FiMMIA: 在多模态领域中扩展基于语义扰动的成员推断
FiMMIA: scaling semantic perturbation-based membership inference across modalities
AI总结:
本文提出FiMMIA框架,用于多模态大语言模型中的成员推断攻击,通过识别数据分布偏移和改进基线流程,提升对抗检测性能。
摘要:
成员推断攻击(MIAs)旨在确定特定数据点是否包含在目标模型的训练集中。尽管已有许多方法用于检测大型语言模型(LLMs)中的数据污染,但其在多模态大语言模型(MLLMs)上的表现不足,因为多模态组件适应引入了不稳定性,并可能在多个输入之间产生分布偏移。本文研究了多模态成员推断,并解决了两个问题:首先,通过识别现有数据集中的分布偏移;其次,通过发布一个扩展的基线流程来检测它们。我们还将基于扰动的成员推断方法推广到MLLMs,并发布FiMMIA——一个多模态成员推断的模块化框架。我们的方法训练神经网络分析目标模型在扰动输入上的行为,捕捉成员和非成员之间的分布差异。在各种微调多模态模型上的全面评估证明了我们基于扰动的成员推断攻击在多模态领域中的有效性。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。