Federated learning (FL) is inherently susceptible to privacy breaches and poisoning attacks. To tackle these challenges, researchers have separately devised secure aggregation mechanisms to protect data privacy and robust aggregation methods that withstand poisoning attacks. However, simultaneously addressing both concerns is challenging; secure aggregation facilitates poisoning attacks as most anomaly detection techniques require access to unencrypted local model updates, which are obscured by secure aggregation. Few recent efforts to simultaneously tackle both challenges offen depend on impractical assumption of non-colluding two-server setups that disrupt FL's topology, or three-party computation which introduces scalability issues, complicating deployment and application. To overcome this dilemma, this paper introduce a Dual Defense Federated learning (DDFed) framework. DDFed simultaneously boosts privacy protection and mitigates poisoning attacks, without introducing new participant roles or disrupting the existing FL topology. DDFed initially leverages cutting-edge fully homomorphic encryption (FHE) to securely aggregate model updates, without the impractical requirement for non-colluding two-server setups and ensures strong privacy protection. Additionally, we proposes a unique two-phase anomaly detection mechanism for encrypted model updates, featuring secure similarity computation and feedback-driven collaborative selection, with additional measures to prevent potential privacy breaches from Byzantine clients incorporated into the detection process. We conducted extensive experiments on various model poisoning attacks and FL scenarios, including both cross-device and cross-silo FL. Experiments on publicly available datasets demonstrate that DDFed successfully protects model privacy and effectively defends against model poisoning threats.
Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and model poisoning attacks (MPAs) that degrade global model performance. While numerous proposed defenses claim substantial effectiveness, their evaluation is typically done in isolation with limited attack strategies, raising concerns about their validity. Additionally, existing studies overlook the mutual effectiveness of defenses against both DPAs and MPAs, causing fragmentation in this field. This paper aims to provide a unified benchmark and analysis of defenses against DPAs and MPAs, clarifying the distinction between these two similar but slightly distinct domains. We present a systematic taxonomy of poisoning attacks and defense strategies, outlining their design, strengths, and limitations. Then, a unified comparative evaluation across FL algorithms and data heterogeneity is conducted to validate their individual and mutual effectiveness and derive key insights for design principles and future research. Along with the analysis, we frame our work to a unified benchmark, FLPoison, with high modularity and scalability to evaluate 15 representative poisoning attacks and 17 defense strategies, facilitating future research in this domain. Code is available at https://github.com/vio1etus/FLPoison.
One of the most common defense strategies against Byzantine clients in federated learning (FL) is to employ a robust aggregator mechanism that makes the training more resilient. While many existing Byzantine robust aggregators provide theoretical convergence guarantees and are empirically effective against certain categories of attacks, we observe that certain high-strength attacks can subvert the robust aggregator and collapse the training. To overcome this limitation, we propose a method called FedSECA for robust Sign Election and Coordinate-wise Aggregation of gradients in FL that is less susceptible to malicious updates by an omniscient attacker. The proposed method has two main components. The Concordance Ratio Induced Sign Election(CRISE) module determines the consensus direction (elected sign) for each individual parameter gradient through a weighted voting strategy. The client weights are assigned based on a novel metric called concordance ratio, which quantifies the degree of sign agreement between the client gradient updates. Based on the elected sign, a Robust Coordinate-wise Aggregation(RoCA) strategy is employed, where variance-reduced sparse gradients are aggregated only if they are in alignment with the corresponding elected sign. We compare our proposed FedSECA method against 10 robust aggregators under 7 Byzantine attacks on 3 datasets and architectures. The results show that existing robust aggregators fail for at least some attacks, while FedSECA exhibits better robustness. Code - https://github.com/JosephGeoBenjamin/FedSECA-ByzantineTolerance
Federated Learning (FL) is a technique that allows multiple parties to train a shared model collaboratively without disclosing their private data. It has become increasingly popular due to its distinct privacy advantages. However, FL models can suffer from biases against certain demographic groups (e.g., racial and gender groups) due to the heterogeneity of data and party selection. Researchers have proposed various strategies for characterizing the group fairness of FL algorithms to address this issue. However, the effectiveness of these strategies in the face of deliberate adversarial attacks has not been fully explored. Although existing studies have revealed various threats (e.g., model poisoning attacks) against FL systems caused by malicious participants, their primary aim is to decrease model accuracy, while the potential of leveraging poisonous model updates to exacerbate model unfairness remains unexplored. In this paper, we propose a new type of model poisoning attack, EAB-FL, with a focus on exacerbating group unfairness while maintaining a good level of model utility. Extensive experiments on three datasets demonstrate the effectiveness and efficiency of our attack, even with state-of-the-art fairness optimization algorithms and secure aggregation rules employed.
Federated learning is highly susceptible to model poisoning attacks, especially those meticulously crafted for servers. Traditional defense methods mainly focus on updating assessments or robust aggregation against manually crafted myopic attacks. When facing advanced attacks, their defense stability is notably insufficient. Therefore, it is imperative to develop adaptive defenses against such advanced poisoning attacks. We find that benign clients exhibit significantly higher data distribution stability than malicious clients in federated learning in both CV and NLP tasks. Therefore, the malicious clients can be recognized by observing the stability of their data distribution. In this paper, we propose AdaAggRL, an RL-based Adaptive Aggregation method, to defend against sophisticated poisoning attacks. Specifically, we first utilize distribution learning to simulate the clients' data distributions. Then, we use the maximum mean discrepancy (MMD) to calculate the pairwise similarity of the current local model data distribution, its historical data distribution, and global model data distribution. Finally, we use policy learning to adaptively determine the aggregation weights based on the above similarities. Experiments on four real-world datasets demonstrate that the proposed defense model significantly outperforms widely adopted defense models for sophisticated attacks.
Recent attacks on federated learning (FL) can introduce malicious model updates that circumvent widely adopted Euclidean distance-based detection methods. This paper proposes a novel defense strategy, referred to as LayerCAM-AE, designed to counteract model poisoning in federated learning. The LayerCAM-AE puts forth a new Layer Class Activation Mapping (LayerCAM) integrated with an autoencoder (AE), significantly enhancing detection capabilities. Specifically, LayerCAM-AE generates a heat map for each local model update, which is then transformed into a more compact visual format. The autoencoder is designed to process the LayerCAM heat maps from the local model updates, improving their distinctiveness and thereby increasing the accuracy in spotting anomalous maps and malicious local models. To address the risk of misclassifications with LayerCAM-AE, a voting algorithm is developed, where a local model update is flagged as malicious if its heat maps are consistently suspicious over several rounds of communication. Extensive tests of LayerCAM-AE on the SVHN and CIFAR-100 datasets are performed under both Independent and Identically Distributed (IID) and non-IID settings in comparison with existing ResNet-50 and REGNETY-800MF defense models. Experimental results show that LayerCAM-AE increases detection rates (Recall: 1.0, Precision: 1.0, FPR: 0.0, Accuracy: 1.0, F1 score: 1.0, AUC: 1.0) and test accuracy in FL, surpassing the performance of both the ResNet-50 and REGNETY-800MF. Our code is available at: https://github.com/jjzgeeks/LayerCAM-AE
This paper puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder (VGAE) to create malicious local models based solely on the benign local models overheard without any access to the training data of FL. Such an advancement leads to the VGAE-MP attack that is not only efficacious but also remains elusive to detection. VGAE-MP attack extracts graph structural correlations among the benign local models and the training data features, adversarially regenerates the graph structure, and generates malicious local models using the adversarial graph structure and benign models' features. Moreover, a new attacking algorithm is presented to train the malicious local models using VGAE and sub-gradient descent, while enabling an optimal selection of the benign local models for training the VGAE. Experiments demonstrate a gradual drop in FL accuracy under the proposed VGAE-MP attack and the ineffectiveness of existing defense mechanisms in detecting the attack, posing a severe threat to FL.
Federated learning enables learning from decentralized data sources without compromising privacy, which makes it a crucial technique. However, it is vulnerable to model poisoning attacks, where malicious clients interfere with the training process. Previous defense mechanisms have focused on the server-side by using careful model aggregation, but this may not be effective when the data is not identically distributed or when attackers can access the information of benign clients. In this paper, we propose a new defense mechanism that focuses on the client-side, called FedDefender, to help benign clients train robust local models and avoid the adverse impact of malicious model updates from attackers, even when a server-side defense cannot identify or remove adversaries. Our method consists of two main components: (1) attack-tolerant local meta update and (2) attack-tolerant global knowledge distillation. These components are used to find noise-resilient model parameters while accurately extracting knowledge from a potentially corrupted global model. Our client-side defense strategy has a flexible structure and can work in conjunction with any existing server-side strategies. Evaluations of real-world scenarios across multiple datasets show that the proposed method enhances the robustness of federated learning against model poisoning attacks.
In a federated learning (FL) system, distributed clients upload their local models to a central server to aggregate into a global model. Malicious clients may plant backdoors into the global model through uploading poisoned local models, causing images with specific patterns to be misclassified into some target labels. Backdoors planted by current attacks are not durable, and vanish quickly once the attackers stop model poisoning. In this paper, we investigate the connection between the durability of FL backdoors and the relationships between benign images and poisoned images (i.e., the images whose labels are flipped to the target label during local training). Specifically, benign images with the original and the target labels of the poisoned images are found to have key effects on backdoor durability. Consequently, we propose a novel attack, Chameleon, which utilizes contrastive learning to further amplify such effects towards a more durable backdoor. Extensive experiments demonstrate that Chameleon significantly extends the backdoor lifespan over baselines by $1.2\times \sim 4\times$, for a wide range of image datasets, backdoor types, and model architectures.
Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine learning (ML) architectures. In this work, we introduce the notion of model poisoning reachability as a technical tool to explore the intrinsic limits of data poisoning attacks towards target parameters (i.e., model-targeted attacks). We derive an easily computable threshold to establish and quantify a surprising phase transition phenomenon among popular ML models: data poisoning attacks can achieve certain target parameters only when the poisoning ratio exceeds our threshold. Building on existing parameter corruption attacks and refining the Gradient Canceling attack, we perform extensive experiments to confirm our theoretical findings, test the predictability of our transition threshold, and significantly improve existing indiscriminate data poisoning baselines over a range of datasets and models. Our work highlights the critical role played by the poisoning ratio, and sheds new insights on existing empirical results, attacks and mitigation strategies in data poisoning.
Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is limited because their updates are quickly drowned out by those of many other users. Existing attacks do not account for future behaviors of other users, and thus require many sequential updates and their effects are quickly erased. We propose an attack that anticipates and accounts for the entire federated learning pipeline, including behaviors of other clients, and ensures that backdoors are effective quickly and persist even after multiple rounds of community updates. We show that this new attack is effective in realistic scenarios where the attacker only contributes to a small fraction of randomly sampled rounds and demonstrate this attack on image classification, next-word prediction, and sentiment analysis.
Federated learning (FL) is vulnerable to model poisoning attacks, in which malicious clients corrupt the global model via sending manipulated model updates to the server. Existing defenses mainly rely on Byzantine-robust FL methods, which aim to learn an accurate global model even if some clients are malicious. However, they can only resist a small number of malicious clients in practice. It is still an open challenge how to defend against model poisoning attacks with a large number of malicious clients. Our FLDetector addresses this challenge via detecting malicious clients. FLDetector aims to detect and remove the majority of the malicious clients such that a Byzantine-robust FL method can learn an accurate global model using the remaining clients. Our key observation is that, in model poisoning attacks, the model updates from a client in multiple iterations are inconsistent. Therefore, FLDetector detects malicious clients via checking their model-updates consistency. Roughly speaking, the server predicts a client's model update in each iteration based on its historical model updates using the Cauchy mean value theorem and L-BFGS, and flags a client as malicious if the received model update from the client and the predicted model update are inconsistent in multiple iterations. Our extensive experiments on three benchmark datasets show that FLDetector can accurately detect malicious clients in multiple state-of-the-art model poisoning attacks. After removing the detected malicious clients, existing Byzantine-robust FL methods can learn accurate global models.Our code is available at https://github.com/zaixizhang/FLDetector.
Federated Recommendation (FR) has received considerable popularity and attention in the past few years. In FR, for each user, its feature vector and interaction data are kept locally on its own client thus are private to others. Without the access to above information, most existing poisoning attacks against recommender systems or federated learning lose validity. Benifiting from this characteristic, FR is commonly considered fairly secured. However, we argue that there is still possible and necessary security improvement could be made in FR. To prove our opinion, in this paper we present FedRecAttack, a model poisoning attack to FR aiming to raise the exposure ratio of target items. In most recommendation scenarios, apart from private user-item interactions (e.g., clicks, watches and purchases), some interactions are public (e.g., likes, follows and comments). Motivated by this point, in FedRecAttack we make use of the public interactions to approximate users' feature vectors, thereby attacker can generate poisoned gradients accordingly and control malicious users to upload the poisoned gradients in a well-designed way. To evaluate the effectiveness and side effects of FedRecAttack, we conduct extensive experiments on three real-world datasets of different sizes from two completely different scenarios. Experimental results demonstrate that our proposed FedRecAttack achieves the state-of-the-art effectiveness while its side effects are negligible. Moreover, even with small proportion (3%) of malicious users and small proportion (1%) of public interactions, FedRecAttack remains highly effective, which reveals that FR is more vulnerable to attack than people commonly considered.
Model poisoning attacks on federated learning (FL) intrude in the entire system via compromising an edge model, resulting in malfunctioning of machine learning models. Such compromised models are tampered with to perform adversary-desired behaviors. In particular, we considered a semi-targeted situation where the source class is predetermined however the target class is not. The goal is to cause the global classifier to misclassify data of the source class. Though approaches such as label flipping have been adopted to inject poisoned parameters into FL, it has been shown that their performances are usually class-sensitive varying with different target classes applied. Typically, an attack can become less effective when shifting to a different target class. To overcome this challenge, we propose the Attacking Distance-aware Attack (ADA) to enhance a poisoning attack by finding the optimized target class in the feature space. Moreover, we studied a more challenging situation where an adversary had limited prior knowledge about a client's data. To tackle this problem, ADA deduces pair-wise distances between different classes in the latent feature space from shared model parameters based on the backward error analysis. We performed extensive empirical evaluations on ADA by varying the factor of attacking frequency in three different image classification tasks. As a result, ADA succeeded in increasing the attack performance by 1.8 times in the most challenging case with an attacking frequency of 0.01.
Federated Learning (FL) enables multiple parties to distributively train a ML model without revealing their private datasets. However, it assumes trust in the centralized aggregator which stores and aggregates model updates. This makes it prone to gradient tampering and privacy leakage by a malicious aggregator. Malicious parties can also introduce backdoors into the joint model by poisoning the training data or model gradients. To address these issues, we present BEAS, the first blockchain-based framework for N-party FL that provides strict privacy guarantees of training data using gradient pruning (showing improved differential privacy compared to existing noise and clipping based techniques). Anomaly detection protocols are used to minimize the risk of data-poisoning attacks, along with gradient pruning that is further used to limit the efficacy of model-poisoning attacks. We also define a novel protocol to prevent premature convergence in heterogeneous learning environments. We perform extensive experiments on multiple datasets with promising results: BEAS successfully prevents privacy leakage from dataset reconstruction attacks, and minimizes the efficacy of poisoning attacks. Moreover, it achieves an accuracy similar to centralized frameworks, and its communication and computation overheads scale linearly with the number of participants.
Federated learning (FL) is a distributed learning paradigm that preserves users' data privacy while leveraging the entire dataset of all participants. In FL, multiple models are trained independently on the clients and aggregated centrally to update a global model in an iterative process. Although this approach is excellent at preserving privacy, FL still suffers from quality issues such as attacks or byzantine faults. Recent attempts have been made to address such quality challenges on the robust aggregation techniques for FL. However, the effectiveness of state-of-the-art (SOTA) robust FL techniques is still unclear and lacks a comprehensive study. Therefore, to better understand the current quality status and challenges of these SOTA FL techniques in the presence of attacks and faults, we perform a large-scale empirical study to investigate the SOTA FL's quality from multiple angles of attacks, simulated faults (via mutation operators), and aggregation (defense) methods. In particular, we study FL's performance on the image classification tasks and use DNNs as our model type. Furthermore, we perform our study on two generic image datasets and one real-world federated medical image dataset. We also investigate the effect of the proportion of affected clients and the dataset distribution factors on the robustness of FL. After a large-scale analysis with 496 configurations, we find that most mutators on each user have a negligible effect on the final model in the generic datasets, and only one of them is effective in the medical dataset. Furthermore, we show that model poisoning attacks are more effective than data poisoning attacks. Moreover, choosing the most robust FL aggregator depends on the attacks and datasets. Finally, we illustrate that a simple ensemble of aggregators achieves a more robust solution than any single aggregator and is the best choice in 75% of the cases.
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on targeted sub-tasks (e.g. classifying planes as birds) by uploading "poisoned" updates. In this report we introduce \algoname{}, a novel defense that uses global top-k update sparsification and device-level gradient clipping to mitigate model poisoning attacks. We propose a theoretical framework for analyzing the robustness of defenses against poisoning attacks, and provide robustness and convergence analysis of our algorithm. To validate its empirical efficacy we conduct an open-source evaluation at scale across multiple benchmark datasets for computer vision and federated learning.
In federated learning, each participant trains its local model with its own data and a global model is formed at a trusted server by aggregating model updates coming from these participants. Since the server has no effect and visibility on the training procedure of the participants to ensure privacy, the global model becomes vulnerable to attacks such as data poisoning and model poisoning. Although many defense algorithms have recently been proposed to address these attacks, they often make strong assumptions that do not agree with the nature of federated learning, such as assuming Non-IID datasets. Moreover, they mostly lack comprehensive experimental analyses. In this work, we propose a defense algorithm called ARFED that does not make any assumptions about data distribution, update similarity of participants, or the ratio of the malicious participants. ARFED mainly considers the outlier status of participant updates for each layer of the model architecture based on the distance to the global model. Hence, the participants that do not have any outlier layer are involved in model aggregation. We have performed extensive experiments on diverse scenarios and shown that the proposed approach provides a robust defense against different attacks. To test the defense capability of the ARFED in different conditions, we considered label flipping, Byzantine, and partial knowledge attacks for both IID and Non-IID settings in our experimental evaluations. Moreover, we proposed a new attack, called organized partial knowledge attack, where malicious participants use their training statistics collaboratively to define a common poisoned model. We have shown that organized partial knowledge attacks are more effective than independent attacks.
Federated learning (FL) is a popular distributed learning framework that trains a global model through iterative communications between a central server and edge devices. Recent works have demonstrated that FL is vulnerable to model poisoning attacks. Several server-based defense approaches (e.g. robust aggregation), have been proposed to mitigate such attacks. However, we empirically show that under extremely strong attacks, these defensive methods fail to guarantee the robustness of FL. More importantly, we observe that as long as the global model is polluted, the impact of attacks on the global model will remain in subsequent rounds even if there are no subsequent attacks. In this work, we propose a client-based defense, named White Blood Cell for Federated Learning (FL-WBC), which can mitigate model poisoning attacks that have already polluted the global model. The key idea of FL-WBC is to identify the parameter space where long-lasting attack effect on parameters resides and perturb that space during local training. Furthermore, we derive a certified robustness guarantee against model poisoning attacks and a convergence guarantee to FedAvg after applying our FL-WBC. We conduct experiments on FasionMNIST and CIFAR10 to evaluate the defense against state-of-the-art model poisoning attacks. The results demonstrate that our method can effectively mitigate model poisoning attack impact on the global model within 5 communication rounds with nearly no accuracy drop under both IID and Non-IID settings. Our defense is also complementary to existing server-based robust aggregation approaches and can further improve the robustness of FL under extremely strong attacks.
Neural Architecture Search (NAS) represents an emerging machine learning (ML) paradigm that automatically searches for models tailored to given tasks, which greatly simplifies the development of ML systems and propels the trend of ML democratization. Yet, little is known about the potential security risks incurred by NAS, which is concerning given the increasing use of NAS-generated models in critical domains. This work represents a solid initial step towards bridging the gap. Through an extensive empirical study of 10 popular NAS methods, we show that compared with their manually designed counterparts, NAS-generated models tend to suffer greater vulnerability to various malicious attacks (e.g., adversarial evasion, model poisoning, and functionality stealing). Further, with both empirical and analytical evidence, we provide possible explanations for such phenomena: given the prohibitive search space and training cost, most NAS methods favor models that converge fast at early training stages; this preference results in architectural properties associated with attack vulnerability (e.g., high loss smoothness and low gradient variance). Our findings not only reveal the relationships between model characteristics and attack vulnerability but also suggest the inherent connections underlying different attacks. Finally, we discuss potential remedies to mitigate such drawbacks, including increasing cell depth and suppressing skip connects, which lead to several promising research directions.