PyTorchKR Papers

최신 논문

총 109편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2112.06274공식 코드 · Papers with Code

SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification

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.

arXiv:2112.01405

FedRAD: Federated Robust Adaptive Distillation

The robustness of federated learning (FL) is vital for the distributed training of an accurate global model that is shared among large number of clients. The collaborative learning framework by typically aggregating model updates is vulnerable to model poisoning attacks from adversarial clients. Since the shared information between the global server and participants are only limited to model parameters, it is challenging to detect bad model updates. Moreover, real-world datasets are usually heterogeneous and not independent and identically distributed (Non-IID) among participants, which makes the design of such robust FL pipeline more difficult. In this work, we propose a novel robust aggregation method, Federated Robust Adaptive Distillation (FedRAD), to detect adversaries and robustly aggregate local models based on properties of the median statistic, and then performing an adapted version of ensemble Knowledge Distillation. We run extensive experiments to evaluate the proposed method against recently published works. The results show that FedRAD outperforms all other aggregators in the presence of adversaries, as well as in heterogeneous data distributions.

arXiv:2111.04550공식 코드 · Papers with Code

ARFED: Attack-Resistant Federated averaging based on outlier elimination

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.

arXiv:2110.13864공식 코드 · Papers with Code

FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective

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.

arXiv:2110.11578

PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy

Federated Learning (FL) allows multiple participating clients to train machine learning models collaboratively by keeping their datasets local and only exchanging model updates. Existing FL protocol designs have been shown to be vulnerable to attacks that aim to compromise data privacy and/or model robustness. Recently proposed defenses focused on ensuring either privacy or robustness, but not both. In this paper, we develop a framework called PRECAD, which simultaneously achieves differential privacy (DP) and enhances robustness against model poisoning attacks with the help of cryptography. Using secure multi-party computation (MPC) techniques (e.g., secret sharing), noise is added to the model updates by the honest-but-curious server(s) (instead of each client) without revealing clients' inputs, which achieves the benefit of centralized DP in terms of providing a better privacy-utility tradeoff than local DP based solutions. Meanwhile, a crypto-aided secure validation protocol is designed to verify that the contribution of model update from each client is bounded without leaking privacy. We show analytically that the noise added to ensure DP also provides enhanced robustness against malicious model submissions. We experimentally demonstrate that our PRECAD framework achieves higher privacy-utility tradeoff and enhances robustness for the trained models.

arXiv:2110.10926

PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion

Due to the growing privacy concerns, decentralization emerges rapidly in personalized services, especially recommendation. Also, recent studies have shown that centralized models are vulnerable to poisoning attacks, compromising their integrity. In the context of recommender systems, a typical goal of such poisoning attacks is to promote the adversary's target items by interfering with the training dataset and/or process. Hence, a common practice is to subsume recommender systems under the decentralized federated learning paradigm, which enables all user devices to collaboratively learn a global recommender while retaining all the sensitive data locally. Without exposing the full knowledge of the recommender and entire dataset to end-users, such federated recommendation is widely regarded `safe' towards poisoning attacks. In this paper, we present a systematic approach to backdooring federated recommender systems for targeted item promotion. The core tactic is to take advantage of the inherent popularity bias that commonly exists in data-driven recommenders. As popular items are more likely to appear in the recommendation list, our innovatively designed attack model enables the target item to have the characteristics of popular items in the embedding space. Then, by uploading carefully crafted gradients via a small number of malicious users during the model update, we can effectively increase the exposure rate of a target (unpopular) item in the resulted federated recommender. Evaluations on two real-world datasets show that 1) our attack model significantly boosts the exposure rate of the target item in a stealthy way, without harming the accuracy of the poisoned recommender; and 2) existing defenses are not effective enough, highlighting the need for new defenses against our local model poisoning attacks to federated recommender systems.

arXiv:2110.10108

TESSERACT: Gradient Flip Score to Secure Federated Learning Against Model Poisoning Attacks

Federated learning---multi-party, distributed learning in a decentralized environment---is vulnerable to model poisoning attacks, even more so than centralized learning approaches. This is because malicious clients can collude and send in carefully tailored model updates to make the global model inaccurate. This motivated the development of Byzantine-resilient federated learning algorithms, such as Krum, Bulyan, FABA, and FoolsGold. However, a recently developed untargeted model poisoning attack showed that all prior defenses can be bypassed. The attack uses the intuition that simply by changing the sign of the gradient updates that the optimizer is computing, for a set of malicious clients, a model can be diverted from the optima to increase the test error rate. In this work, we develop TESSERACT---a defense against this directed deviation attack, a state-of-the-art model poisoning attack. TESSERACT is based on a simple intuition that in a federated learning setting, certain patterns of gradient flips are indicative of an attack. This intuition is remarkably stable across different learning algorithms, models, and datasets. TESSERACT assigns reputation scores to the participating clients based on their behavior during the training phase and then takes a weighted contribution of the clients. We show that TESSERACT provides robustness against even a white-box version of the attack.

arXiv:2110.06018공식 코드 · Papers with Code

On the Security Risks of AutoML

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.

arXiv:2109.05872공식 코드 · Papers with Code

Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering

Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e.g., by computing validation error rate) or leverages statistic-based methods (e.g. median and Krum) to identify and remove malicious gradients from Byzantine clients. In this paper, we remark that auxiliary data may not always be available in practice and focus on the statistic-based approach. However, recent work on model poisoning attacks has shown that well-crafted attacks can circumvent most of median- and distance-based statistical defense methods, making malicious gradients indistinguishable from honest ones. To tackle this challenge, we show that the element-wise sign of gradient vector can provide valuable insight in detecting model poisoning attacks. Based on our theoretical analysis of the \textit{Little is Enough} attack, we propose a novel approach called \textit{SignGuard} to enable Byzantine-robust federated learning through collaborative malicious gradient filtering. More precisely, the received gradients are first processed to generate relevant magnitude, sign, and similarity statistics, which are then collaboratively utilized by multiple filters to eliminate malicious gradients before final aggregation. Finally, extensive experiments of image and text classification tasks are conducted under recently proposed attacks and defense strategies. The numerical results demonstrate the effectiveness and superiority of our proposed approach. The code is available at \textit{\url{https://github.com/JianXu95/SignGuard}}

arXiv:2109.01275

A Synergetic Attack against Neural Network Classifiers combining Backdoor and Adversarial Examples

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a carefully crafted adversarial perturbation is injected into the input examples during inference, and 2) a Trojan backdoor is implanted during the training process of the model. We leverage adversarial noise in the input space to move Trojan-infected examples across the model decision boundary, making it difficult to detect. The stealthiness behavior of AdvTrojan fools the users into accidentally trust the infected model as a robust classifier against adversarial examples. AdvTrojan can be implemented by only poisoning the training data similar to conventional Trojan backdoor attacks. Our thorough analysis and extensive experiments on several benchmark datasets show that AdvTrojan can bypass existing defenses with a success rate close to 100% in most of our experimental scenarios and can be extended to attack federated learning tasks as well.

arXiv:2108.10241

Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning

While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not fully understood. In this work, we aim to develop a comprehensive systemization for poisoning attacks on FL by enumerating all possible threat models, variations of poisoning, and adversary capabilities. We specifically put our focus on untargeted poisoning attacks, as we argue that they are significantly relevant to production FL deployments. We present a critical analysis of untargeted poisoning attacks under practical, production FL environments by carefully characterizing the set of realistic threat models and adversarial capabilities. Our findings are rather surprising: contrary to the established belief, we show that FL is highly robust in practice even when using simple, low-cost defenses. We go even further and propose novel, state-of-the-art data and model poisoning attacks, and show via an extensive set of experiments across three benchmark datasets how (in)effective poisoning attacks are in the presence of simple defense mechanisms. We aim to correct previous misconceptions and offer concrete guidelines to conduct more accurate (and more realistic) research on this topic.

arXiv:2104.10561

Turning Federated Learning Systems Into Covert Channels

Federated learning (FL) goes beyond traditional, centralized machine learning by distributing model training among a large collection of edge clients. These clients cooperatively train a global, e.g., cloud-hosted, model without disclosing their local, private training data. The global model is then shared among all the participants which use it for local predictions. In this paper, we put forward a novel attacker model aiming at turning FL systems into covert channels to implement a stealth communication infrastructure. The main intuition is that, during federated training, a malicious sender can poison the global model by submitting purposely crafted examples. Although the effect of the model poisoning is negligible to other participants, and does not alter the overall model performance, it can be observed by a malicious receiver and used to transmit a single bit.

arXiv:2104.08020

FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning

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 advanced poisoning attacks or need to centralize a public validation dataset, which is intractable in FL. Moreover, to the best of our knowledge, none of the existing Byzantine-robust distributed learning methods could well exert its power in Non-Independent and Identically distributed (Non-IID) data among clients. To address these issues, we propose FedCom, a novel Byzantine-robust federated learning framework by incorporating the idea of commitment from cryptography, which could achieve both data poisoning and model poisoning tolerant FL under practical Non-IID data partitions. Specifically, in FedCom, each client is first required to make a commitment to its local training data distribution. Then, we identify poisoned datasets by comparing the Wasserstein distance among commitments submitted by different clients. Furthermore, we distinguish abnormal local model updates from benign ones by testing each local model's behavior on its corresponding data commitment. We conduct an extensive performance evaluation of FedCom. The results demonstrate its effectiveness and superior performance compared to the state-of-the-art Byzantine-robust schemes in defending against typical data poisoning and model poisoning attacks under practical Non-IID data distributions.

arXiv:2102.05257공식 코드 · Papers with Code

Robust Federated Learning with Attack-Adaptive Aggregation

Federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks, even if some existing defense strategies are used. To address this challenge, we propose an attack-adaptive aggregation strategy to defend against various attacks for robust federated learning. The proposed approach is based on training a neural network with an attention mechanism that learns the vulnerability of federated learning models from a set of plausible attacks. To the best of our knowledge, our aggregation strategy is the first one that can be adapted to defend against various attacks in a data-driven fashion. Our approach has achieved competitive performance in defending model poisoning and backdoor attacks in federated learning tasks on image and text datasets.

arXiv:2102.02402

SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregation

For model privacy, local model parameters in federated learning shall be obfuscated before sent to the remote aggregator. This technique is referred to as \emph{secure aggregation}. However, secure aggregation makes model poisoning attacks such backdooring more convenient considering that existing anomaly detection methods mostly require access to plaintext local models. This paper proposes SAFELearning which supports backdoor detection for secure aggregation. We achieve this through two new primitives - \emph{oblivious random grouping (ORG)} and \emph{partial parameter disclosure (PPD)}. ORG partitions participants into one-time random subgroups with group configurations oblivious to participants; PPD allows secure partial disclosure of aggregated subgroup models for anomaly detection without leaking individual model privacy. SAFELearning can significantly reduce backdoor model accuracy without jeopardizing the main task accuracy under common backdoor strategies. Extensive experiments show SAFELearning is robust against malicious and faulty participants, whilst being more efficient than the state-of-art secure aggregation protocol in terms of both communication and computation costs.

arXiv:2101.11799

Covert Model Poisoning Against Federated Learning: Algorithm Design and Optimization

Federated learning (FL), as a type of distributed machine learning frameworks, is vulnerable to external attacks on FL models during parameters transmissions. An attacker in FL may control a number of participant clients, and purposely craft the uploaded model parameters to manipulate system outputs, namely, model poisoning (MP). In this paper, we aim to propose effective MP algorithms to combat state-of-the-art defensive aggregation mechanisms (e.g., Krum and Trimmed mean) implemented at the server without being noticed, i.e., covert MP (CMP). Specifically, we first formulate the MP as an optimization problem by minimizing the Euclidean distance between the manipulated model and designated one, constrained by a defensive aggregation rule. Then, we develop CMP algorithms against different defensive mechanisms based on the solutions of their corresponding optimization problems. Furthermore, to reduce the optimization complexity, we propose low complexity CMP algorithms with a slight performance degradation. In the case that the attacker does not know the defensive aggregation mechanism, we design a blind CMP algorithm, in which the manipulated model will be adjusted properly according to the aggregated model generated by the unknown defensive aggregation. Our experimental results demonstrate that the proposed CMP algorithms are effective and substantially outperform existing attack mechanisms.

arXiv:2101.10904

Untargeted Poisoning Attack Detection in Federated Learning via Behavior Attestation

Federated Learning (FL) is a paradigm in Machine Learning (ML) that addresses data privacy, security, access rights and access to heterogeneous information issues by training a global model using distributed nodes. Despite its advantages, there is an increased potential for cyberattacks on FL-based ML techniques that can undermine the benefits. Model-poisoning attacks on FL target the availability of the model. The adversarial objective is to disrupt the training. We propose attestedFL, a defense mechanism that monitors the training of individual nodes through state persistence in order to detect a malicious worker. A fine-grained assessment of the history of the worker permits the evaluation of its behavior in time and results in innovative detection strategies. We present three lines of defense that aim at assessing if the worker is reliable by observing if the node is really training, advancing towards a goal. Our defense exposes an attacker's malicious behavior and removes unreliable nodes from the aggregation process so that the FL process converge faster. Through extensive evaluations and against various adversarial settings, attestedFL increased the accuracy of the model between 12% to 58% under different scenarios such as attacks performed at different stages of convergence, attackers colluding and continuous attacks.

arXiv:2012.04221공식 코드 · Papers with Code

Ditto: Fair and Robust Federated Learning Through Personalization

Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robustness simultaneously on a class of linear problems. Empirically, across a suite of federated datasets, we show that Ditto not only achieves competitive performance relative to recent personalization methods, but also enables more accurate, robust, and fair models relative to state-of-the-art fair or robust baselines.

arXiv:2011.07516

2CP: Decentralized Protocols to Transparently Evaluate Contributivity in Blockchain Federated Learning Environments

Federated Learning harnesses data from multiple sources to build a single model. While the initial model might belong solely to the actor bringing it to the network for training, determining the ownership of the trained model resulting from Federated Learning remains an open question. In this paper we explore how Blockchains (in particular Ethereum) can be used to determine the evolving ownership of a model trained with Federated Learning. Firstly, we use the step-by-step evaluation metric to assess the relative contributivities of participants in a Federated Learning process. Next, we introduce 2CP, a framework comprising two novel protocols for Blockchained Federated Learning, which both reward contributors with shares in the final model based on their relative contributivity. The Crowdsource Protocol allows an actor to bring a model forward for training, and use their own data to evaluate the contributions made to it. Potential trainers are guaranteed a fair share of the resulting model, even in a trustless setting. The Consortium Protocol gives trainers the same guarantee even when no party owns the initial model and no evaluator is available. We conduct experiments with the MNIST dataset that reveal sound contributivity scores resulting from both Protocols by rewarding larger datasets with greater shares in the model. Our experiments also showed the necessity to pair 2CP with a robust model aggregation mechanism to discard low quality inputs coming from model poisoning attacks.

arXiv:2011.02167

BaFFLe: Backdoor detection via Feedback-based Federated Learning

Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable by most existing defensive techniques. In this paper, we propose Backdoor detection via Feedback-based Federated Learning (BAFFLE), a novel defense to secure FL against backdoor attacks. The core idea behind BAFFLE is to leverage data of multiple clients not only for training but also for uncovering model poisoning. We exploit the availability of diverse datasets at the various clients by incorporating a feedback loop into the FL process, to integrate the views of those clients when deciding whether a given model update is genuine or not. We show that this powerful construct can achieve very high detection rates against state-of-the-art backdoor attacks, even when relying on straightforward methods to validate the model. Through empirical evaluation using the CIFAR-10 and FEMNIST datasets, we show that by combining the feedback loop with a method that suspects poisoning attempts by assessing the per-class classification performance of the updated model, BAFFLE reliably detects state-of-the-art backdoor attacks with a detection accuracy of 100% and a false-positive rate below 5%. Moreover, we show that our solution can detect adaptive attacks aimed at bypassing the defense.