Certified Federated Adversarial Training

• URL: http://arxiv.org/abs/2112.10525v1
• Date: Mon, 20 Dec 2021 13:40:20 GMT
• Title: Certified Federated Adversarial Training
• Authors: Giulio Zizzo, Ambrish Rawat, Mathieu Sinn, Sergio Maffeis, Chris Hankin
• Abstract summary: We tackle the scenario of securing FL systems conducting adversarial training when a quorum of workers could be completely malicious. We model an attacker who poisons the model to insert a weakness into the adversarial training such that the model displays apparent adversarial robustness. We show that this defence can preserve adversarial robustness even against an adaptive attacker.
• Score: 3.474871319204387
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In federated learning (FL), robust aggregation schemes have been developed to protect against malicious clients. Many robust aggregation schemes rely on certain numbers of benign clients being present in a quorum of workers. This can be hard to guarantee when clients can join at will, or join based on factors such as idle system status, and connected to power and WiFi. We tackle the scenario of securing FL systems conducting adversarial training when a quorum of workers could be completely malicious. We model an attacker who poisons the model to insert a weakness into the adversarial training such that the model displays apparent adversarial robustness, while the attacker can exploit the inserted weakness to bypass the adversarial training and force the model to misclassify adversarial examples. We use abstract interpretation techniques to detect such stealthy attacks and block the corrupted model updates. We show that this defence can preserve adversarial robustness even against an adaptive attacker.

Related papers

• FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training [16.10247754923311]
  We introduce a novel approach called Fair Targeted Adversarial Training (FAIR-TAT) We show that using targeted adversarial attacks for adversarial training (instead of untargeted attacks) can allow for more favorable trade-offs with respect to adversarial fairness.
  arXiv  Detail & Related papers  (2024-10-30T15:58:03Z)
• Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning [49.242828934501986]
  Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features. backdoor attacks subtly embed malicious behaviors within the model during training. We introduce an innovative token-based localized forgetting training regime.
  arXiv  Detail & Related papers  (2024-03-24T18:33:15Z)
• FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning [98.43475653490219]
  Federated learning (FL) is susceptible to poisoning attacks. FreqFed is a novel aggregation mechanism that transforms the model updates into the frequency domain. We demonstrate that FreqFed can mitigate poisoning attacks effectively with a negligible impact on the utility of the aggregated model.
  arXiv  Detail & Related papers  (2023-12-07T16:56:24Z)
• FedDefender: Client-Side Attack-Tolerant Federated Learning [60.576073964874]
  Federated learning enables learning from decentralized data sources without compromising privacy. It is vulnerable to model poisoning attacks, where malicious clients interfere with the training process. We propose a new defense mechanism that focuses on the client-side, called FedDefender, to help benign clients train robust local models.
  arXiv  Detail & Related papers  (2023-07-18T08:00:41Z)
• Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack [53.032801921915436]
  Human Activity Recognition (HAR) has been employed in a wide range of applications, e.g. self-driving cars. Recently, the robustness of skeleton-based HAR methods have been questioned due to their vulnerability to adversarial attacks. We show such threats exist, even when the attacker only has access to the input/output of the model. We propose the very first black-box adversarial attack approach in skeleton-based HAR called BASAR.
  arXiv  Detail & Related papers  (2022-11-21T09:51:28Z)
• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning [66.56240101249803]
  We study how hardening benign clients can affect the global model (and the malicious clients) We propose a trigger reverse engineering based defense and show that our method can achieve improvement with guarantee robustness. Our results on eight competing SOTA defense methods show the empirical superiority of our method on both single-shot and continuous FL backdoor attacks.
  arXiv  Detail & Related papers  (2022-10-23T22:24:03Z)
• Characterizing Internal Evasion Attacks in Federated Learning [12.873984200814533]
  Federated learning allows for clients to jointly train a machine learning model. Clients' models are vulnerable to attacks during the training and testing phases. In this paper, we address the issue of adversarial clients performing "internal evasion attacks"
  arXiv  Detail & Related papers  (2022-09-17T21:46:38Z)
• BlockFLA: Accountable Federated Learning via Hybrid Blockchain Architecture [11.908715869667445]
  Federated Learning (FL) is a distributed, and decentralized machine learning protocol. It has been shown that an attacker can inject backdoors to the trained model during FL. We develop a hybrid blockchain-based FL framework that uses smart contracts to automatically detect, and punish the attackers.
  arXiv  Detail & Related papers  (2020-10-14T22:43:39Z)
• Dynamic Defense Against Byzantine Poisoning Attacks in Federated Learning [11.117880929232575]
  Federated learning is vulnerable to Byzatine poisoning adversarial attacks. We propose a dynamic aggregation operator that dynamically discards those adversarial clients. The results show that the dynamic selection of the clients to aggregate enhances the performance of the global learning model.
  arXiv  Detail & Related papers  (2020-07-29T18:02:11Z)
• Adversarial Example Games [51.92698856933169]
  Adrial Example Games (AEG) is a framework that models the crafting of adversarial examples. AEG provides a new way to design adversarial examples by adversarially training a generator and aversa from a given hypothesis class. We demonstrate the efficacy of AEG on the MNIST and CIFAR-10 datasets.
  arXiv  Detail & Related papers  (2020-07-01T19:47:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.