10 citations · 29 across the 12 of their papers we have counts for
13 papers
TAPDreamer: Transferable Adversarial Patches for World Action Models
Xuanyu Lu, Fengqing Jiang, Kaiyuan Zheng +8
World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera i…
Green Shielding: A User-Centric Approach Towards Trustworthy AI
Aaron J. Li, Nicolas Sanchez, Hao Huang +8
Large language models (LLMs) are increasingly deployed, yet their outputs can be highly sensitive to routine, non-adversarial variation in how users phrase queries, a gap not well…
Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment
Qitao Tan, Xiaoying Song, Ningxi Cheng +6
Public large language models (LLMs) are typically safety-aligned during pretraining, yet task-specific fine-tuning required for deployment often erodes this alignment and introduce…
MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
Wentian Zhu, Zhen Xiang, Wei Niu +1
Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Langu…
SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
Fengqing Jiang, Fengbo Ma, Zhangchen Xu +8
Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particul…
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen +22
Multimodal foundation models (MMFMs) play a crucial role in various applications, including autonomous driving, healthcare, and virtual assistants. However, several studies have re…
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
Fengqing Jiang, Zhangchen Xu, Yuetai Li +5
Emerging large reasoning models (LRMs), such as DeepSeek-R1 models, leverage long chain-of-thought (CoT) reasoning to generate structured intermediate steps, enhancing their reason…
Data Free Backdoor Attacks
Bochuan Cao, Jinyuan Jia, Chuxuan Hu +5
Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing ba…
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
Zhaorun Chen, Zhen Xiang, Chaowei Xiao +2
LLM agents have demonstrated remarkable performance across various applications, primarily due to their advanced capabilities in reasoning, utilizing external knowledge and tools,…
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Zhen Xiang, Linzhi Zheng, Yanjie Li +9
The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail ag…
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
Fengqing Jiang, Zhangchen Xu, Luyao Niu +4
Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine-tuning have been developed to strengthen LLM safety.…
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Zhen Xiang, Fengqing Jiang, Zidi Xiong +3
Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other…
CBD: A Certified Backdoor Detector Based on Local Dominant Probability
Zhen Xiang, Zidi Xiong, Bo Li
Backdoor attack is a common threat to deep neural networks. During testing, samples embedded with a backdoor trigger will be misclassified as an adversarial target by a backdoored…