Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can reconstruct data samples from language models, making this threat scenario an important aspect of model release. Differential privacy is a known solution to such attacks, but is often used with a relatively large privacy budget (epsilon > 8) which does not translate to meaningful guarantees. In this paper we show that, for a same mechanism, we can derive privacy guarantees for reconstruction attacks that are better than the traditional ones from the literature. In particular, we show that larger privacy budgets do not protect against membership inference, but can still protect extraction of rare secrets. We show experimentally that our guarantees hold against various language models, including GPT-2 finetuned on Wikitext-103.
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peng Cheng Laboratory（鹏城实验室）；School of Computer and Information Engineering, Zhejiang Gongshang University（浙江工商大学计算机与信息工程学院）；Information Security and National Computing Grid Laboratory, Southwest Jiaotong University（西南交通大学）
Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching reconstruction and membership inference attacks. To defend such privacy attacks, many noises perturbation methods (like differential privacy or CountSketch matrix) have been widely designed. However, the strong defence ability and high learning accuracy of these schemes cannot be ensured at the same time, which will impede the wide application of FL in practice (…
Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
Huazhong University of Science and Technology（华中科技大学）；Griffith University（格里菲斯大学）；Union Hospital, Tongji Medical College, Huazhong University of Science and Technology（华中科技大学同济医学院附属协和医院）；Lehigh University（理海大学）
University of Oxford（牛津大学）；Imperial College London（帝国理工学院）；McGill University（麦吉尔大学）
Federated learning (FL) is a promising way to allow multiple data owners (clients) to collaboratively train machine learning models without compromising data privacy. Yet, existing FL solutions usually rely on a centralized aggregator for model weight aggregation, while assuming clients are honest. Even if data privacy can still be preserved, the problem of single-point failure and data poisoning attack from malicious clients remains unresolved. To tackle this challenge, we propose to use distributed ledger technology (DLT) to achieve FLock, a secure and reliable decentralized Federated Learni…
University of Potsdam（波茨坦大学）；Hasso Plattner Institute for Digital Engineering gGmbH（哈索·普拉特纳数字工程研究院）；Philips Research（飞利浦研究院）
Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we sim…
Recently researchers have studied input leakage problems in Federated Learning (FL) where a malicious party can reconstruct sensitive training inputs provided by users from shared gradient. It raises concerns about FL since input leakage contradicts the privacy-preserving intention of using FL. Despite a relatively rich literature on attacks and defenses of input reconstruction in Horizontal FL, input leakage and protection in vertical FL starts to draw researcher's attention recently. In this paper, we study how to defend against input leakage attacks in Vertical FL. We design an adversarial …
Duke University（杜克大学）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）
In a membership inference attack, an attacker aims to infer whether a data sample is in a target classifier's training dataset or not. Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier, which takes a data sample's confidence score vector predicted by the target classifier as an input and predicts the data sample to be a member or non-member of the target classifier's training dataset. Membership inference attacks pose severe privacy and security threats to the training dataset. Most existing defenses leverage differential privacy when trai…
Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
Tsinghua University（清华大学）；Institute for Network Science and Cyberspace, Tsinghua University（清华大学网络科学与网络空间研究院）；Beijing Institute of Technology（北京理工大学）；Lenovo Research（联想研究院）
Defending Against Poisoning Attacks in Federated Learning with Blockchain
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Imperial College London（帝国理工学院）；UiT The Arctic University of Norway（挪威北极大学）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in their devices. However, that same autonomy opens the door for malicious peers to poison the model by conducting either untargeted or targeted poisoning attacks. The label-flipping (LF) attack is a targeted poisoning attack where the attackers poison their training data by flipping the labels of some examples from one class (i.e., the source class) to another (i.e., the target class). Unfortunately, this attack is easy …
Convergent Differential Privacy Analysis for General Federated Learning
School of Computer Science Faculty of Engineering（计算机科学学院工程学院）；University of Sydney（悉尼大学）；Generative AI Lab（生成式人工智能实验室）；College of Computing and Data Science（计算与数据科学学院）；Nanyang Technological University（南洋理工大学）；School of Cyber Science and Technology（网络安全科学与技术学院）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）
Federated learning (FL) is a popular distributed learning framework that can reduce privacy risks by not explicitly sharing private data. However, recent works demonstrated that sharing model updates makes FL vulnerable to inference attacks. In this work, we show our key observation that the data representation leakage from gradients is the essential cause of privacy leakage in FL. We also provide an analysis of this observation to explain how the data presentation is leaked. Based on this observation, we propose a defense against model inversion attack in FL. The key idea of our defense is le…
Johns Hopkins University（约翰霍普金斯大学）；Applied Physics Laboratory（应用物理实验室）；University of Virginia（弗吉尼亚大学）
Machine learning (ML) models used in medical imaging diagnostics can be vulnerable to a variety of privacy attacks, including membership inference attacks, that lead to violations of regulations governing the use of medical data and threaten to compromise their effective deployment in the clinic. In contrast to most recent work in privacy-aware ML that has been focused on model alteration and post-processing steps, we propose here a novel and complementary scheme that enhances the security of medical data by controlling the data sharing process. We develop and evaluate a privacy defense protoc…
Institute for AI Industry Research, Tsinghua University（清华大学智能产业研究院）
Vertical Federated Learning (VFL) is widely utilized in real-world applications to enable collaborative learning while protecting data privacy and safety. However, previous works show that parties without labels (passive parties) in VFL can infer the sensitive label information owned by the party with labels (active party) or execute backdoor attacks to VFL. Meanwhile, active party can also infer sensitive feature information from passive party. All these pose new privacy and security challenges to VFL systems. We propose a new general defense method which limits the mutual information between…
Shanghai Jiao Tong University（上海交通大学）；Institute for Network Sciences and Cyberspace, Beijing National Research Center for Information Science and Technology, Tsinghua University（清华大学网络科学与网络空间研究院，北京信息科学与技术国家研究中心）
Learning-based Network Intrusion Detection Systems (NIDSs) are widely deployed for defending various cyberattacks. Existing learning-based NIDS mainly uses Neural Network (NN) as a classifier that relies on the quality and quantity of cyberattack data. Such NN-based approaches are also hard to interpret for improving efficiency and scalability. In this paper, we design a new local-global computation paradigm, FEDFOREST, a novel learning-based NIDS by combining the interpretable Gradient Boosting Decision Tree (GBDT) and Federated Learning (FL) framework. Specifically, FEDFOREST is composed of …
Stanford University（斯坦福大学）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）
In cloud computing environments with many virtual machines, containers, and other systems, an epidemic of malware can be highly threatening to business processes. In this vision paper, we introduce a hierarchical approach to performing malware detection and analysis using several recent advances in machine learning on graphs, hypergraphs, and natural language. We analyze individual systems and their logs, inspecting and understanding their behavior with attentional sequence models. Given a feature representation of each system's logs using this procedure, we construct an attributed network of …
German Research Center for Artificial Intelligence（德国人工智能研究中心）；Technical University of Darmstadt（达姆施塔特工业大学）；TU Dortmund University（多特蒙德工业大学）；Center for Trustworthy Data Science and Security, University Alliance Ruhr（鲁尔大学联盟可信数据科学与安全中心）；Hessian Center for AI (hessian.AI)（黑森州人工智能中心）；Centre for Cognitive Science TU Darmstadt（达姆施塔特工业大学认知科学中心）
Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
East China Normal University（东华师范大学）；The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）；Alibaba Group（阿里巴巴集团）
CISPA Helmholtz Center for Information Security（亥姆霍兹信息安全中心（CISPA））；Salesforce Research（赛富时研究院）；University of Maryland（马里兰大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
As a long-term threat to the privacy of training data, membership inference attacks (MIAs) emerge ubiquitously in machine learning models. Existing works evidence strong connection between the distinguishability of the training and testing loss distributions and the model's vulnerability to MIAs. Motivated by existing results, we propose a novel training framework based on a relaxed loss with a more achievable learning target, which leads to narrowed generalization gap and reduced privacy leakage. RelaxLoss is applicable to any classification model with added benefits of easy implementation an…
The decentralized nature of federated learning makes detecting and defending against adversarial attacks a challenging task. This paper focuses on backdoor attacks in the federated learning setting, where the goal of the adversary is to reduce the performance of the model on targeted tasks while maintaining good performance on the main task. Unlike existing works, we allow non-malicious clients to have correctly labeled samples from the targeted tasks. We conduct a comprehensive study of backdoor attacks and defenses for the EMNIST dataset, a real-life, user-partitioned, and non-iid dataset. W…
Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；South China University of Technology（华南理工大学）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Perceptual hashes map images with identical semantic content to the same $n$-bit hash value, while mapping semantically-different images to different hashes. These algorithms carry important applications in cybersecurity such as copyright infringement detection, content fingerprinting, and surveillance. Apple's NeuralHash is one such system that aims to detect the presence of illegal content on users' devices without compromising consumer privacy. We make the surprising discovery that NeuralHash is approximately linear, which inspires the development of novel black-box attacks that can (i) eva…
In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data. Existing MIA defenses conceal the presence of a target sample through strong regularization, knowledge distillation, confidence masking, or differential privacy. We propose MIAShield, a new MIA defense based on preemptive exclusion of member samples instead of masking the presence of a member. The key insight in MIAShield is weakening the strong membership signal that stems from the presence of a target sample by preemptively excluding it …
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference attack, an attacker has access to some data (called public data) of an individual, a software, or a system; and the attacker uses an ML classifier to automatically infer their private data. Inference attacks pose severe privacy and security threats to individuals and systems. Inference attacks are successful because private data are statistically correlated with public data, and …
A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning
School of Cyberspace Science and Technology, Beijing Institute of Technology（信息空间科学与技术学院，北京理工大学）；School of Information Engineering, Minzu University of China（信息工程学院，民族大学）；Australian Institute of Machine Learning, The University of Adelaide（澳大利亚机器学习研究所，阿德莱德大学）
Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial attacks due to decentralized and unvetted data. One important line of attacks against FL is the backdoor attacks. In a backdoor attack, an adversary tries to embed a backdoor functionality to the model during training that can later be activated to cause a desired misclassification. To prevent backdoor attacks, we propose a lightweight defense that requires…
To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
School of Computing；Augmented Intelligence, Arizona State University, Tempe, AZ, USA；Department of Computer Science；Engineering, Texas A\&M University, College Station, TX, USA
Substantial improvements have been achieved in recent years in voice conversion, which converts the speaker characteristics of an utterance into those of another speaker without changing the linguistic content of the utterance. Nonetheless, the improved conversion technologies also led to concerns about privacy and authentication. It thus becomes highly desired to be able to prevent one's voice from being improperly utilized with such voice conversion technologies. This is why we report in this paper the first known attempt to perform adversarial attack on voice conversion. We introduce human …
Technical University of Munich (TUM)（慕尼黑工业大学）；TUM University Hospital（慕尼黑工业大学医院）；Imperial College London（帝国理工学院）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
University of Science and Technology of China（中国科学技术大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Nanjing University（南京大学）
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS)（深圳市人工智能与机器人研究院）
Federated learning (FL) is a promising privacy-preserving distributed machine learning methodology that allows multiple clients (i.e., workers) to collaboratively train statistical models without disclosing private training data. Due to the characteristics of data remaining localized and the uninspected on-device training process, there may exist Byzantine workers launching data poisoning and model poisoning attacks, which would seriously deteriorate model performance or prevent the model from convergence. Most of the existing Byzantine-robust FL schemes are either ineffective against several …
