Robust Federated Learning with Attack-Adaptive Aggregation
- URL: http://arxiv.org/abs/2102.05257v1
- Date: Wed, 10 Feb 2021 04:23:23 GMT
- Title: Robust Federated Learning with Attack-Adaptive Aggregation
- Authors: Ching Pui Wan, Qifeng Chen
- Abstract summary: Federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks.
We propose an attack-adaptive aggregation strategy to defend against various attacks for robust learning.
- Score: 45.60981228410952
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Federated learning is vulnerable to various attacks, such as model poisoning
and backdoor attacks, even if some existing defense strategies are used. To
address this challenge, we propose an attack-adaptive aggregation strategy to
defend against various attacks for robust federated learning. The proposed
approach is based on training a neural network with an attention mechanism that
learns the vulnerability of federated learning models from a set of plausible
attacks. To the best of our knowledge, our aggregation strategy is the first
one that can be adapted to defend against various attacks in a data-driven
fashion. Our approach has achieved competitive performance in defending model
poisoning and backdoor attacks in federated learning tasks on image and text
datasets.
Related papers
- GenFighter: A Generative and Evolutive Textual Attack Removal [6.044610337297754]
Adrial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP)
This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial robustness by learning and reasoning on the training classification distribution.
We show that GenFighter outperforms state-of-the-art defenses in accuracy under attack and attack success rate metrics.
arXiv Detail & Related papers (2024-04-17T16:32:13Z) - Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme.
Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
arXiv Detail & Related papers (2023-12-20T05:06:01Z) - Improving Adversarial Robustness with Self-Paced Hard-Class Pair
Reweighting [5.084323778393556]
adversarial training with untargeted attacks is one of the most recognized methods.
We find that the naturally imbalanced inter-class semantic similarity makes those hard-class pairs to become the virtual targets of each other.
We propose to upweight hard-class pair loss in model optimization, which prompts learning discriminative features from hard classes.
arXiv Detail & Related papers (2022-10-26T22:51:36Z) - Resisting Deep Learning Models Against Adversarial Attack
Transferability via Feature Randomization [17.756085566366167]
We propose a feature randomization-based approach that resists eight adversarial attacks targeting deep learning models.
Our methodology can secure the target network and resists adversarial attack transferability by over 60%.
arXiv Detail & Related papers (2022-09-11T20:14:12Z) - LAS-AT: Adversarial Training with Learnable Attack Strategy [82.88724890186094]
"Learnable attack strategy", dubbed LAS-AT, learns to automatically produce attack strategies to improve the model robustness.
Our framework is composed of a target network that uses AEs for training to improve robustness and a strategy network that produces attack strategies to control the AE generation.
arXiv Detail & Related papers (2022-03-13T10:21:26Z) - Projective Ranking-based GNN Evasion Attacks [52.85890533994233]
Graph neural networks (GNNs) offer promising learning methods for graph-related tasks.
GNNs are at risk of adversarial attacks.
arXiv Detail & Related papers (2022-02-25T21:52:09Z) - Survey on Federated Learning Threats: concepts, taxonomy on attacks and
defences, experimental study and challenges [10.177219272933781]
Federated learning is a machine learning paradigm that emerges as a solution to the privacy-preservation demands in artificial intelligence.
As machine learning, federated learning is threatened by adversarial attacks against the integrity of the learning model and the privacy of data via a distributed approach to tackle local and global learning.
arXiv Detail & Related papers (2022-01-20T12:23:03Z) - Adversarial Robustness of Deep Reinforcement Learning based Dynamic
Recommender Systems [50.758281304737444]
We propose to explore adversarial examples and attack detection on reinforcement learning-based interactive recommendation systems.
We first craft different types of adversarial examples by adding perturbations to the input and intervening on the casual factors.
Then, we augment recommendation systems by detecting potential attacks with a deep learning-based classifier based on the crafted data.
arXiv Detail & Related papers (2021-12-02T04:12:24Z) - Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial
Robustness [53.094682754683255]
We propose a Model-Agnostic Meta-Attack (MAMA) approach to discover stronger attack algorithms automatically.
Our method learns the in adversarial attacks parameterized by a recurrent neural network.
We develop a model-agnostic training algorithm to improve the ability of the learned when attacking unseen defenses.
arXiv Detail & Related papers (2021-10-13T13:54:24Z)
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.