19 papers
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…
Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks
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…
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)…
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…