How to Backdoor HyperNetwork in Personalized Federated Learning?

• URL: http://arxiv.org/abs/2201.07063v3
• Date: Mon, 11 Dec 2023 13:15:51 GMT
• Title: How to Backdoor HyperNetwork in Personalized Federated Learning?
• Abstract summary: We propose a novel model transferring attack (HNTroj) to transfer a local backdoor infected model to all legitimate and personalized local models. HNTroj reduces the number of compromised clients needed to successfully launch the attack. An experiment that is carried out using several benchmark datasets shows that HNTroj significantly outperforms data poisoning and model replacement attacks.
• Score: 16.190739713218942
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper explores previously unknown backdoor risks in HyperNet-based personalized federated learning (HyperNetFL) through poisoning attacks. Based upon that, we propose a novel model transferring attack (called HNTroj), i.e., the first of its kind, to transfer a local backdoor infected model to all legitimate and personalized local models, which are generated by the HyperNetFL model, through consistent and effective malicious local gradients computed across all compromised clients in the whole training process. As a result, HNTroj reduces the number of compromised clients needed to successfully launch the attack without any observable signs of sudden shifts or degradation regarding model utility on legitimate data samples making our attack stealthy. To defend against HNTroj, we adapted several backdoor-resistant FL training algorithms into HyperNetFL. An extensive experiment that is carried out using several benchmark datasets shows that HNTroj significantly outperforms data poisoning and model replacement attacks and bypasses robust training algorithms even with modest numbers of compromised clients.

Related papers

• SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors [9.273743530407977]
  Federated Learning (FL) enables collaborative model training without sharing raw data.<n>It is vulnerable to backdoor attacks, where malicious clients embed hidden triggers into local training data to manipulate model predictions.<n>We propose SCRUB-FL, a two-phase solution for post-training backdoor removal in FL.
  arXiv  Detail & Related papers  (2026-06-21T22:34:34Z)
• Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips [1.0874100424278175]
  Federated Learning (FL) allows a set of clients to collectively train a global model without sharing local training data.<n>Recent advances in hardware faults threats have widen the overall attack surface.<n>We propose a task-agnostic backdoor attack that is implanted during the FL training time by inducing hardware faults.
  arXiv  Detail & Related papers  (2026-06-08T14:27:21Z)
• ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version) [58.595691399741646]
  Split Learning (SL) is a distributed learning approach that enables resource-constrained clients to collaboratively train deep neural networks (DNNs)<n>This setup enables SL to leverage server capacities without sharing data, making it highly effective in resource-constrained environments dealing with sensitive data.<n>We present ZORRO, a private, verifiable, and robust SL defense scheme.
  arXiv  Detail & Related papers  (2025-09-11T18:44:09Z)
• BadSFL: Backdoor Attack against Scaffold Federated Learning [16.104941796138128]
  Federated learning (FL) enables the training of deep learning models on distributed clients to preserve data privacy. BadSFL is a novel backdoor attack method designed for the FL framework using the scaffold aggregation algorithm in non-IID settings. BadSFL is effective over 60 rounds in the global model and up to 3 times longer than existing baseline attacks.
  arXiv  Detail & Related papers  (2024-11-25T07:46:57Z)
• Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats [52.94388672185062]
  We propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime.
  arXiv  Detail & Related papers  (2024-09-29T02:55:38Z)
• Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic Classification [1.1887808102491482]
  We propose GABAttack, a novel genetic algorithm-based backdoor attack against federated learning for network traffic classification. This research serves as an alarming call for network security experts and practitioners to develop robust defense measures against such attacks.
  arXiv  Detail & Related papers  (2023-09-27T14:02:02Z)
• Client-side Gradient Inversion Against Federated Learning from Poisoning [59.74484221875662]
  Federated Learning (FL) enables distributed participants to train a global model without sharing data directly to a central server. Recent studies have revealed that FL is vulnerable to gradient inversion attack (GIA), which aims to reconstruct the original training samples. We propose Client-side poisoning Gradient Inversion (CGI), which is a novel attack method that can be launched from clients.
  arXiv  Detail & Related papers  (2023-09-14T03:48:27Z)
• One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training [54.622474306336635]
  A new weight modification attack called bit flip attack (BFA) was proposed, which exploits memory fault inject techniques. We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release.
  arXiv  Detail & Related papers  (2023-08-12T09:34:43Z)
• 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)
• FedDefender: Backdoor Attack Defense in Federated Learning [0.0]
  Federated Learning (FL) is a privacy-preserving distributed machine learning technique. We propose FedDefender, a defense mechanism against targeted poisoning attacks in FL.
  arXiv  Detail & Related papers  (2023-07-02T03:40:04Z)
• DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning [14.312593000209693]
  Federated learning (FL) attempts to train a global model by aggregating local models from distributed devices under the coordination of a central server. The existence of a large number of heterogeneous devices makes FL vulnerable to various attacks, especially the stealthy backdoor attack. We propose a new attack model for FL, namely Data-Agnostic Backdoor attack at the Server (DABS), where the server directly modifies the global model to backdoor an FL system.
  arXiv  Detail & Related papers  (2023-05-02T09:04:34Z)
• CrowdGuard: Federated Backdoor Detection in Federated Learning [39.58317527488534]
  This paper presents a novel defense mechanism, CrowdGuard, that effectively mitigates backdoor attacks in Federated Learning. CrowdGuard employs a server-located stacked clustering scheme to enhance its resilience to rogue client feedback. The evaluation results demonstrate that CrowdGuard achieves a 100% True-Positive-Rate and True-Negative-Rate across various scenarios.
  arXiv  Detail & Related papers  (2022-10-14T11:27:49Z)
• FL-Defender: Combating Targeted Attacks in Federated Learning [7.152674461313707]
  Federated learning (FL) enables learning a global machine learning model from local data distributed among a set of participating workers. FL is vulnerable to targeted poisoning attacks that negatively impact the integrity of the learned model. We propose textitFL-Defender as a method to combat FL targeted attacks.
  arXiv  Detail & Related papers  (2022-07-02T16:04:46Z)
• CRFL: Certifiably Robust Federated Learning against Backdoor Attacks [59.61565692464579]
  This paper provides the first general framework, Certifiably Robust Federated Learning (CRFL), to train certifiably robust FL models against backdoors. Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude.
  arXiv  Detail & Related papers  (2021-06-15T16:50:54Z)
• Scalable Backdoor Detection in Neural Networks [61.39635364047679]
  Deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch. We propose a novel trigger reverse-engineering based approach whose computational complexity does not scale with the number of labels, and is based on a measure that is both interpretable and universal across different network and patch types. In experiments, we observe that our method achieves a perfect score in separating Trojaned models from pure models, which is an improvement over the current state-of-the art method.
  arXiv  Detail & Related papers  (2020-06-10T04:12:53Z)

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.