Do Membership Inference Attacks Work on Large Language Models?

Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. Despite extensive research on traditional machine learning models, there has been limited work studying MIA on the pre-training data of large language models (LLMs). We perform a large-scale evaluation of MIAs over a suite of language models (LMs) trained on the Pile, ranging from 160M to 12B parameters. We find that MIAs barely outperform random guessing for most settings across varying LLM sizes and domains. Our further analyses reveal that this poor performance can be attributed to (1) the combination of a large dataset and few training iterations, and (2) an inherently fuzzy boundary between members and non-members. We identify specific settings where LLMs have been shown to be vulnerable to membership inference and show that the apparent success in such settings can be attributed to a distribution shift, such as when members and non-members are drawn from the seemingly identical domain but with different temporal ranges. We release our code and data as a unified benchmark package that includes all existing MIAs, supporting future work.

SoK: Pitfalls in Evaluating Black-Box Attacks

Numerous works study black-box attacks on image classifiers. However, these works make different assumptions on the adversary's knowledge and current literature lacks a cohesive organization centered around the threat model. To systematize knowledge in this area, we propose a taxonomy over the threat space spanning the axes of feedback granularity, the access of interactive queries, and the quality and quantity of the auxiliary data available to the attacker. Our new taxonomy provides three key insights. 1) Despite extensive literature, numerous under-explored threat spaces exist, which cannot be trivially solved by adapting techniques from well-explored settings. We demonstrate this by establishing a new state-of-the-art in the less-studied setting of access to top-k confidence scores by adapting techniques from well-explored settings of accessing the complete confidence vector, but show how it still falls short of the more restrictive setting that only obtains the prediction label, highlighting the need for more research. 2) Identification the threat model of different attacks uncovers stronger baselines that challenge prior state-of-the-art claims. We demonstrate this by enhancing an initially weaker baseline (under interactive query access) via surrogate models, effectively overturning claims in the respective paper. 3) Our taxonomy reveals interactions between attacker knowledge that connect well to related areas, such as model inversion and extraction attacks. We discuss how advances in other areas can enable potentially stronger black-box attacks. Finally, we emphasize the need for a more realistic assessment of attack success by factoring in local attack runtime. This approach reveals the potential for certain attacks to achieve notably higher success rates and the need to evaluate attacks in diverse and harder settings, highlighting the need for better selection criteria.

SoK: Memorization in General-Purpose Large Language Models

Large Language Models (LLMs) are advancing at a remarkable pace, with myriad applications under development. Unlike most earlier machine learning models, they are no longer built for one specific application but are designed to excel in a wide range of tasks. A major part of this success is due to their huge training datasets and the unprecedented number of model parameters, which allow them to memorize large amounts of information contained in the training data. This memorization goes beyond mere language, and encompasses information only present in a few documents. This is often desirable since it is necessary for performing tasks such as question answering, and therefore an important part of learning, but also brings a whole array of issues, from privacy and security to copyright and beyond. LLMs can memorize short secrets in the training data, but can also memorize concepts like facts or writing styles that can be expressed in text in many different ways. We propose a taxonomy for memorization in LLMs that covers verbatim text, facts, ideas and algorithms, writing styles, distributional properties, and alignment goals. We describe the implications of each type of memorization - both positive and negative - for model performance, privacy, security and confidentiality, copyright, and auditing, and ways to detect and prevent memorization. We further highlight the challenges that arise from the predominant way of defining memorization with respect to model behavior instead of model weights, due to LLM-specific phenomena such as reasoning capabilities or differences between decoding algorithms. Throughout the paper, we describe potential risks and opportunities arising from memorization in LLMs that we hope will motivate new research directions.

Manipulating Transfer Learning for Property Inference

Transfer learning is a popular method for tuning pretrained (upstream) models for different downstream tasks using limited data and computational resources. We study how an adversary with control over an upstream model used in transfer learning can conduct property inference attacks on a victim's tuned downstream model. For example, to infer the presence of images of a specific individual in the downstream training set. We demonstrate attacks in which an adversary can manipulate the upstream model to conduct highly effective and specific property inference attacks (AUC score $> 0.9$), without incurring significant performance loss on the main task. The main idea of the manipulation is to make the upstream model generate activations (intermediate features) with different distributions for samples with and without a target property, thus enabling the adversary to distinguish easily between downstream models trained with and without training examples that have the target property. Our code is available at https://github.com/yulongt23/Transfer-Inference.

SoK: Let The Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to reconstruction attacks. Inspired by the success of games (i.e., probabilistic experiments) to study security properties in cryptography, some authors describe privacy inference risks in machine learning using a similar game-based style. However, adversary capabilities and goals are often stated in subtly different ways from one presentation to the other, which makes it hard to relate and compose results. In this paper, we present a game-based framework to systematize the body of knowledge on privacy inference risks in machine learning.

Dissecting Distribution Inference

A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well understood and demonstrated attacks often rely on strong and unrealistic assumptions such as full knowledge of training environments even in supposedly black-box threat scenarios. To improve understanding of distribution inference risks, we develop a new black-box attack that even outperforms the best known white-box attack in most settings. Using this new attack, we evaluate distribution inference risk while relaxing a variety of assumptions about the adversary's knowledge under black-box access, like known model architectures and label-only access. Finally, we evaluate the effectiveness of previously proposed defenses and introduce new defenses. We find that although noise-based defenses appear to be ineffective, a simple re-sampling defense can be highly effective. Code is available at https://github.com/iamgroot42/dissecting_distribution_inference

Subject Membership Inference Attacks in Federated Learning

Privacy in Federated Learning (FL) is studied at two different granularities: item-level, which protects individual data points, and user-level, which protects each user (participant) in the federation. Nearly all of the private FL literature is dedicated to studying privacy attacks and defenses at these two granularities. Recently, subject-level privacy has emerged as an alternative privacy granularity to protect the privacy of individuals (data subjects) whose data is spread across multiple (organizational) users in cross-silo FL settings. An adversary might be interested in recovering private information about these individuals (a.k.a. \emph{data subjects}) by attacking the trained model. A systematic study of these patterns requires complete control over the federation, which is impossible with real-world datasets. We design a simulator for generating various synthetic federation configurations, enabling us to study how properties of the data, model design and training, and the federation itself impact subject privacy risk. We propose three attacks for \emph{subject membership inference} and examine the interplay between all factors within a federation that affect the attacks' efficacy. We also investigate the effectiveness of Differential Privacy in mitigating this threat. Our takeaways generalize to real-world datasets like FEMNIST, giving credence to our findings.

Formalizing and Estimating Distribution Inference Risks

Property inference attacks reveal statistical properties about a training set but are difficult to distinguish from the intrinsic purpose of statistical machine learning, namely to produce models that capture statistical properties about a distribution. Motivated by Yeom et al.'s membership inference framework, we propose a formal and general definition of property inference attacks. The proposed notion describes attacks that can distinguish between possible training distributions, extending beyond previous property inference attacks that infer the ratio of a particular type of data in the training data set such as the proportion of females. We show how our definition captures previous property inference attacks as well as a new attack that can reveal the average node degree or clustering coefficient of a training graph. Our definition also enables a theorem that connects the maximum possible accuracy of inference attacks distinguishing between distributions to the effective size of dataset leaked by the model. To quantify and understand property inference risks, we conduct a series of experiments across a range of different distributions using both black-box and white-box attacks. Our results show that inexpensive attacks are often as effective as expensive meta-classifier attacks, and that there are surprising asymmetries in the effectiveness of attacks. We also extend the state-of-the-art property inference attack to work on convolutional neural networks, and propose techniques to help identify parameters in a model that leak the most information, thus significantly lowering resource requirements for meta-classifier attacks.

Formalizing Distribution Inference Risks

Property inference attacks reveal statistical properties about a training set but are difficult to distinguish from the primary purposes of statistical machine learning, which is to produce models that capture statistical properties about a distribution. Motivated by Yeom et al.'s membership inference framework, we propose a formal and generic definition of property inference attacks. The proposed notion describes attacks that can distinguish between possible training distributions, extending beyond previous property inference attacks that infer the ratio of a particular type of data in the training data set. In this paper, we show how our definition captures previous property inference attacks as well as a new attack that reveals the average degree of nodes of a training graph and report on experiments giving insight into the potential risks of property inference attacks.

One Neuron to Fool Them All

Despite vast research in adversarial examples, the root causes of model susceptibility are not well understood. Instead of looking at attack-specific robustness, we propose a notion that evaluates the sensitivity of individual neurons in terms of how robust the model's output is to direct perturbations of that neuron's output. Analyzing models from this perspective reveals distinctive characteristics of standard as well as adversarially-trained robust models, and leads to several curious results. In our experiments on CIFAR-10 and ImageNet, we find that attacks using a loss function that targets just a single sensitive neuron find adversarial examples nearly as effectively as ones that target the full model. We analyze the properties of these sensitive neurons to propose a regularization term that can help a model achieve robustness to a variety of different perturbation constraints while maintaining accuracy on natural data distributions. Code for all our experiments is available at https://github.com/iamgroot42/sauron .