 and Gemini-2.5, is often hindered by high pricing, payment barriers, and regional restrictions. These limitations dri…
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…
GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents
Xinyu Zhang, Yixin Wu, Boyang Zhang +4
Images shared on social media often expose geographic cues. While early geolocation methods required expert effort and lacked generalization, the rise of Large Vision Language Mode…
AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
Yixin Wu, Rui Wen, Chi Cui +2
Inference attacks have been widely studied and offer a systematic risk assessment of ML services; however, their implementation and the attack parameters for optimal estimation are…
Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
Yukun Jiang, Mingjie Li, Michael Backes +1
Despite their superior performance on a wide range of domains, large language models (LLMs) remain vulnerable to misuse for generating harmful content, a risk that has been further…
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…
Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions
Yiting Qu, Ziqing Yang, Yihan Ma +3
Recent advances in text-to-image diffusion models have enabled the creation of a new form of digital art: optical illusions--visual tricks that create different perceptions of real…
Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
Yiting Qu, Michael Backes, Yang Zhang
Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However,…
Amplifying Machine Learning Attacks Through Strategic Compositions
Yugeng Liu, Zheng Li, Hai Huang +2
Machine learning (ML) models are proving to be vulnerable to a variety of attacks that allow the adversary to learn sensitive information, cause mispredictions, and more. While the…
Excessive Reasoning Attack on Reasoning LLMs
Wai Man Si, Mingjie Li, Michael Backes +1
Recent reasoning large language models (LLMs), such as OpenAI o1 and DeepSeek-R1, exhibit strong performance on complex tasks through test-time inference scaling. However, prior st…
Watermarking LLM-Generated Datasets in Downstream Tasks
Yugeng Liu, Tianshuo Cong, Michael Backes +2
Large Language Models (LLMs) have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and ques…
SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark
Rui Wen, Yiyong Liu, Michael Backes +1
Data reconstruction attacks, which aim to recover the training dataset of a target model with limited access, have gained increasing attention in recent years. However, there is cu…
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 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…
Peering Behind the Shield: Guardrail Identification in Large Language Models
Ziqing Yang, Yixin Wu, Rui Wen +2
With the rapid adoption of large language models (LLMs), conversational AI agents have become widely deployed across real-world applications. To enhance safety, these agents are of…
HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns
Xinyue Shen, Yixin Wu, Yiting Qu +3
Large Language Models (LLMs) have raised increasing concerns about their misuse in generating hate speech. Among all the efforts to address this issue, hate speech detectors play a…
: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities
Yukun Jiang, Zheng Li, Xinyue Shen +3
Large vision-language models (LVLMs) have been rapidly developed and widely used in various fields, but the (potential) stereotypical bias in the model is largely unexplored. In th…