PyTorchKR Papers

최신 논문

총 109편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2311.10248

Identifying the Truth of Global Model: A Generic Solution to Defend Against Byzantine and Backdoor Attacks in Federated Learning (full version)

Federated Learning (FL) enables multiple parties to train machine learning models collaboratively without sharing the raw training data. However, the federated nature of FL enables malicious clients to influence a trained model by injecting error model updates via Byzantine or backdoor attacks. To detect malicious model updates, a typical approach is to measure the distance between each model update and a \textit{ground-truth model update}. To find such \textit{ground-truth model updates}, existing defenses either require a benign root dataset on the server (e.g., FLTrust) or simply use trimmed mean or median as the threshold for clipping (e.g., FLAME). However, such benign root datasets are impractical, and the trimmed mean or median may also eliminate contributions from these underrepresented datasets. In this paper, we propose a generic solution, namely FedTruth, to defend against model poisoning attacks in FL, where the \textit{ground-truth model update} (i.e., the global model update) will be estimated among all the model updates with dynamic aggregation weights. Specifically, FedTruth does not have specific assumptions on the benign or malicious data distribution or access to a benign root dataset. Moreover, FedTruth considers the potential contributions from all benign clients. Our empirical results show that FedTruth can reduce the impacts of poisoned model updates against both Byzantine and backdoor attacks, and is also efficient in large-scale FL systems.

arXiv:2311.03369

Can We Trust the Similarity Measurement in Federated Learning?

Is it secure to measure the reliability of local models by similarity in federated learning (FL)? This paper delves into an unexplored security threat concerning applying similarity metrics, such as the L_2 norm, Euclidean distance, and cosine similarity, in protecting FL. We first uncover the deficiencies of similarity metrics that high-dimensional local models, including benign and poisoned models, may be evaluated to have the same similarity while being significantly different in the parameter values. We then leverage this finding to devise a novel untargeted model poisoning attack, Faker, which launches the attack by simultaneously maximizing the evaluated similarity of the poisoned local model and the difference in the parameter values. Experimental results based on seven datasets and eight defenses show that Faker outperforms the state-of-the-art benchmark attacks by 1.1-9.0X in reducing accuracy and 1.2-8.0X in saving time cost, which even holds for the case of a single malicious client with limited knowledge about the FL system. Moreover, Faker can degrade the performance of the global model by attacking only once. We also preliminarily explore extending Faker to other attacks, such as backdoor attacks and Sybil attacks. Lastly, we provide a model evaluation strategy, called the similarity of partial parameters (SPP), to defend against Faker. Given that numerous mechanisms in FL utilize similarity metrics to assess local models, this work suggests that we should be vigilant regarding the potential risks of using these metrics.

arXiv:2310.04055

Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification

Federated Learning (FL) systems are vulnerable to adversarial attacks, such as model poisoning and backdoor attacks. However, existing defense mechanisms often fall short in real-world settings due to key limitations: they may rely on impractical assumptions, introduce distortions by modifying aggregation functions, or degrade model performance even in benign scenarios. To address these issues, we propose a novel anomaly detection method designed specifically for practical FL scenarios. Our approach employs a two-stage, conditionally activated detection mechanism: cross-round check first detects whether suspicious activity has occurred, and, if warranted, a cross-client check filters out malicious participants. This mechanism preserves utility while avoiding unrealistic assumptions. Moreover, to ensure the transparency and integrity of the defense mechanism, we incorporate zero-knowledge proofs, enabling clients to verify the detection without relying solely on the server's goodwill. To the best of our knowledge, this is the first method to bridge the gap between theoretical advances in FL security and the demands of real-world deployment. Extensive experiments across diverse tasks and real-world edge devices demonstrate the effectiveness of our method over state-of-the-art defenses.

arXiv:2308.07387

DISBELIEVE: Distance Between Client Models is Very Essential for Effective Local Model Poisoning Attacks

Federated learning is a promising direction to tackle the privacy issues related to sharing patients' sensitive data. Often, federated systems in the medical image analysis domain assume that the participating local clients are \textit{honest}. Several studies report mechanisms through which a set of malicious clients can be introduced that can poison the federated setup, hampering the performance of the global model. To overcome this, robust aggregation methods have been proposed that defend against those attacks. We observe that most of the state-of-the-art robust aggregation methods are heavily dependent on the distance between the parameters or gradients of malicious clients and benign clients, which makes them prone to local model poisoning attacks when the parameters or gradients of malicious and benign clients are close. Leveraging this, we introduce DISBELIEVE, a local model poisoning attack that creates malicious parameters or gradients such that their distance to benign clients' parameters or gradients is low respectively but at the same time their adverse effect on the global model's performance is high. Experiments on three publicly available medical image datasets demonstrate the efficacy of the proposed DISBELIEVE attack as it significantly lowers the performance of the state-of-the-art \textit{robust aggregation} methods for medical image analysis. Furthermore, compared to state-of-the-art local model poisoning attacks, DISBELIEVE attack is also effective on natural images where we observe a severe drop in classification performance of the global model for multi-class classification on benchmark dataset CIFAR-10.

arXiv:2308.02747

SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection

In this work, we introduce SureFED, a novel framework for byzantine robust federated learning. Unlike many existing defense methods that rely on statistically robust quantities, making them vulnerable to stealthy and colluding attacks, SureFED establishes trust using the local information of benign clients. SureFED utilizes an uncertainty aware model evaluation and introspection to safeguard against poisoning attacks. In particular, each client independently trains a clean local model exclusively using its local dataset, acting as the reference point for evaluating model updates. SureFED leverages Bayesian models that provide model uncertainties and play a crucial role in the model evaluation process. Our framework exhibits robustness even when the majority of clients are compromised, remains agnostic to the number of malicious clients, and is well-suited for non-IID settings. We theoretically prove the robustness of our algorithm against data and model poisoning attacks in a decentralized linear regression setting. Proof-of Concept evaluations on benchmark image classification data demonstrate the superiority of SureFED over the state of the art defense methods under various colluding and non-colluding data and model poisoning attacks.

arXiv:2307.09048공식 코드 · Papers with Code

FedDefender: Client-Side Attack-Tolerant Federated Learning

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.

arXiv:2307.01565

An Analysis of Untargeted Poisoning Attack and Defense Methods for Federated Online Learning to Rank Systems

Federated online learning to rank (FOLTR) aims to preserve user privacy by not sharing their searchable data and search interactions, while guaranteeing high search effectiveness, especially in contexts where individual users have scarce training data and interactions. For this, FOLTR trains learning to rank models in an online manner -- i.e. by exploiting users' interactions with the search systems (queries, clicks), rather than labels -- and federatively -- i.e. by not aggregating interaction data in a central server for training purposes, but by training instances of a model on each user device on their own private data, and then sharing the model updates, not the data, across a set of users that have formed the federation. Existing FOLTR methods build upon advances in federated learning. While federated learning methods have been shown effective at training machine learning models in a distributed way without the need of data sharing, they can be susceptible to attacks that target either the system's security or its overall effectiveness. In this paper, we consider attacks on FOLTR systems that aim to compromise their search effectiveness. Within this scope, we experiment with and analyse data and model poisoning attack methods to showcase their impact on FOLTR search effectiveness. We also explore the effectiveness of defense methods designed to counteract attacks on FOLTR systems. We contribute an understanding of the effect of attack and defense methods for FOLTR systems, as well as identifying the key factors influencing their effectiveness.

arXiv:2306.13800

A First Order Meta Stackelberg Method for Robust Federated Learning

Previous research has shown that federated learning (FL) systems are exposed to an array of security risks. Despite the proposal of several defensive strategies, they tend to be non-adaptive and specific to certain types of attacks, rendering them ineffective against unpredictable or adaptive threats. This work models adversarial federated learning as a Bayesian Stackelberg Markov game (BSMG) to capture the defender's incomplete information of various attack types. We propose meta-Stackelberg learning (meta-SL), a provably efficient meta-learning algorithm, to solve the equilibrium strategy in BSMG, leading to an adaptable FL defense. We demonstrate that meta-SL converges to the first-order $\varepsilon$-equilibrium point in $O(\varepsilon^{-2})$ gradient iterations, with $O(\varepsilon^{-4})$ samples needed per iteration, matching the state of the art. Empirical evidence indicates that our meta-Stackelberg framework performs exceptionally well against potent model poisoning and backdoor attacks of an uncertain nature.

arXiv:2306.13157

Anticipatory Thinking Challenges in Open Worlds: Risk Management

Anticipatory thinking drives our ability to manage risk - identification and mitigation - in everyday life, from bringing an umbrella when it might rain to buying car insurance. As AI systems become part of everyday life, they too have begun to manage risk. Autonomous vehicles log millions of miles, StarCraft and Go agents have similar capabilities to humans, implicitly managing risks presented by their opponents. To further increase performance in these tasks, out-of-distribution evaluation can characterize a model's bias, what we view as a type of risk management. However, learning to identify and mitigate low-frequency, high-impact risks is at odds with the observational bias required to train machine learning models. StarCraft and Go are closed-world domains whose risks are known and mitigations well documented, ideal for learning through repetition. Adversarial filtering datasets provide difficult examples but are laborious to curate and static, both barriers to real-world risk management. Adversarial robustness focuses on model poisoning under the assumption there is an adversary with malicious intent, without considering naturally occurring adversarial examples. These methods are all important steps towards improving risk management but do so without considering open-worlds. We unify these open-world risk management challenges with two contributions. The first is our perception challenges, designed for agents with imperfect perceptions of their environment whose consequences have a high impact. Our second contribution are cognition challenges, designed for agents that must dynamically adjust their risk exposure as they identify new risks and learn new mitigations. Our goal with these challenges is to spur research into solutions that assess and improve the anticipatory thinking required by AI agents to manage risk in open-worlds and ultimately the real-world.

arXiv:2306.04872

Mitigating Evasion Attacks in Federated Learning-Based Signal Classifiers

Recent interest in leveraging federated learning (FL) for radio signal classification (SC) tasks has shown promise but FL-based SC remains susceptible to model poisoning adversarial attacks. These adversarial attacks mislead the ML model training process, damaging ML models across the network and leading to lower SC performance. In this work, we seek to mitigate model poisoning adversarial attacks on FL-based SC by proposing the Underlying Server Defense of Federated Learning (USD-FL). Unlike existing server-driven defenses, USD-FL does not rely on perfect network information, i.e., knowing the quantity of adversaries, the adversarial attack architecture, or the start time of the adversarial attacks. Our proposed USD-FL methodology consists of deriving logits for devices' ML models on a reserve dataset, comparing pair-wise logits via 1-Wasserstein distance and then determining a time-varying threshold for adversarial detection. As a result, USD-FL effectively mitigates model poisoning attacks introduced in the FL network. Specifically, when baseline server-driven defenses do have perfect network information, USD-FL outperforms them by (i) improving final ML classification accuracies by at least 6%, (ii) reducing false positive adversary detection rates by at least 10%, and (iii) decreasing the total number of misclassified signals by over 8%. Moreover, when baseline defenses do not have perfect network information, we show that USD-FL achieves accuracies of approximately 74.1% and 62.5% in i.i.d. and non-i.i.d. settings, outperforming existing server-driven baselines, which achieve 52.1% and 39.2% in i.i.d. and non-i.i.d. settings, respectively.

arXiv:2305.08183

Manipulating Visually-aware Federated Recommender Systems and Its Countermeasures

Federated recommender systems (FedRecs) have been widely explored recently due to their ability to protect user data privacy. In FedRecs, a central server collaboratively learns recommendation models by sharing model public parameters with clients, thereby offering a privacy-preserving solution. Unfortunately, the exposure of model parameters leaves a backdoor for adversaries to manipulate FedRecs. Existing works about FedRec security already reveal that items can easily be promoted by malicious users via model poisoning attacks, but all of them mainly focus on FedRecs with only collaborative information (i.e., user-item interactions). We argue that these attacks are effective because of the data sparsity of collaborative signals. In practice, auxiliary information, such as products' visual descriptions, is used to alleviate collaborative filtering data's sparsity. Therefore, when incorporating visual information in FedRecs, all existing model poisoning attacks' effectiveness becomes questionable. In this paper, we conduct extensive experiments to verify that incorporating visual information can beat existing state-of-the-art attacks in reasonable settings. However, since visual information is usually provided by external sources, simply including it will create new security problems. Specifically, we propose a new kind of poisoning attack for visually-aware FedRecs, namely image poisoning attacks, where adversaries can gradually modify the uploaded image to manipulate item ranks during FedRecs' training process. Furthermore, we reveal that the potential collaboration between image poisoning attacks and model poisoning attacks will make visually-aware FedRecs more vulnerable to being manipulated. To safely use visual information, we employ a diffusion model in visually-aware FedRecs to purify each uploaded image and detect the adversarial images.

arXiv:2305.02022

A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning

Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case attacks that target a small fraction of the input space are nearly impossible to detect using existing defenses, leading to a high attack success rate. We propose an effective defense using an external defense dataset, which provides information about the attack target. The defense dataset contains a mix of poisoned and clean examples, with only a few known to be clean. The proposed method, DataDefense, uses this dataset to learn a poisoned data detector model which marks each example in the defense dataset as poisoned or clean. It also learns a client importance model that estimates the probability of a client update being malicious. The global model is then updated as a weighted average of the client models' updates. The poisoned data detector and the client importance model parameters are updated using an alternating minimization strategy over the Federated Learning rounds. Extensive experiments on standard attack scenarios demonstrate that DataDefense can defend against model poisoning attacks where other state-of-the-art defenses fail. In particular, DataDefense is able to reduce the attack success rate by at least ~ 40% on standard attack setups and by more than 80% on some setups. Furthermore, DataDefense requires very few defense examples (as few as five) to achieve a near-optimal reduction in attack success rate.

arXiv:2304.12961공식 코드 · Papers with Code

Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning

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.

arXiv:2304.10783

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious perturbations along certain prescribed directions to cause DoS, we propose a Flexible Model Poisoning Attack (FMPA) that can achieve versatile attack goals. We consider a practical threat scenario where no extra knowledge about the FL system (e.g., aggregation rules or updates on benign devices) is available to adversaries. FMPA exploits the global historical information to construct an estimator that predicts the next round of the global model as a benign reference. It then fine-tunes the reference model to obtain the desired poisoned model with low accuracy and small perturbations. Besides the goal of causing DoS, FMPA can be naturally extended to launch a fine-grained controllable attack, making it possible to precisely reduce the global accuracy. Armed with precise control, malicious FL service providers can gain advantages over their competitors without getting noticed, hence opening a new attack surface in FL other than DoS. Even for the purpose of DoS, experiments show that FMPA significantly decreases the global accuracy, outperforming six state-of-the-art attacks.

arXiv:2303.16668

Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection

Current defense mechanisms against model poisoning attacks in federated learning (FL) systems have proven effective up to a certain threshold of malicious clients. In this work, we introduce FLANDERS, a novel pre-aggregation filter for FL resilient to large-scale model poisoning attacks, i.e., when malicious clients far exceed legitimate participants. FLANDERS treats the sequence of local models sent by clients in each FL round as a matrix-valued time series. Then, it identifies malicious client updates as outliers in this time series by comparing actual observations with estimates generated by a matrix autoregressive forecasting model maintained by the server. Experiments conducted in several non-iid FL setups show that FLANDERS significantly improves robustness across a wide spectrum of attacks when paired with standard and robust existing aggregation methods.

arXiv:2303.03592공식 코드 · Papers with Code

Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks

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.

arXiv:2303.01243

Poster: Sponge ML Model Attacks of Mobile Apps

Machine Learning (ML)-powered apps are used in pervasive devices such as phones, tablets, smartwatches and IoT devices. Recent advances in collaborative, distributed ML such as Federated Learning (FL) attempt to solve privacy concerns of users and data owners, and thus used by tech industry leaders such as Google, Facebook and Apple. However, FL systems and models are still vulnerable to adversarial membership and attribute inferences and model poisoning attacks, especially in FL-as-a-Service ecosystems recently proposed, which can enable attackers to access multiple ML-powered apps. In this work, we focus on the recently proposed Sponge attack: It is designed to soak up energy consumed while executing inference (not training) of ML model, without hampering the classifier's performance. Recent work has shown sponge attacks on ASCI-enabled GPUs can potentially escalate the power consumption and inference time. For the first time, in this work, we investigate this attack in the mobile setting and measure the effect it can have on ML models running inside apps on mobile devices.

arXiv:2303.01021

CADeSH: Collaborative Anomaly Detection for Smart Homes

Although home IoT (Internet of Things) devices are typically plain and task oriented, the context of their daily use may affect their traffic patterns. For this reason, anomaly-based intrusion detection systems tend to suffer from a high false positive rate (FPR). To overcome this, we propose a two-step collaborative anomaly detection method which first uses an autoencoder to differentiate frequent (`benign') and infrequent (possibly `malicious') traffic flows. Clustering is then used to analyze only the infrequent flows and classify them as either known ('rare yet benign') or unknown (`malicious'). Our method is collaborative, in that (1) normal behaviors are characterized more robustly, as they take into account a variety of user interactions and network topologies, and (2) several features are computed based on a pool of identical devices rather than just the inspected device. We evaluated our method empirically, using 21 days of real-world traffic data that emanated from eight identical IoT devices deployed on various networks, one of which was located in our controlled lab where we implemented two popular IoT-related cyber-attacks. Our collaborative anomaly detection method achieved a macro-average area under the precision-recall curve of 0.841, an F1 score of 0.929, and an FPR of only 0.014. These promising results were obtained by using labeled traffic data from our lab as the test set, while training the models on the traffic of devices deployed outside the lab, and thus demonstrate a high level of generalizability. In addition to its high generalizability and promising performance, our proposed method also offers benefits such as privacy preservation, resource savings, and model poisoning mitigation. On top of that, as a contribution to the scientific community, our novel dataset is available online.

arXiv:2302.09904

WW-FL: Secure and Private Large-Scale Federated Learning

Federated learning (FL) is an efficient approach for large-scale distributed machine learning that promises data privacy by keeping training data on client devices. However, recent research has uncovered vulnerabilities in FL, impacting both security and privacy through poisoning attacks and the potential disclosure of sensitive information in individual model updates as well as the aggregated global model. This paper explores the inadequacies of existing FL protection measures when applied independently, and the challenges of creating effective compositions. Addressing these issues, we propose WW-FL, an innovative framework that combines secure multi-party computation (MPC) with hierarchical FL to guarantee data and global model privacy. One notable feature of WW-FL is its capability to prevent malicious clients from directly poisoning model parameters, confining them to less destructive data poisoning attacks. We furthermore provide a PyTorch-based FL implementation integrated with Meta's CrypTen MPC framework to systematically measure the performance and robustness of WW-FL. Our extensive evaluation demonstrates that WW-FL is a promising solution for secure and private large-scale federated learning.

arXiv:2302.00271

CATFL: Certificateless Authentication-based Trustworthy Federated Learning for 6G Semantic Communications

Federated learning (FL) provides an emerging approach for collaboratively training semantic encoder/decoder models of semantic communication systems, without private user data leaving the devices. Most existing studies on trustworthy FL aim to eliminate data poisoning threats that are produced by malicious clients, but in many cases, eliminating model poisoning attacks brought by fake servers is also an important objective. In this paper, a certificateless authentication-based trustworthy federated learning (CATFL) framework is proposed, which mutually authenticates the identity of clients and server. In CATFL, each client verifies the server's signature information before accepting the delivered global model to ensure that the global model is not delivered by false servers. On the contrary, the server also verifies the server's signature information before accepting the delivered model updates to ensure that they are submitted by authorized clients. Compared to PKI-based methods, the CATFL can avoid too high certificate management overheads. Meanwhile, the anonymity of clients shields data poisoning attacks, while real-name registration may suffer from user-specific privacy leakage risks. Therefore, a pseudonym generation strategy is also presented in CATFL to achieve a trade-off between identity traceability and user anonymity, which is essential to conditionally prevent from user-specific privacy leakage. Theoretical security analysis and evaluation results validate the superiority of CATFL.