paper-with-me

Papers

Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answering

2026-05-05 · Tejas Kulkarni, Antti Koskela, Laith Zumot arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.04116

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Mask-based Membership Inference Attacks for Retrieval-Augmented Generation

2024-10-26 · Mingrui Liu, Sixiao Zhang, Cheng Long

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 Generation

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation

2025-02-01 · Ali Naseh, Yuefeng Peng, Anshuman Suri, Harsh Chaudhari 외

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 Generation

Membership Inference Attack against Long-Context Large Language Models

2024-11-18 · Zixiong Wang, Gaoyang Liu, Yang Yang, Chen Wang

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 Similarity

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

2025-02-06 · Khanh Nguyen, Raouf Kerkouche, Mario Fritz, Dimosthenis Karatzas

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+1

E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems

2026-05-01 · Zelin Guan, Shengda Zhuo, Zeyan Li, Jinchun He 외 arxiv

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