paper-with-me

Papers

FiMMIA: scaling semantic perturbation-based membership inference across modalities

2025-12-02 · Anton Emelyanov, Sergei Kudriashov, Alena Fenogenova arxiv

Membership Inference Attacks (MIAs) aim to determine whether a specific data point was included in the training set of a target model. Although there are have been numerous methods developed for detecting data contamination in large language models (LLMs), their performance on multimodal LLMs (MLLMs) falls short due to the instabilities introduced through multimodal component adaptation and possible distribution shifts across multiple inputs. In this work, we investigate multimodal membership inference and address two issues: first, by identifying distribution shifts in the existing datasets, and second, by releasing an extended baseline pipeline to detect them. We also generalize the perturbation-based membership inference methods to MLLMs and release \textbf{FiMMIA} -- a modular \textbf{F}ramework for \textbf{M}ultimodal \textbf{MIA}.\footnote{The source code and framework have been made publicly available under the MIT license via \href{https://github.com/ai-forever/data_leakage_detect}{link}.The video demonstration is available on \href{https://youtu.be/a9L4-H80aSg}{YouTube}.} Our approach trains a neural network to analyze the target model's behavior on perturbed inputs, capturing distributional differences between members and non-members. Comprehensive evaluations on various fine-tuned multimodal models demonstrate the effectiveness of our perturbation-based membership inference attacks in multimodal domains.

📄 PDF Abstract BibTeX arXiv:2512.02786

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Semantic Membership Inference Attack against Large Language Models

2024-06-14 · Hamid Mozaffari, Virendra J. Marathe

Membership Inference Attacks (MIAs) determine whether a specific data point was included in the training set of a target model. In this paper, we introduce the Semantic Membership Inference Attack (SMIA), a novel approac…

Inference AttackMembership Inference Attack

Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries

2020-09-01 · Shadi Rahimian, Tribhuvanesh Orekondy, Mario Fritz

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was…

BIG-bench Machine LearningInference AttackMembership Inference Attack

Label-Only Membership Inference Attacks

2020-07-28 · Christopher A. Choquette-Choo, Florian Tramer, Nicholas Carlini, Nicolas Papernot

Membership inference attacks are one of the simplest forms of privacy leakage for machine learning models: given a data point and model, determine whether the point was used to train the model. Existing membership infere…

L2 Regularization

A Unified Perspective on Adversarial Membership Manipulation in Vision Models

2026-04-03 · Ruize Gao, Kaiwen Zhou, Yongqiang Chen, Feng Liu arxiv

Membership inference attacks (MIAs) aim to determine whether a specific data point was part of a model's training set, serving as effective tools for evaluating privacy leakage of vision models. However, existing MIAs im…

Adversarial Robustness

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models

2025-02-26 · Yu He, Boheng Li, Liu Liu, Zhongjie Ba 외

Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model's training set or not. Although prior research has extensively explored MIAs in Large Language Models (LLMs), they typically r…

Inference AttackMembership Inference AttackSemantic SimilaritySemantic Textual Similarity