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 learning to perturb data representation such that the quality of the reconstructed data is severely degraded, while FL performance is maintained. In addition, we derive certified robustness guarantee to FL and convergence guarantee to FedAvg, after applying our defense. To evaluate our defense, we conduct experiments on MNIST and CIFAR10 for defending against the DLG attack and GS attack. Without sacrificing accuracy, the results demonstrate that our proposed defense can increase the mean squared error between the reconstructed data and the raw data by as much as more than 160X for both DLG attack and GS attack, compared with baseline defense methods. The privacy of the FL system is significantly improved.
Federated Learning (FL) is a distributed learning paradigm that enables different parties to train a model together for high quality and strong privacy protection. In this scenario, individual participants may get compromised and perform backdoor attacks by poisoning the data (or gradients). Existing work on robust aggregation and certified FL robustness does not study how hardening benign clients can affect the global model (and the malicious clients). In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting. Moreo…
Michigan State University（密歇根州立大学）；The Hong Kong Polytechnic University（香港理工大学）
Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the existence of attackers who deliberately conduct gradient leakage attacks to reconstruct the client data. Recently, popular strategies such as gradient perturbation methods and input encryption methods have been proposed to defend against gradient leakage attacks. Nevertheless, these defenses can either greatly sacrifice the model performance, or be evaded by more …
Rensselaer Polytechnic Institute（伦斯勒理工学院）；IBM Research（IBM研究院）；National Yang Ming Chiao Tung University（国立阳明交通大学）
Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate data recovery is often viewed as a promising defense strategy against data leakage. In this paper, we revisit this defense premise and propose an advanced data leakage attack with theoretical justification to efficiently recover batch data from the shared aggregated gradients. We name our proposed method as catastrophic data leakage in vertical federated learning (CAFE). Compar…
Federated learning is an established method for training machine learning models without sharing training data. However, recent work has shown that it cannot guarantee data privacy as shared gradients can still leak sensitive information. To formalize the problem of gradient leakage, we propose a theoretical framework that enables, for the first time, analysis of the Bayes optimal adversary phrased as an optimization problem. We demonstrate that existing leakage attacks can be seen as approximations of this optimal adversary with different assumptions on the probability distributions of the in…
Imperial College London（帝国理工学院）；University of Warwick（华威大学）
In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information from the shared network's gradients compromising clients' privacy. In this paper, to quantify the private information leakage from gradients we adopt usable information theory. We focus on two types of private information: original information in data reconstruction attacks and latent information in attribute inference attacks. Furthermore, a sensitivity ana…
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）
Eliminating Label Leakage in Tree-Based Vertical Federated Learning
The University of Tokyo（东京大学）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Gradient inversion attacks on federated learning systems reconstruct client training data from exchanged gradient information. To defend against such attacks, a variety of defense mechanisms were proposed. However, they usually lead to an unacceptable trade-off between privacy and model utility. Recent observations suggest that dropout could mitigate gradient leakage and improve model utility if added to neural networks. Unfortunately, this phenomenon has not been systematically researched yet. In this work, we thoroughly analyze the effect of dropout on iterative gradient inversion attacks. W…
Tsinghua-Berkeley Shenzhen Institute, Tsinghua University（清华大学清华-伯克利深圳学院）
Distributed machine learning has been widely used in recent years to tackle the large and complex dataset problem. Therewith, the security of distributed learning has also drawn increasing attentions from both academia and industry. In this context, federated learning (FL) was developed as a "secure" distributed learning by maintaining private training data locally and only public model gradients are communicated between. However, to date, a variety of gradient leakage attacks have been proposed for this procedure and prove that it is insecure. For instance, a common drawback of these attacks …
Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）
Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to raw training data, and (b) a new phenomenon we identify called backdoor leakage causes models trained continuously to eventually suffer from backdoors due to cumulative errors in defense mechanisms. We propose shadow learning, a framework for defending against backdoor attacks in the FL setting under long-range training. Shadow learning trains two models in…
We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact allows hidden triggers. During deployment, the adversary can modify observed states in a particular way to trigger unexpected actions and harm the agent. We assume the agent does not have the resources to re-train a good policy. Instead, our defense mechanism sanitizes the backdoor policy by projecting observed states to a 'safe subspace', estimated from a …
Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Aalborg University（奥尔堡大学）；University of Twente（特温特大学）；Netherlands Defence Academy（荷兰国防学院）；Delft University of Technology（代尔夫特理工大学）
Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the clients' private data. This paper evaluates existing attacks and defenses. We find that some attacks make strong assumptions about the setup. Relaxing such assumptions can substantially weaken these attacks. We then evaluate the benefits of three proposed defense mechanisms against gradient inversion attacks. We show the trade-offs of privacy leakage and data …
We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100. Our approach is based on differentiable abstract interpretation and introduces two novel concepts: (i) abstract layers for fine-tuning the precision and scalability of the abstraction, (ii) a flexible domain specific language (DSL) for describing training objectives that combine abstract and concrete losses with arbitrary specifications. Our training method is implemented in the DiffAI system.
Adversarial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. A provable defense provides a certificate for each test sample, which is a lower bound on the magnitude of any adversarial distortion of the training set that can corrupt the test sample's classification. We propose two novel provable defenses against poisoning attacks: (i) Deep Partition Aggregation (DPA), a certified defense against a general poisoning threat model, defined as the insertion or deletion of a bounded number of samples to the training set -- by implication, this threa…
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；JZTData Technology（JZTData科技公司 (JZTData Technology)）
With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical applications. On the one hand, although most cryptographic methods are provable secure, they bring heavy computation and communication. On the other hand, the security of many relatively efficient private methods (e.g., federated learning and split learning) is being questioned, since they are non-provable secure. Inspired by previous work on privacy-preserving machine learning, …
Federated learning enables multiple users to build a joint model by sharing their model updates (gradients), while their raw data remains local on their devices. In contrast to the common belief that this provides privacy benefits, we here add to the very recent results on privacy risks when sharing gradients. Specifically, we investigate Label Leakage from Gradients (LLG), a novel attack to extract the labels of the users' training data from their shared gradients. The attack exploits the direction and magnitude of gradients to determine the presence or absence of any label. LLG is simple yet…
Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China（虚拟现实技术与系统国家重点实验室，计算机科学与工程学院，北京航空航天大学）；Hangzhou Innovation Institute of Beihang University, Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems, Hangzhou, China（北京航空航天大学杭州创新研究院，浙江省工业大数据与机器人智能系统重点实验室）；Center for AI Business Innovation, Department of Management Science and Systems, University at Buffalo, Buffalo, New York, USA（人工智能商业创新中心，管理科学与系统系，布法罗大学）；University of North Texas, Denton, Texas, USA（德克萨斯大学达文波特分校）；Zhongguancun Laboratory, Beijing, China（中关村实验室）
We present a method for provably defending any pretrained image classifier against $\ell_p$ adversarial attacks. This method, for instance, allows public vision API providers and users to seamlessly convert pretrained non-robust classification services into provably robust ones. By prepending a custom-trained denoiser to any off-the-shelf image classifier and using randomized smoothing, we effectively create a new classifier that is guaranteed to be $\ell_p$-robust to adversarial examples, without modifying the pretrained classifier. Our approach applies to both the white-box and the black-box…
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 …
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks. In this paper, in an effort to scale these approaches to substantially larger models, we extend previous work in three main directions. First, we present a technique for extending these training procedures to much more general networks, with skip connections (such as ResNets) and general nonlinearities; the approach is fully modular, and can be implemented automati…
As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden backdoors. The so-called backdoor attacks are especially difficult to detect since the model behaves normally on standard test data but gives wrong outputs when triggered by certain backdoor keys. Although Byzantine-tolerant training algorithms provide convergence guarantee, provable defense against backdoor attacks remains largely unsolved. Methods based on random…
AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing
Xidian University（西安电子科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Hong Kong Chu Hai College（香港 Chu Hai 学院）；National University of Defense Technology（国防科技大学）；Shanghai JiaoTong University（上海交通大学）；Hubei University（湖北大学）
We propose a method to learn deep ReLU-based classifiers that are provably robust against norm-bounded adversarial perturbations on the training data. For previously unseen examples, the approach is guaranteed to detect all adversarial examples, though it may flag some non-adversarial examples as well. The basic idea is to consider a convex outer approximation of the set of activations reachable through a norm-bounded perturbation, and we develop a robust optimization procedure that minimizes the worst case loss over this outer region (via a linear program). Crucially, we show that the dual pr…
Princeton University（普林斯顿大学）；University of Chicago（芝加哥大学）
Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial patch to the object to be misclassified, and defending against such attacks is an unsolved/open problem. In this paper, we propose a general defense framework called PatchGuard that can achieve high provable robustness while maintaining high clean accuracy against localized adversarial patches. The cornerstone of PatchGuard involves the use of CNNs with sma…
A robustness certificate is the minimum distance of a given input to the decision boundary of the classifier (or its lower bound). For {\it any} input perturbations with a magnitude smaller than the certificate value, the classification output will provably remain unchanged. Exactly computing the robustness certificates for neural networks is difficult since it requires solving a non-convex optimization. In this paper, we provide computationally-efficient robustness certificates for neural networks with differentiable activation functions in two steps. First, we show that if the eigenvalues of…
In recent years, researchers have extensively studied adversarial robustness in a variety of threat models, including L_0, L_1, L_2, and L_infinity-norm bounded adversarial attacks. However, attacks bounded by fractional L_p "norms" (quasi-norms defined by the L_p distance with 0<p<1) have yet to be thoroughly considered. We proactively propose a defense with several desirable properties: it provides provable (certified) robustness, scales to ImageNet, and yields deterministic (rather than high-probability) certified guarantees when applied to quantized data (e.g., images). Our technique for f…
Significant work is being done to develop the math and tools necessary to build provable defenses, or at least bounds, against adversarial attacks of neural networks. In this work, we argue that tools from control theory could be leveraged to aid in defending against such attacks. We do this by example, building a provable defense against a weaker adversary. This is done so we can focus on the mechanisms of control theory, and illuminate its intrinsic value.
We study defense strategies against reward poisoning attacks in reinforcement learning. As a threat model, we consider attacks that minimally alter rewards to make the attacker's target policy uniquely optimal under the poisoned rewards, with the optimality gap specified by an attack parameter. Our goal is to design agents that are robust against such attacks in terms of the worst-case utility w.r.t. the true, unpoisoned, rewards while computing their policies under the poisoned rewards. We propose an optimization framework for deriving optimal defense policies, both when the attack parameter …
In recent years several adversarial attacks and defenses have been proposed. Often seemingly robust models turn out to be non-robust when more sophisticated attacks are used. One way out of this dilemma are provable robustness guarantees. While provably robust models for specific $l_p$-perturbation models have been developed, we show that they do not come with any guarantee against other $l_q$-perturbations. We propose a new regularization scheme, MMR-Universal, for ReLU networks which enforces robustness wrt $l_1$- and $l_\infty$-perturbations and show how that leads to the first provably rob…
FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data
University of California, San Francisco（加州大学旧金山分校）；Lehigh University（利哈伊大学）；New Jersey Institute of Technology（新泽西理工学院）；University of Louisiana at Lafayette（路易斯安那大学拉法叶分校）
