DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
원문 초록
With the growing demand for personalized AI solutions, customized LLMs have become a preferred choice for businesses and individuals, driving the deployment of millions of AI agents across various platforms, e.g., GPT Store hosts over 3 million customized GPTs. Their popularity is partly driven by advanced reasoning capabilities, such as Chain-of-Thought, which enhance their ability to tackle complex tasks. However, their rapid proliferation introduces new vulnerabilities, particularly in reasoning processes that remain largely unexplored. We introduce DarkMind, a novel backdoor attack that exploits the reasoning capabilities of customized LLMs. Designed to remain latent, DarkMind activates within the reasoning chain to covertly alter the final outcome. Unlike existing attacks, it operates without injecting triggers into user queries, making it a more potent threat. We evaluate DarkMind across eight datasets covering arithmetic, commonsense, and symbolic reasoning domains, using five state-of-the-art LLMs with five distinct trigger implementations. Our results demonstrate DarkMind effectiveness across all scenarios, underscoring its impact. Finally, we explore potential defense mechanisms to mitigate its risks, emphasizing the need for stronger security measures.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking
MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges
Protocol-agnostic and Data-free Backdoor Attacks on Pre-trained Models in RF Fingerprinting
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
Towards Invisible Backdoor Attack on Text-to-Image Diffusion Model
AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.