333 citations · 395 across the 31 of their papers we have counts for
35 papers
Speaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents
Xi Chen, Zhe Liu, Xiaogang Xu +8
Aerial vision-and-language navigation (VLN) agents are typically trained on detail-rich, trajectory-aligned commands, whereas users issue short, intent-driven instructions; on a fr…
StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning
Naen Xu, Wanqing Cui, Yibo Hu +5
Large language models deployed as personalized assistants must reason over long, evolving interaction histories. However, in long-term dialogue reasoning, relevant evidence is scat…
Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository Poisoning
Fukang Zhu, Binbin Zhao, Ruixiao Lin +3
Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity cannot be assumed. Prior work on…
Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds
Jiahao Chen, Rui Yin, Xinfeng Li +6
Large Language Models (LLMs) have been integrated into complex ecosystems (e.g., Code Agents), while Indirect Prompt Injection (IPI) attacks have emerged as critical barriers to th…
The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails
Shuo Shi, Rui Yin, Naen Xu +7
Multimodal guard models have emerged as critical safety components for screening content in vision-language systems. While adversarial research has extensively studied jailbreaking…
Flipping Minds by Flipping Bits: Decision-Level Cognitive Hijacking of Large Language Models
Yu Yan, Jiahao Chen, Siqi Lu +6
Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. Howe…
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications
Yong Yang, Chong Fu, Tong Zhang +6
Large language model (LLM)-based applications rely on system prompts to encode core logic and developer-defined constraints, making these prompts important intellectual property. H…
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
Rui Yin, Tianxu Han, Naen Xu +8
Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can di…
ACIArena: Toward Unified Evaluation for Agent Cascading Injection
Hengyu An, Minxi Li, Jinghuai Zhang +6
Collaboration and information sharing empower Multi-Agent Systems (MAS) but also introduce a critical security risk known as Agent Cascading Injection (ACI). In such attacks, a com…
"I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?
Naen Xu, Jiayi Sheng, Changjiang Li +7
Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground th…
When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
Naen Xu, Hengyu An, Shuo Shi +7
Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges.…
FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
Naen Xu, Jinghuai Zhang, Ping He +6
Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible t…
Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
Naen Xu, Jinghuai Zhang, Changjiang Li +7
Large vision-language models (LVLMs) have achieved remarkable advancements in multimodal reasoning tasks. However, their widespread accessibility raises critical concerns about pot…
The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks
Zhou Feng, Jiahao Chen, Chunyi Zhou +5
Deep neural networks (DNNs) underpin critical applications yet remain vulnerable to backdoor attacks, typically reliant on heuristic brute-force methods. Despite significant empiri…
Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
Ping He, Changjiang Li, Binbin Zhao +2
The remarkable capability of large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agen…
NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
Chuhan Zhang, Ye Zhang, Bowen Shi +5
Jailbreak attacks bypass the safety alignment of large language models (LLMs) to elicit harmful outputs, yet the vast parameter space makes diagnosing the underlying failure mechan…
VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
Naen Xu, Jinghuai Zhang, Changjiang Li +5
The rapid growth of text-to-video (T2V) diffusion models has raised concerns about privacy, copyright, and safety due to their potential misuse in generating harmful or misleading…
IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Hengyu An, Jinghuai Zhang, Tianyu Du +4
Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, whe…
Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes
Zhou Feng, Jiahao Chen, Chunyi Zhou +4
The rapid advancement of voice deepfake technologies has raised serious concerns about user audio privacy, as attackers increasingly exploit publicly available voice data to genera…
LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing
Jiahao Chen, Junhao Li, Yiming Wang +6
The proliferation of Low-Rank Adaptation (LoRA) models has democratized personalized text-to-image generation, enabling users to share lightweight models (e.g., personal portraits)…
CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
Rui Zeng, Xi Chen, Yuwen Pu +3
Backdoors can be injected into NLP models to induce misbehavior when the input text contains a specific feature, known as a trigger, which the attacker secretly selects. Unlike fix…
LABOR-LLM: Language-Based Occupational Representations with Large Language Models
Susan Athey, Herman Brunborg, Tianyu Du +2
This paper builds an empirical model that predicts a worker's next occupation as a function of the worker's occupational history. Because histories are sequences of occupations, th…
An Inversion-based Measure of Memorization for Diffusion Models
Zhe Ma, Qingming Li, Xuhong Zhang +5
The past few years have witnessed substantial advances in image generation powered by diffusion models. However, it was shown that diffusion models are susceptible to training data…
VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
Ziyi Yin, Muchao Ye, Tianrong Zhang +6
Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Exist…