Noisy Neighbors: Efficient membership inference attacks against LLMs
The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory measures like GDPR and CCPA call for using robust auditing tools to address potential privacy issues, with Membership Inference Attacks (MIA) being the primary method for assessing LLMs' privacy risks. Differently from traditional MIA approaches, often requiring computationally intensive training of additional models, this paper introduces an efficient methodology that generates \textit{noisy neighbors} for a target sample by adding stochastic noise in the embedding space, requiring operating the target model in inference mode only. Our findings demonstrate that this approach closely matches the effectiveness of employing shadow models, showing its usability in practical privacy auditing scenarios.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Reconstruction and Membership Inference Attacks against Generative Models
We present two information leakage attacks that outperform previous work on membership inference against generative models. The first attack allows membership inference without assumptions on the type of the generative m…
Density EstimationInference AttackMembership Inference AttackOne Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy
Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a datas…
Label-Only Membership Inference Attacks
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 RegularizationPrivacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning
While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference,…
BIG-bench Machine LearningTransfer LearningSemi-Leak: Membership Inference Attacks Against Semi-supervised Learning
Semi-supervised learning (SSL) leverages both labeled and unlabeled data to train machine learning (ML) models. State-of-the-art SSL methods can achieve comparable performance to supervised learning by leveraging much fe…
Data AugmentationInference AttackMembership Inference Attack