Permissive Information-Flow Analysis for Large Language Models
원문 초록
Large Language Models (LLMs) are rapidly becoming commodity components of larger software systems. This poses natural security and privacy problems: poisoned data retrieved from one component can change the model's behavior and compromise the entire system, including coercing the model to spread confidential data to untrusted components. One promising approach is to tackle this problem at the system level via dynamic information flow (aka taint) tracking. Unfortunately, the traditional approach of propagating the most restrictive input label to the output is too conservative for applications where LLMs operate on inputs retrieved from diverse sources. In this paper, we propose a novel, more permissive approach to propagate information flow labels through LLM queries. The key idea behind our approach is to propagate only the labels of the samples that were influential in generating the model output and to eliminate the labels of unnecessary input. We implement and investigate the effectiveness of two variations of this approach, based on (i) prompt-based retrieval augmentation, and (ii) a $k$-nearest-neighbors language model. We compare these with the baseline of an introspection-based influence estimator that directly asks the language model to predict the output label. The results obtained highlight the superiority of our prompt-based label propagator, which improves the label in more than 85% of the cases in an LLM agent setting. These findings underscore the practicality of permissive label propagation for retrieval augmentation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Kodezi Chronos: A Debugging-First Language Model for Repository-Scale, Memory-Driven Code Understanding
Differential Mamba
RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge
FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation
XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation
Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.