11 papers
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…
Safety in Self-Evolving Agents: A Survey
Jiahao Chen, Zhou Feng, Oubo Ma +28
Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from new interactions. In open-end…
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…
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…
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…
CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models
Naen Xu, Changjiang Li, Tianyu Du +8
Text-to-image diffusion models have emerged as powerful tools for generating high-quality images from textual descriptions. However, their increasing popularity has raised signific…