Sampling-based Pseudo-Likelihood for Membership Inference Attacks
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.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
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+1Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
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 AttackMemorizationThe Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
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
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 AttackSome Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage
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