Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910890412998656 |
|---|---|
| author | Raza, Ali Li, Shujun Tran, Kim-Phuc Koehl, Ludovic Tran, Kim Duc |
| author_facet | Raza, Ali Li, Shujun Tran, Kim-Phuc Koehl, Ludovic Tran, Kim Duc |
| contents | Adversarial attacks such as poisoning attacks have attracted the attention of many machine learning researchers. Traditionally, poisoning attacks attempt to inject adversarial training data in order to manipulate the trained model. In federated learning (FL), data poisoning attacks can be generalized to model poisoning attacks, which cannot be detected by simpler methods due to the lack of access to local training data by the detector. State-of-the-art poisoning attack detection methods for FL have various weaknesses, e.g., the number of attackers has to be known or not high enough, working with i.i.d. data only, and high computational complexity. To overcome above weaknesses, we propose a novel framework for detecting poisoning attacks in FL, which employs a reference model based on a public dataset and an auditor model to detect malicious updates. We implemented a detector based on the proposed framework and using a one-class support vector machine (OC-SVM), which reaches the lowest possible computational complexity O(K) where K is the number of clients. We evaluated our detector's performance against state-of-the-art (SOTA) poisoning attacks for two typical applications of FL: electrocardiograph (ECG) classification and human activity recognition (HAR). Our experimental results validated the performance of our detector over other SOTA detection methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2207_08486 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications Raza, Ali Li, Shujun Tran, Kim-Phuc Koehl, Ludovic Tran, Kim Duc Machine Learning Cryptography and Security Adversarial attacks such as poisoning attacks have attracted the attention of many machine learning researchers. Traditionally, poisoning attacks attempt to inject adversarial training data in order to manipulate the trained model. In federated learning (FL), data poisoning attacks can be generalized to model poisoning attacks, which cannot be detected by simpler methods due to the lack of access to local training data by the detector. State-of-the-art poisoning attack detection methods for FL have various weaknesses, e.g., the number of attackers has to be known or not high enough, working with i.i.d. data only, and high computational complexity. To overcome above weaknesses, we propose a novel framework for detecting poisoning attacks in FL, which employs a reference model based on a public dataset and an auditor model to detect malicious updates. We implemented a detector based on the proposed framework and using a one-class support vector machine (OC-SVM), which reaches the lowest possible computational complexity O(K) where K is the number of clients. We evaluated our detector's performance against state-of-the-art (SOTA) poisoning attacks for two typical applications of FL: electrocardiograph (ECG) classification and human activity recognition (HAR). Our experimental results validated the performance of our detector over other SOTA detection methods. |
| title | Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2207.08486 |