Logits Poisoning Attack in Federated Distillation

• URL: http://arxiv.org/abs/2401.03685v1
• Date: Mon, 8 Jan 2024 06:18:46 GMT
• Title: Logits Poisoning Attack in Federated Distillation
• Authors: Yuhan Tang, Zhiyuan Wu, Bo Gao, Tian Wen, Yuwei Wang, Sheng Sun
• Abstract summary: We introduce FDLA, a poisoning attack method tailored for Federated Distillation (FD) We demonstrate that LPA effectively compromises client model accuracy, outperforming established baseline algorithms in this regard. Our findings underscore the critical need for robust defense mechanisms in FD settings to mitigate such adversarial threats.
• Score: 8.728629314547248
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Distillation (FD) is a novel and promising distributed machine learning paradigm, where knowledge distillation is leveraged to facilitate a more efficient and flexible cross-device knowledge transfer in federated learning. By optimizing local models with knowledge distillation, FD circumvents the necessity of uploading large-scale model parameters to the central server, simultaneously preserving the raw data on local clients. Despite the growing popularity of FD, there is a noticeable gap in previous works concerning the exploration of poisoning attacks within this framework. This can lead to a scant understanding of the vulnerabilities to potential adversarial actions. To this end, we introduce FDLA, a poisoning attack method tailored for FD. FDLA manipulates logit communications in FD, aiming to significantly degrade model performance on clients through misleading the discrimination of private samples. Through extensive simulation experiments across a variety of datasets, attack scenarios, and FD configurations, we demonstrate that LPA effectively compromises client model accuracy, outperforming established baseline algorithms in this regard. Our findings underscore the critical need for robust defense mechanisms in FD settings to mitigate such adversarial threats.

Related papers

• Formal Logic-guided Robust Federated Learning against Poisoning Attacks [6.997975378492098]
  Federated Learning (FL) offers a promising solution to the privacy concerns associated with centralized Machine Learning (ML) FL is vulnerable to various security threats, including poisoning attacks, where adversarial clients manipulate the training data or model updates to degrade overall model performance. We present a defense mechanism designed to mitigate poisoning attacks in federated learning for time-series tasks.
  arXiv  Detail & Related papers  (2024-11-05T16:23:19Z)
• Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense [3.685395311534351]
  Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. FL systems are vulnerable to attacks that are happening in malicious clients through data poisoning and model poisoning. Existing defense methods typically focus on mitigating specific types of poisoning and are often ineffective against unseen types of attack.
  arXiv  Detail & Related papers  (2024-08-05T20:27:45Z)
• Peak-Controlled Logits Poisoning Attack in Federated Distillation [7.844189001319052]
  We present PCFDLA (Peak-Controlled Federated Distillation Logits Attack), an advanced and more stealthy logits poisoning attack method for FD. PCFDLA enhances the effectiveness of FDLA by carefully controlling the peak values of logits to create highly misleading yet inconspicuous modifications.
  arXiv  Detail & Related papers  (2024-07-25T13:36:42Z)
• Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning [4.907460152017894]
  Federated Learning (FL) is a collaborative learning paradigm enabling participants to collectively train a shared machine learning model. Current FL defense strategies against data poisoning attacks either involve a trade-off between accuracy and robustness. We present FedZZ, which harnesses a zone-based deviating update (ZBDU) mechanism to effectively counter data poisoning attacks in FL.
  arXiv  Detail & Related papers  (2024-04-05T14:37:49Z)
• 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)
• Over-the-Air Federated Learning and Optimization [52.5188988624998]
  We focus on Federated learning (FL) via edge-the-air computation (AirComp) We describe the convergence of AirComp-based FedAvg (AirFedAvg) algorithms under both convex and non- convex settings. For different types of local updates that can be transmitted by edge devices (i.e., model, gradient, model difference), we reveal that transmitting in AirFedAvg may cause an aggregation error. In addition, we consider more practical signal processing schemes to improve the communication efficiency and extend the convergence analysis to different forms of model aggregation error caused by these signal processing schemes.
  arXiv  Detail & Related papers  (2023-10-16T05:49:28Z)
• Mitigating Cross-client GANs-based Attack in Federated Learning [78.06700142712353]
  Multi distributed multimedia clients can resort to federated learning (FL) to jointly learn a global shared model. FL suffers from the cross-client generative adversarial networks (GANs)-based (C-GANs) attack. We propose Fed-EDKD technique to improve the current popular FL schemes to resist C-GANs attack.
  arXiv  Detail & Related papers  (2023-07-25T08:15:55Z)
• Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations [55.2480439325792]
  Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. FL faces vulnerabilities such as poisoning attacks, undermining model integrity with both untargeted performance degradation and targeted backdoor attacks. We define a new notion of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. MESAS is the first defense robust against strong adaptive adversaries, effective in real-world data scenarios, with an average overhead of just 24.37 seconds.
  arXiv  Detail & Related papers  (2023-06-06T11:44:42Z)
• Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher [52.2926020848095]
  Federated learning is vulnerable to white-box attacks and struggles to adapt to heterogeneous clients. This paper proposes a selective knowledge sharing mechanism for FD, termed Selective-FD.
  arXiv  Detail & Related papers  (2023-04-04T12:04:19Z)
• 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)
• Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation [20.24005399782197]
  Federated learning is a privacy-preserving machine learning paradigm. Recent proxy-data-free FD approaches can eliminate the need for additional public data, but suffer from remarkable discrepancy among local knowledge. We propose a proxy-data-free FD algorithm based on distributed knowledge congruence (FedDKC)
  arXiv  Detail & Related papers  (2022-04-14T15:39:22Z)

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.