paper-with-me

Papers

Sampling-based Pseudo-Likelihood for Membership Inference Attacks

2024-04-17 · Masahiro Kaneko, Youmi Ma, Yuki Wata, Naoaki Okazaki

Large Language Models (LLMs) are trained on large-scale web data, which makes it difficult to grasp the contribution of each text. This poses the risk of leaking inappropriate data such as benchmarks, personal information, and copyrighted texts in the training data. Membership Inference Attacks (MIA), which determine whether a given text is included in the model's training data, have been attracting attention. Previous studies of MIAs revealed that likelihood-based classification is effective for detecting leaks in LLMs. However, the existing methods cannot be applied to some proprietary models like ChatGPT or Claude 3 because the likelihood is unavailable to the user. In this study, we propose a Sampling-based Pseudo-Likelihood (\textbf{SPL}) method for MIA (\textbf{SaMIA}) that calculates SPL using only the text generated by an LLM to detect leaks. The SaMIA treats the target text as the reference text and multiple outputs from the LLM as text samples, calculates the degree of $n$-gram match as SPL, and determines the membership of the text in the training data. Even without likelihoods, SaMIA performed on par with existing likelihood-based methods.

📄 PDF Abstract BibTeX arXiv:2404.11262

Code (1)

nlp-titech/samia 공식 구현

Methods 이 논문이 사용한 방법론

SPL 설명 없음

Similar Papers 제목 키워드 기반

GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation

2024-05-13 · Andrey V. Galichin, Mikhail Pautov, Alexey Zhavoronkin, Oleg Y. Rogov 외

While Deep Neural Networks (DNNs) have demonstrated remarkable performance in tasks related to perception and control, there are still several unresolved concerns regarding the privacy of their training data, particularl…

image-classificationImage ClassificationInference AttackKnowledge Distillation+1

Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks

2022-03-08 · FatemehSadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick 외

The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs…

Inference AttackMembership Inference AttackMemorization

The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers

2025-10-17 · Owais Makroo, Siva Rajesh Kasa, Sumegh Roychowdhury, Karan Gupta 외 arxiv

Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despite extensive research on MIAs, systematic…

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

Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage

2024-02-15 · Achraf Azize, Debabrota Basu

In a Membership Inference (MI) game, an attacker tries to infer whether a target point was included or not in the input of an algorithm. Existing works show that some target points are easier to identify, while others ar…

Federated Learning