SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark

Membership inference (MI) attacks threaten user privacy through determining if a given data example has been used to train a target model. However, it has been increasingly recognized that the "comparing different MI attacks" methodology used in the existing works has serious limitations. Due to these limitations, we found (through the experiments in this work) that some comparison results reported in the literature are quite misleading. In this paper, we seek to develop a comprehensive benchmark for comparing different MI attacks, called MIBench, which consists not only the evaluation metrics, but also the evaluation scenarios. And we design the evaluation scenarios from four perspectives: the distance distribution of data samples in the target dataset, the distance between data samples of the target dataset, the differential distance between two datasets (i.e., the target dataset and a generated dataset with only nonmembers), and the ratio of the samples that are made no inferences by an MI attack. The evaluation metrics consist of ten typical evaluation metrics. We have identified three principles for the proposed "comparing different MI attacks" methodology, and we have designed and implemented the MIBench benchmark with 84 evaluation scenarios for each dataset. In total, we have used our benchmark to fairly and systematically compare 15 state-of-the-art MI attack algorithms across 588 evaluation scenarios, and these evaluation scenarios cover 7 widely used datasets and 7 representative types of models. All codes and evaluations of MIBench are publicly available at https://github.com/MIBench/MIBench.github.io/blob/main/README.md.

Gradient Leakage Defense with Key-Lock Module for Federated Learning

Federated Learning (FL) is a widely adopted privacy-preserving machine learning approach where private data remains local, enabling secure computations and the exchange of local model gradients between local clients and third-party parameter servers. However, recent findings reveal that privacy may be compromised and sensitive information potentially recovered from shared gradients. In this study, we offer detailed analysis and a novel perspective on understanding the gradient leakage problem. These theoretical works lead to a new gradient leakage defense technique that secures arbitrary model architectures using a private key-lock module. Only the locked gradient is transmitted to the parameter server for global model aggregation. Our proposed learning method is resistant to gradient leakage attacks, and the key-lock module is designed and trained to ensure that, without the private information of the key-lock module: a) reconstructing private training data from the shared gradient is infeasible; and b) the global model's inference performance is significantly compromised. We discuss the theoretical underpinnings of why gradients can leak private information and provide theoretical proof of our method's effectiveness. We conducted extensive empirical evaluations with a total of forty-four models on several popular benchmarks, demonstrating the robustness of our proposed approach in both maintaining model performance and defending against gradient leakage attacks.

Privacy-preserving Generative Framework Against Membership Inference Attacks

Artificial intelligence and machine learning have been integrated into all aspects of our lives and the privacy of personal data has attracted more and more attention. Since the generation of the model needs to extract the effective information of the training data, the model has the risk of leaking the privacy of the training data. Membership inference attacks can measure the model leakage of source data to a certain degree. In this paper, we design a privacy-preserving generative framework against membership inference attacks, through the information extraction and data generation capabilities of the generative model variational autoencoder (VAE) to generate synthetic data that meets the needs of differential privacy. Instead of adding noise to the model output or tampering with the training process of the target model, we directly process the original data. We first map the source data to the latent space through the VAE model to get the latent code, then perform noise process satisfying metric privacy on the latent code, and finally use the VAE model to reconstruct the synthetic data. Our experimental evaluation demonstrates that the machine learning model trained with newly generated synthetic data can effectively resist membership inference attacks and still maintain high utility.

Backdoor Defense with Machine Unlearning

Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASE, a novel method that can erase the backdoor injected into the victim model through machine unlearning. Specifically, BAERASE mainly implements backdoor defense in two key steps. First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model. Here, the trigger pattern recovery problem is equivalent to the one of extracting an unknown noise distribution from the victim model, which can be easily resolved by the entropy maximization based generative model. Subsequently, BAERASE leverages these recovered trigger patterns to reverse the backdoor injection procedure and induce the victim model to erase the polluted memories through a newly designed gradient ascent based machine unlearning method. Compared with the previous machine unlearning solutions, the proposed approach gets rid of the reliance on the full access to training data for retraining and shows higher effectiveness on backdoor erasing than existing fine-tuning or pruning methods. Moreover, experiments show that BAERASE can averagely lower the attack success rates of three kinds of state-of-the-art backdoor attacks by 99\% on four benchmark datasets.

Cloud-based Federated Boosting for Mobile Crowdsensing

The application of federated extreme gradient boosting to mobile crowdsensing apps brings several benefits, in particular high performance on efficiency and classification. However, it also brings a new challenge for data and model privacy protection. Besides it being vulnerable to Generative Adversarial Network (GAN) based user data reconstruction attack, there is not the existing architecture that considers how to preserve model privacy. In this paper, we propose a secret sharing based federated learning architecture FedXGB to achieve the privacy-preserving extreme gradient boosting for mobile crowdsensing. Specifically, we first build a secure classification and regression tree (CART) of XGBoost using secret sharing. Then, we propose a secure prediction protocol to protect the model privacy of XGBoost in mobile crowdsensing. We conduct a comprehensive theoretical analysis and extensive experiments to evaluate the security, effectiveness, and efficiency of FedXGB. The results indicate that FedXGB is secure against the honest-but-curious adversaries and attains less than 1% accuracy loss compared with the original XGBoost model.

Learn to Forget: User-Level Memorization Elimination in Federated Learning

Federated learning is a decentralized machine learning technique that evokes widespread attention in both the research field and the real-world market. However, the current privacy-preserving federated learning scheme only provides a secure way for the users to contribute their private data but never leaves a way to withdraw the contribution to model update. Such an irreversible setting potentially breaks the regulations about data protection and increases the risk of data extraction. To resolve the problem, this paper describes a novel concept for federated learning, called memorization elimination. Based on the concept, we propose \sysname, a federated learning framework that allows the user to eliminate the memorization of its private data in the trained model. Specifically, each user in \sysname is deployed with a trainable dummy gradient generator. After steps of training, the generator can produce dummy gradients to stimulate the neurons of a machine learning model to eliminate the memorization of the specific data. Also, we prove that the additional memorization elimination service of \sysname does not break the common procedure of federated learning or lower its security.