Cen Chen

Huimin Chen, Fengran Mo, Yanhao Wang et al.

As privacy issues are receiving increasing attention within the Natural Language Processing (NLP) community, numerous methods have been proposed to sanitize texts subject to differential privacy. However, the state-of-the-art text sanitization mechanisms based on metric local differential privacy (MLDP) do not apply to non-metric semantic similarity measures and cannot achieve good trade-offs between privacy and utility. To address the above limitations, we propose a novel Customized Text (CusText) sanitization mechanism based on the original $ε$-differential privacy (DP) definition, which is compatible with any similarity measure. Furthermore, CusText assigns each input token a customized output set of tokens to provide more advanced privacy protection at the token level. Extensive experiments on several benchmark datasets show that CusText achieves a better trade-off between privacy and utility than existing mechanisms. The code is available at https://github.com/sai4july/CusText.

Tianchen Zhou, Zhanyi Hu, Bingzhe Wu et al.

Data privacy concerns has made centralized training of data, which is scattered across silos, infeasible, leading to the need for collaborative learning frameworks. To address that, two prominent frameworks emerged, i.e., federated learning (FL) and split learning (SL). While FL has established various benchmark frameworks and research libraries,SL currently lacks a unified library despite its diversity in terms of label sharing, model aggregation, and cut layer choice. This lack of standardization makes comparing SL paradigms difficult. To address this, we propose SLPerf, a unified research framework and open research library for SL, and conduct extensive experiments on four widely-used datasets under both IID and Non-IID data settings. Our contributions include a comprehensive survey of recently proposed SL paradigms, a detailed benchmark comparison of different SL paradigms in different situations, and rich engineering take-away messages and research insights for improving SL paradigms. SLPerf can facilitate SL algorithm development and fair performance comparisons. The code is available at https://github.com/Rainysponge/Split-learning-Attacks .

Tiandi Ye, Cen Chen, Yinggui Wang et al.

Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A recent study conducted by Qin et al. (2023) marks the initial exploration of backdoor attacks within the personalized federated learning (pFL) scenario, where each client constructs a personalized model based on its local data. Notably, the study demonstrates that pFL methods with \textit{parameter decoupling} can significantly enhance robustness against backdoor attacks. However, in this paper, we whistleblow that pFL methods with parameter decoupling are still vulnerable to backdoor attacks. The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts. We analyze two direct causes of the heterogeneous classifiers: (1) data heterogeneity inherently exists among clients and (2) poisoning by malicious clients further exacerbates the data heterogeneity. To address these issues, we propose a two-pronged attack method, BapFL, which comprises two simple yet effective strategies: (1) poisoning only the feature encoder while keeping the classifier fixed and (2) diversifying the classifier through noise introduction to simulate that of the benign clients. Extensive experiments on three benchmark datasets under varying conditions demonstrate the effectiveness of our proposed attack. Additionally, we evaluate the effectiveness of six widely used defense methods and find that BapFL still poses a significant threat even in the presence of the best defense, Multi-Krum. We hope to inspire further research on attack and defense strategies in pFL scenarios. The code is available at: https://github.com/BapFL/code.

Tiandi Ye, Cen Chen, Yinggui Wang et al.

Personalized federated learning has gained significant attention as a promising approach to address the challenge of data heterogeneity. In this paper, we address a relatively unexplored problem in federated learning. When a federated model has been trained and deployed, and an unlabeled new client joins, providing a personalized model for the new client becomes a highly challenging task. To address this challenge, we extend the adaptive risk minimization technique into the unsupervised personalized federated learning setting and propose our method, FedTTA. We further improve FedTTA with two simple yet effective optimization strategies: enhancing the training of the adaptation model with proxy regularization and early-stopping the adaptation through entropy. Moreover, we propose a knowledge distillation loss specifically designed for FedTTA to address the device heterogeneity. Extensive experiments on five datasets against eleven baselines demonstrate the effectiveness of our proposed FedTTA and its variants. The code is available at: https://github.com/anonymous-federated-learning/code.

Mingyuan Fan, Cen Chen, Chengyu Wang et al.

Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i.e., sever and clients only hold partial sub-networks and exchange intermediate computations). However, existing research has mainly focused on examining its reliability for privacy protection, with little investigation into model security. Specifically, by exploring full models, attackers can launch adversarial attacks, and split learning can mitigate this severe threat by only disclosing part of models to untrusted servers.This paper aims to evaluate the robustness of split learning against adversarial attacks, particularly in the most challenging setting where untrusted servers only have access to the intermediate layers of the model.Existing adversarial attacks mostly focus on the centralized setting instead of the collaborative setting, thus, to better evaluate the robustness of split learning, we develop a tailored attack called SPADV, which comprises two stages: 1) shadow model training that addresses the issue of lacking part of the model and 2) local adversarial attack that produces adversarial examples to evaluate.The first stage only requires a few unlabeled non-IID data, and, in the second stage, SPADV perturbs the intermediate output of natural samples to craft the adversarial ones. The overall cost of the proposed attack process is relatively low, yet the empirical attack effectiveness is significantly high, demonstrating the surprising vulnerability of split learning to adversarial attacks.

Wei Huang, Yinggui Wang, Cen Chen

By inducing privacy attacks on NLP models, attackers can obtain sensitive information such as training data and model parameters, etc. Although researchers have studied, in-depth, several kinds of attacks in NLP models, they are non-systematic analyses. It lacks a comprehensive understanding of the impact caused by the attacks. For example, we must consider which scenarios can apply to which attacks, what the common factors are that affect the performance of different attacks, the nature of the relationships between different attacks, and the influence of various datasets and models on the effectiveness of the attacks, etc. Therefore, we need a benchmark to holistically assess the privacy risks faced by NLP models. In this paper, we present a privacy attack and defense evaluation benchmark in the field of NLP, which includes the conventional/small models and large language models (LLMs). This benchmark supports a variety of models, datasets, and protocols, along with standardized modules for comprehensive evaluation of attacks and defense strategies. Based on the above framework, we present a study on the association between auxiliary data from different domains and the strength of privacy attacks. And we provide an improved attack method in this scenario with the help of Knowledge Distillation (KD). Furthermore, we propose a chained framework for privacy attacks. Allowing a practitioner to chain multiple attacks to achieve a higher-level attack objective. Based on this, we provide some defense and enhanced attack strategies. The code for reproducing the results can be found at https://github.com/user2311717757/nlp_doctor.

Mingyuan Fan, Chengyu Wang, Cen Chen et al.

Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life. However, the practical implementations of these models have also exposed inherent risks, bringing to the forefront their evil sides and sparking concerns regarding their trustworthiness. Despite the wealth of literature on this subject, a comprehensive survey specifically delving into the intersection of large-scale generative models and their trustworthiness remains largely absent. To bridge this gap, this paper investigates both the long-standing and emerging threats associated with these models across four fundamental dimensions: 1) privacy, 2) security, 3) fairness, and 4) responsibility. Based on the investigation results, we develop an extensive map outlining the trustworthiness of large generative models. After that, we provide practical recommendations and potential research directions for future secure applications equipped with large generative models, ultimately promoting the trustworthiness of the models and benefiting the society as a whole.

Qianyi Zhao, Chen Qu, Cen Chen et al.

With increasing concerns and regulations on data privacy, fine-tuning pretrained language models (PLMs) in federated learning (FL) has become a common paradigm for NLP tasks. Despite being extensively studied, the existing methods for this problem still face two primary challenges. First, the huge number of parameters in large-scale PLMs leads to excessive communication and computational overhead. Second, the heterogeneity of data and tasks across clients poses a significant obstacle to achieving the desired fine-tuning performance. To address the above problems, we propose FedMCP, a novel parameter-efficient fine-tuning method with model-contrastive personalization for FL. Specifically, FedMCP adds two lightweight adapter modules, i.e., the global adapter and the private adapter, to the frozen PLMs within clients. In a communication round, each client sends only the global adapter to the server for federated aggregation. Furthermore, FedMCP introduces a model-contrastive regularization term between the two adapters. This, on the one hand, encourages the global adapter to assimilate universal knowledge and, on the other hand, the private adapter to capture client-specific knowledge. By leveraging both adapters, FedMCP can effectively provide fine-tuned personalized models tailored to individual clients. Extensive experiments on highly heterogeneous cross-task, cross-silo datasets show that FedMCP achieves substantial performance improvements over state-of-the-art FL fine-tuning approaches for PLMs.

Mingyuan Fan, Yang Liu, Cen Chen et al.

Adversarial attack has garnered considerable attention due to its profound implications for the secure deployment of robots in sensitive security scenarios. To potentially push for advances in the field, this paper studies the adversarial attack in the black-box setting and proposes an unlabeled data-driven adversarial attack method, called SemiAdv. Specifically, SemiAdv achieves the following breakthroughs compared with previous works. First, by introducing the semi-supervised learning technique into the adversarial attack, SemiAdv substantially decreases the number of queries required for generating adversarial samples. On average, SemiAdv only needs to query a few hundred times to launch an effective attack with more than 90% success rate. Second, many existing black-box adversarial attacks require massive labeled data to mitigate the difference between the local substitute model and the remote target model for a good attack performance. While SemiAdv relaxes this limitation and is capable of utilizing unlabeled raw data to launch an effective attack. Finally, our experiments show that SemiAdv saves up to 12x query accesses for generating adversarial samples while maintaining a competitive attack success rate compared with state-of-the-art attacks.

Die Chen, Zhongjie Duan, Zhiwen Li et al.

Recent breakthroughs in text-to-image diffusion models have significantly enhanced both the visual fidelity and semantic controllability of generated images. However, fine-grained control over aesthetic attributes remains challenging, especially when users require continuous and intensity-specific adjustments. Existing approaches often rely on vague textual prompts, which are inherently ambiguous in expressing both the aesthetic semantics and the desired intensity, or depend on costly human preference data for alignment, limiting their scalability and practicality. To address these limitations, we propose AttriCtrl, a plug-and-play framework for precise and continuous control of aesthetic attributes. Specifically, we quantify abstract aesthetics by leveraging semantic similarity from pre-trained vision-language models, and employ a lightweight value encoder that maps scalar intensities in $[0,1]$ to learnable embeddings within diffusion-based generation. This design enables intuitive and customizable aesthetic manipulation, with minimal training overhead and seamless integration into existing generation pipelines. Extensive experiments demonstrate that AttriCtrl achieves accurate control over individual attributes as well as flexible multi-attribute composition. Moreover, it is fully compatible with popular open-source controllable generation frameworks, showcasing strong integration capability and practical utility across diverse generation scenarios.

Zhiwen Li, Die Chen, Mingyuan Fan et al.

The remarkable ability of diffusion models to generate high-fidelity images has led to their widespread adoption. However, concerns have also arisen regarding their potential to produce Not Safe for Work (NSFW) content and exhibit social biases, hindering their practical use in real-world applications. In response to this challenge, prior work has focused on employing security filters to identify and exclude toxic text, or alternatively, fine-tuning pre-trained diffusion models to erase sensitive concepts. Unfortunately, existing methods struggle to achieve satisfactory performance in the sense that they can have a significant impact on the normal model output while still failing to prevent the generation of harmful content in some cases. In this paper, we propose a novel self-discovery approach to identifying a semantic direction vector in the embedding space to restrict text embedding within a safe region. Our method circumvents the need for correcting individual words within the input text and steers the entire text prompt towards a safe region in the embedding space, thereby enhancing model robustness against all possibly unsafe prompts. In addition, we employ Low-Rank Adaptation (LoRA) for semantic direction vector initialization to reduce the impact on the model performance for other semantics. Furthermore, our method can also be integrated with existing methods to improve their social responsibility. Extensive experiments on benchmark datasets demonstrate that our method can effectively reduce NSFW content and mitigate social bias generated by diffusion models compared to several state-of-the-art baselines.

Dongyu Liu, Xuhong Wang, Cen Chen et al.

In recent years, there has been an increasing interest in image anonymization, particularly focusing on the de-identification of faces and individuals. However, for self-driving applications, merely de-identifying faces and individuals might not provide sufficient privacy protection since street views like vehicles and buildings can still disclose locations, trajectories, and other sensitive information. Therefore, it remains crucial to extend anonymization techniques to street view images to fully preserve the privacy of users, pedestrians, and vehicles. In this paper, we propose a Street View Image Anonymization (SVIA) framework for self-driving applications. The SVIA framework consists of three integral components: a semantic segmenter to segment an input image into functional regions, an inpainter to generate alternatives to privacy-sensitive regions, and a harmonizer to seamlessly stitch modified regions to guarantee visual coherence. Compared to existing methods, SVIA achieves a much better trade-off between image generation quality and privacy protection, as evidenced by experimental results for five common metrics on two widely used public datasets.

Tiandi Ye, Wenyan Liu, Kai Yao et al.

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (pFL) has gained increasing attention for its ability to address data heterogeneity. However, most existing pFL methods assume that each client's data follows a single distribution and learn one client-level personalized model for each client. This assumption often fails in practice, where a single client may possess data from multiple sources or domains, resulting in significant intra-client heterogeneity and suboptimal performance. To tackle this challenge, we propose pFedBayesPT, a fine-grained instance-wise pFL framework based on visual prompt tuning. Specifically, we formulate instance-wise prompt generation from a Bayesian perspective and model the prompt posterior as an implicit distribution to capture diverse visual semantics. We derive a variational training objective under the semi-implicit variational inference framework. Extensive experiments on benchmark datasets demonstrate that pFedBayesPT consistently outperforms existing pFL methods under both feature and label heterogeneity settings.

Jianwei Wang, Chengming Shi, Junyao Yang et al.

The success of large language models (LLMs) has attracted many individuals to fine-tune them for domain-specific tasks by uploading their data. However, in sensitive areas like healthcare and finance, privacy concerns often arise. One promising solution is to generate synthetic data with Differential Privacy (DP) guarantees to replace private data. However, these synthetic data contain significant flawed data, which are considered as noise. Existing solutions typically rely on naive filtering by comparing ROUGE-L scores or embedding similarities, which are ineffective in addressing the noise. To address this issue, we propose \textit{RewardDS}, a novel privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation. Our \textit{RewardDS} introduces two key modules, Reward Guided Filtering and Self-Optimizing Refinement, to both filter and refine the synthetic data, effectively mitigating the noise. Extensive experiments across medical, financial, and code generation domains demonstrate the effectiveness of our method.

Zhongjie Duan, Qianyi Zhao, Cen Chen et al.

The emergence of diffusion models has significantly advanced image synthesis. The recent studies of model interaction and self-corrective reasoning approach in large language models offer new insights for enhancing text-to-image models. Inspired by these studies, we propose a novel method called ArtAug for enhancing text-to-image models in this paper. To the best of our knowledge, ArtAug is the first one that improves image synthesis models via model interactions with understanding models. In the interactions, we leverage human preferences implicitly learned by image understanding models to provide fine-grained suggestions for image synthesis models. The interactions can modify the image content to make it aesthetically pleasing, such as adjusting exposure, changing shooting angles, and adding atmospheric effects. The enhancements brought by the interaction are iteratively fused into the synthesis model itself through an additional enhancement module. This enables the synthesis model to directly produce aesthetically pleasing images without any extra computational cost. In the experiments, we train the ArtAug enhancement module on existing text-to-image models. Various evaluation metrics consistently demonstrate that ArtAug enhances the generative capabilities of text-to-image models without incurring additional computational costs. The source code and models will be released publicly.

Yiping Wang, Yanhao Wang, Cen Chen

The sliding window model of computation captures scenarios in which data are continually arriving in the form of a stream, and only the most recent $w$ items are used for analysis. In this setting, an algorithm needs to accurately track some desired statistics over the sliding window using a small space. When data streams contain sensitive information about individuals, the algorithm is also urgently needed to provide a provable guarantee of privacy. In this paper, we focus on the two fundamental problems of privately (1) estimating the frequency of an arbitrary item and (2) identifying the most frequent items (i.e., \emph{heavy hitters}), in the sliding window model. We propose \textsc{DPSW-Sketch}, a sliding window framework based on the count-min sketch that not only satisfies differential privacy over the stream but also approximates the results for frequency and heavy-hitter queries within bounded errors in sublinear time and space w.r.t.~$w$. Extensive experiments on five real-world and synthetic datasets show that \textsc{DPSW-Sketch} provides significantly better utility-privacy trade-offs than state-of-the-art methods.

Ziqian Zeng, Jianwei Wang, Junyao Yang et al.

The widespread usage of online Large Language Models (LLMs) inference services has raised significant privacy concerns about the potential exposure of private information in user inputs to malicious eavesdroppers. Existing privacy protection methods for LLMs suffer from either insufficient privacy protection, performance degradation, or large inference time overhead. To address these limitations, we propose PrivacyRestore, a plug-and-play method to protect the privacy of user inputs during LLM inference. The server first trains restoration vectors for each privacy span and then release to clients. Privacy span is defined as a contiguous sequence of tokens within a text that contain private information. The client then aggregate restoration vectors of all privacy spans in the input into a single meta restoration vector which is later sent to the server side along with the input without privacy spans.The private information is restored via activation steering during inference. Furthermore, we prove that PrivacyRestore inherently prevents the linear growth of the privacy budget.We create three datasets, covering medical and legal domains, to evaluate the effectiveness of privacy preserving methods. The experimental results show that PrivacyRestore effectively protects private information and maintain acceptable levels of performance and inference overhead.

Jamie Cui, Cen Chen, Tiandi Ye et al.

Recently, Niu, et. al. introduced a new variant of Federated Learning (FL), called Federated Submodel Learning (FSL). Different from traditional FL, each client locally trains the submodel (e.g., retrieved from the servers) based on its private data and uploads a submodel at its choice to the servers. Then all clients aggregate all their submodels and finish the iteration. Inevitably, FSL introduces two privacy-preserving computation tasks, i.e., Private Submodel Retrieval (PSR) and Secure Submodel Aggregation (SSA). Existing work fails to provide a loss-less scheme, or has impractical efficiency. In this work, we leverage Distributed Point Function (DPF) and cuckoo hashing to construct a practical and light-weight secure FSL scheme in the two-server setting. More specifically, we propose two basic protocols with few optimisation techniques, which ensures our protocol practicality on specific real-world FSL tasks. Our experiments show that our proposed protocols can finish in less than 1 minute when weight sizes $\leq 2^{15}$, we also demonstrate protocol efficiency by comparing with existing work and by handling a real-world FSL task.

Yuchen Li, Yifan Bao, Liyao Xiang et al.

Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties. It is renowned for preserving privacy as the data never leaves the computational devices, and recent approaches further enhance its privacy by hiding messages transferred in encryption. However, we found that despite the efforts, federated learning remains privacy-threatening, due to its interactive nature across different parties. In this paper, we analyze the privacy threats in industrial-level federated learning frameworks with secure computation, and reveal such threats widely exist in typical machine learning models such as linear regression, logistic regression and decision tree. For the linear and logistic regression, we show through theoretical analysis that it is possible for the attacker to invert the entire private input of the victim, given very few information. For the decision tree model, we launch an attack to infer the range of victim's private inputs. All attacks are evaluated on popular federated learning frameworks and real-world datasets.

Shuang Zhang, Liyao Xiang, Xi Yu et al.

Real-world data is usually segmented by attributes and distributed across different parties. Federated learning empowers collaborative training without exposing local data or models. As we demonstrate through designed attacks, even with a small proportion of corrupted data, an adversary can accurately infer the input attributes. We introduce an adversarial learning based procedure which tunes a local model to release privacy-preserving intermediate representations. To alleviate the accuracy decline, we propose a defense method based on the forward-backward splitting algorithm, which respectively deals with the accuracy loss and privacy loss in the forward and backward gradient descent steps, achieving the two objectives simultaneously. Extensive experiments on a variety of datasets have shown that our defense significantly mitigates privacy leakage with negligible impact on the federated learning task.

Jun Zhou, Longfei Zheng, Chaochao Chen et al.

Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build privacy preserving DNN models from either algorithmic perspective or cryptographic perspective. The former mainly splits the DNN computation graph between data holders or between data holders and server, which demonstrates good scalability but suffers from accuracy loss and potential privacy risks. In contrast, the latter leverages time-consuming cryptographic techniques, which has strong privacy guarantee but poor scalability. In this paper, we propose SPNN - a Scalable and Privacy-preserving deep Neural Network learning framework, from algorithmic-cryptographic co-perspective. From algorithmic perspective, we split the computation graph of DNN models into two parts, i.e., the private data related computations that are performed by data holders and the rest heavy computations that are delegated to a server with high computation ability. From cryptographic perspective, we propose using two types of cryptographic techniques, i.e., secret sharing and homomorphic encryption, for the isolated data holders to conduct private data related computations privately and cooperatively. Furthermore, we implement SPNN in a decentralized setting and introduce user-friendly APIs. Experimental results conducted on real-world datasets demonstrate the superiority of SPNN.

Yilun Lin, Chaochao Chen, Cen Chen et al.

Federated learning (FL) has attracted increasing attention in recent years. As a privacy-preserving collaborative learning paradigm, it enables a broader range of applications, especially for computer vision and natural language processing tasks. However, to date, there is limited research of federated learning on relational data, namely Knowledge Graph (KG). In this work, we present a modified version of the graph neural network algorithm that performs federated modeling over KGs across different participants. Specifically, to tackle the inherent data heterogeneity issue and inefficiency in algorithm convergence, we propose a novel optimization algorithm, named FedAlign, with 1) optimal transportation (OT) for on-client personalization and 2) weight constraint to speed up the convergence. Extensive experiments have been conducted on several widely used datasets. Empirical results show that our proposed method outperforms the state-of-the-art FL methods, such as FedAVG and FedProx, with better convergence.

Huiwen Wu, Cen Chen, Li Wang

In the era of big data, the need to expand the amount of data through data sharing to improve model performance has become increasingly compelling. As a result, effective collaborative learning models need to be developed with respect to both privacy and utility concerns. In this work, we propose a new federated multi-task learning method for effective parameter transfer with differential privacy to protect gradients at the client level. Specifically, the lower layers of the networks are shared across all clients to capture transferable feature representation, while top layers of the network are task-specific for on-client personalization. Our proposed algorithm naturally resolves the statistical heterogeneity problem in federated networks. We are, to the best of knowledge, the first to provide both privacy and utility guarantees for such a proposed federated algorithm. The convergences are proved for the cases with Lipschitz smooth objective functions under the non-convex, convex, and strongly convex settings. Empirical experiment results on different datasets have been conducted to demonstrate the effectiveness of the proposed algorithm and verify the implications of the theoretical findings.

Bin Zhang, Cen Chen, Li Wang

The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models. However, data is a valuable resource and are always held by different parties in reality. An effective solution to such a data isolation problem is to employ federated learning, which allows multiple parties to collaboratively train a model. In this paper, we propose a Secure version of the widely used Maximum Mean Discrepancy (SMMD) based on homomorphic encryption to enable effective knowledge transfer under the data federation setting without compromising the data privacy. The proposed SMMD is able to avoid the potential information leakage in transfer learning when aligning the source and target data distribution. As a result, both the source domain and target domain can fully utilize their data to build more scalable models. Experimental results demonstrate that our proposed SMMD is secure and effective.

Cen Chen, Bingzhe Wu, Minghui Qiu et al.

Transfer learning is widely used for transferring knowledge from a source domain to the target domain where the labeled data is scarce. Recently, deep transfer learning has achieved remarkable progress in various applications. However, the source and target datasets usually belong to two different organizations in many real-world scenarios, potential privacy issues in deep transfer learning are posed. In this study, to thoroughly analyze the potential privacy leakage in deep transfer learning, we first divide previous methods into three categories. Based on that, we demonstrate specific threats that lead to unintentional privacy leakage in each category. Additionally, we also provide some solutions to prevent these threats. To the best of our knowledge, our study is the first to provide a thorough analysis of the information leakage issues in deep transfer learning methods and provide potential solutions to the issue. Extensive experiments on two public datasets and an industry dataset are conducted to show the privacy leakage under different deep transfer learning settings and defense solution effectiveness.

Bingzhe Wu, Chaochao Chen, Shiwan Zhao et al.

Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD) is an effective method to enable Bayesian deep learning on large-scale datasets. Previous theoretical studies have shown various appealing properties of SGLD, ranging from the convergence properties to the generalization bounds. In this paper, we study the properties of SGLD from a novel perspective of membership privacy protection (i.e., preventing the membership attack). The membership attack, which aims to determine whether a specific sample is used for training a given DNN model, has emerged as a common threat against deep learning algorithms. To this end, we build a theoretical framework to analyze the information leakage (w.r.t. the training dataset) of a model trained using SGLD. Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent. Moreover, our theoretical analysis can be naturally extended to other types of Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods. Empirical results on different datasets and models verify our theoretical findings and suggest that the SGLD algorithm can not only reduce the information leakage but also improve the generalization ability of the DNN models in real-world applications.