End-to-End Anti-Backdoor Learning on Images and Time Series

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jiang, Yujing, Ma, Xingjun, Erfani, Sarah Monazam, Li, Yige, Bailey, James
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914632041496576
author Jiang, Yujing
Ma, Xingjun
Erfani, Sarah Monazam
Li, Yige
Bailey, James
author_facet Jiang, Yujing
Ma, Xingjun
Erfani, Sarah Monazam
Li, Yige
Bailey, James
contents Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security. These attacks manipulate model behavior by embedding a hidden trigger during the training phase, allowing unauthorized control over the model's output during inference time. Although numerous defenses exist for image classification models, there is a conspicuous absence of defenses tailored for time series data, as well as an end-to-end solution capable of training clean models on poisoned data. To address this gap, this paper builds upon Anti-Backdoor Learning (ABL) and introduces an innovative method, End-to-End Anti-Backdoor Learning (E2ABL), for robust training against backdoor attacks. Unlike the original ABL, which employs a two-stage training procedure, E2ABL accomplishes end-to-end training through an additional classification head linked to the shallow layers of a Deep Neural Network (DNN). This secondary head actively identifies potential backdoor triggers, allowing the model to dynamically cleanse these samples and their corresponding labels during training. Our experiments reveal that E2ABL significantly improves on existing defenses and is effective against a broad range of backdoor attacks in both image and time series domains.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03215
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle End-to-End Anti-Backdoor Learning on Images and Time Series
Jiang, Yujing
Ma, Xingjun
Erfani, Sarah Monazam
Li, Yige
Bailey, James
Machine Learning
Cryptography and Security
Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security. These attacks manipulate model behavior by embedding a hidden trigger during the training phase, allowing unauthorized control over the model's output during inference time. Although numerous defenses exist for image classification models, there is a conspicuous absence of defenses tailored for time series data, as well as an end-to-end solution capable of training clean models on poisoned data. To address this gap, this paper builds upon Anti-Backdoor Learning (ABL) and introduces an innovative method, End-to-End Anti-Backdoor Learning (E2ABL), for robust training against backdoor attacks. Unlike the original ABL, which employs a two-stage training procedure, E2ABL accomplishes end-to-end training through an additional classification head linked to the shallow layers of a Deep Neural Network (DNN). This secondary head actively identifies potential backdoor triggers, allowing the model to dynamically cleanse these samples and their corresponding labels during training. Our experiments reveal that E2ABL significantly improves on existing defenses and is effective against a broad range of backdoor attacks in both image and time series domains.
title End-to-End Anti-Backdoor Learning on Images and Time Series
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2401.03215