Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answering
We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be vulnerable to membership-inference attacks even when the service provider and users are separate parties. We propose two black-box membership inference attacks that exploit query text prefixes to distinguish member from non-member inputs. The first attack uses a reference model to estimate an otherwise unavailable loss metric. The second attack improves upon it by eliminating the reference model and instead computing a membership statistic through a simple but novel weighted-averaging scheme. Our comprehensive empirical evaluations consider a stricter case in which the adversary has a paraphrased version of the text in the queries and show that our attacks can exhibit stronger resilience to paraphrasing and outperform three prior attacks in many cases with small number of prefixes. We also adapt an existing ensemble prompting defense to our setting, demonstrating that it substantially mitigates the privacy leakage caused by our second attack.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringSimilar Papers 제목 키워드 기반
Mask-based Membership Inference Attacks for Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has been an effective approach to mitigate hallucinations in large language models (LLMs) by incorporating up-to-date and domain-specific knowledge. Recently, there has been a trend o…
RAGRetrievalRetrieval-augmented GenerationRiddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to generate grounded responses by leveraging external knowledge databases without altering model parameters. Although the absence of weight tuning…
Membership Inference AttackRAGRetrievalRetrieval-augmented GenerationMembership Inference Attack against Long-Context Large Language Models
Recent advances in Large Language Models (LLMs) have enabled them to overcome their context window limitations, and demonstrate exceptional retrieval and reasoning capacities on longer context. Quesion-answering systems …
Inference AttackMembership Inference AttackSemantic SimilaritySemantic Textual SimilarityDocMIA: Document-Level Membership Inference Attacks against DocVQA Models
Document Visual Question Answering (DocVQA) has introduced a new paradigm for end-to-end document understanding, and quickly became one of the standard benchmarks for multimodal LLMs. Automating document processing workf…
document understandingInference AttackMembership Inference AttackQuestion Answering+1E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
Retrieval-Augmented Generation (RAG) equips large language models (LLMs) with external evidence by retrieving documents at inference time, but it also turns the retrieval corpusinto a sensitive asset. Under a black-box s…
Semantic Similarity