paper-with-me

Papers

Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?

2019-04-11 · TACL 2020 1 · Sorami Hisamoto, Matt Post, Kevin Duh

Data privacy is an important issue for "machine learning as a service" providers. We focus on the problem of membership inference attacks: given a data sample and black-box access to a model's API, determine whether the sample existed in the model's training data. Our contribution is an investigation of this problem in the context of sequence-to-sequence models, which are important in applications such as machine translation and video captioning. We define the membership inference problem for sequence generation, provide an open dataset based on state-of-the-art machine translation models, and report initial results on whether these models leak private information against several kinds of membership inference attacks.

📄 PDF Abstract BibTeX arXiv:1904.05506

Code (1)

sorami/TACL-Membership 공식 구현

Tasks

Machine TranslationTranslationVideo Captioning

Similar Papers 제목 키워드 기반

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models

2024-09-11 · Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi 외

Prior Membership Inference Attacks (MIAs) on pre-trained Large Language Models (LLMs), adapted from classification model attacks, fail due to ignoring the generative process of LLMs across token sequences. In this paper,…

Memorization

Sequential Membership Inference Attacks

2026-02-18 · Thomas Michel, Debabrota Basu, Emilie Kaufmann arxiv

Modern AI models are not static. They go through multiple updates in their lifecycles. We propose to design Sequential Membership Inference (SeMI) attacks leading to tighter privacy audits by exploiting the sequence of m…

(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs

2025-10-07 · Jiashu Tao, Reza Shokri arxiv

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, whi…

Computational Efficiency

SeqMIA: Sequential-Metric Based Membership Inference Attack

2024-07-21 · Hao Li, Zheng Li, Siyuan Wu, Chengrui Hu 외

Most existing membership inference attacks (MIAs) utilize metrics (e.g., loss) calculated on the model's final state, while recent advanced attacks leverage metrics computed at various stages, including both intermediate…

Inference AttackKnowledge DistillationMembership Inference Attack

Membership Inference Attacks Against Text-to-image Generation Models

2022-10-03 · Yixin Wu, Ning Yu, Zheng Li, Michael Backes 외

Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requires huge amounts of data that might cont…

image-classificationImage ClassificationImage GenerationText to Image Generation+1