14 citations · 15 across the 15 of their papers we have counts for
21 papers
Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning
Yuqi Jia, Hangsheng Zhang, Chenxi Liu +2
Large language model (LLM) agents are increasingly deployed in multi-agent systems (MAS) to accomplish complex tasks. Prior black-box red-teaming attacks mainly focus on single age…
LongPIBench: A Long-Context Benchmark for Prompt Injection
Yupei Liu, Yuqi Jia, Neil Zhenqiang Gong +1
Prompt injection attacks pose a serious security risk to large language models in real-world applications. However, existing prompt injection benchmarks primarily focus on short-co…
ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools
Yuqi Jia, Ruiqi Wang, Patrick Li +3
Exfiltrating an LLM agent's runtime context -- such as the user prompt, execution trajectory, and tool list -- poses severe security and privacy risks to users. Such attacks can be…
Visual Contrastive Self-Distillation
Yijun Liang, Yunjie Tian, Yijiang Li +5
On-policy self-distillation (OPSD) removes the external teacher required by on-policy distillation (OPD), but still needs asymmetric information between teacher and student so that…
Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening
Mohan Zhang, Yuqi Jia, Zhen Tan +4
LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or through a few anecdotal case studie…
Evaluating Tool Cloning in Agentic-AI Ecosystems
Taein Kim, David Jiang, Yuepeng Hu +2
Agent tools are becoming a core interface through which LLM agents access external data, services, and execution environments. As these tools are distributed through public marketp…
AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks
Yuqi Jia, Ruiqi Wang, Xilong Wang +2
Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typic…
MalTool: Malicious Tool Attacks on LLM Agents
Yuepeng Hu, Yuqi Jia, Mengyuan Li +2
In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user inadvertently installs the tool and the LLM agent selects it during task ex…
ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
Reachal Wang, Yuqi Jia, Neil Zhenqiang Gong
Prompt injection attacks aim to contaminate the input data of an LLM to mislead it into completing an attacker-chosen task instead of the intended task. In many applications and ag…
Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models
Chenxi Liu, Junjie Liang, Yuqi Jia +4
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative…
PromptLocate: Localizing Prompt Injection Attacks
Yuqi Jia, Yupei Liu, Zedian Shao +2
Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected pro…
WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
Yinuo Liu, Ruohan Xu, Xilong Wang +2
Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none…
SecInfer: Preventing Prompt Injection via Inference-time Scaling
Yupei Liu, Yanting Wang, Yuqi Jia +2
Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to…
PromptArmor: Simple yet Effective Prompt Injection Defenses
Tianneng Shi, Kaijie Zhu, Zhun Wang +13
Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, c…
A Critical Evaluation of Defenses against Prompt Injection Attacks
Yuqi Jia, Zedian Shao, Yupei Liu +3
Large Language Models (LLMs) are vulnerable to prompt injection attacks, and several defenses have recently been proposed, often claiming to mitigate these attacks successfully. Ho…
DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks
Yupei Liu, Yuqi Jia, Jinyuan Jia +2
LLM-integrated applications and agents are vulnerable to prompt injection attacks, where an attacker injects prompts into their inputs to induce attacker-desired outputs. A detecti…
Evaluating LLM-based Personal Information Extraction and Countermeasures
Yupei Liu, Yuqi Jia, Jinyuan Jia +1
Automatically extracting personal information -- such as name, phone number, and email address -- from publicly available profiles at a large scale is a stepstone to many other sec…
Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
Yuqi Jia, Minghong Fang, Hongbin Liu +2
Poisoning attacks compromise the training phase of federated learning (FL) such that the learned global model misclassifies attacker-chosen inputs called target inputs. Existing de…
Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents
Yuqi Jia, Saeed Vahidian, Jingwei Sun +4
Data heterogeneity presents significant challenges for federated learning (FL). Recently, dataset distillation techniques have been introduced, and performed at the client level, t…
Competitive Advantage Attacks to Decentralized Federated Learning
Yuqi Jia, Minghong Fang, Neil Zhenqiang Gong
Decentralized federated learning (DFL) enables clients (e.g., hospitals and banks) to jointly train machine learning models without a central orchestration server. In each global t…
Formalizing and Benchmarking Prompt Injection Attacks and Defenses
Yupei Liu, Yuqi Jia, Runpeng Geng +2
A prompt injection attack aims to inject malicious instruction/data into the input of an LLM-Integrated Application such that it produces results as an attacker desires. Existing w…