Anti-Backdoor Learning: Training Clean Models on Poisoned Data

10/22/2021
by   Yige Li, et al.
0

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training methods can be devised to prevent the backdoor triggers being injected into the trained model in the first place. In this paper, we introduce the concept of anti-backdoor learning, aiming to train clean models given backdoor-poisoned data. We frame the overall learning process as a dual-task of learning the clean and the backdoor portions of data. From this view, we identify two inherent characteristics of backdoor attacks as their weaknesses: 1) the models learn backdoored data much faster than learning with clean data, and the stronger the attack the faster the model converges on backdoored data; 2) the backdoor task is tied to a specific class (the backdoor target class). Based on these two weaknesses, we propose a general learning scheme, Anti-Backdoor Learning (ABL), to automatically prevent backdoor attacks during training. ABL introduces a two-stage gradient ascent mechanism for standard training to 1) help isolate backdoor examples at an early training stage, and 2) break the correlation between backdoor examples and the target class at a later training stage. Through extensive experiments on multiple benchmark datasets against 10 state-of-the-art attacks, we empirically show that ABL-trained models on backdoor-poisoned data achieve the same performance as they were trained on purely clean data. Code is available at <https://github.com/bboylyg/ABL>.

READ FULL TEXT

page 17

page 21

research
03/13/2023

Backdoor Defense via Deconfounded Representation Learning

Deep neural networks (DNNs) are recently shown to be vulnerable to backd...
research
03/23/2023

Backdoor Defense via Adaptively Splitting Poisoned Dataset

Backdoor defenses have been studied to alleviate the threat of deep neur...
research
05/24/2023

Reconstructive Neuron Pruning for Backdoor Defense

Deep neural networks (DNNs) have been found to be vulnerable to backdoor...
research
04/22/2021

SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics

Modern machine learning increasingly requires training on a large collec...
research
06/13/2023

DHBE: Data-free Holistic Backdoor Erasing in Deep Neural Networks via Restricted Adversarial Distillation

Backdoor attacks have emerged as an urgent threat to Deep Neural Network...
research
08/08/2023

XGBD: Explanation-Guided Graph Backdoor Detection

Backdoor attacks pose a significant security risk to graph learning mode...
research
04/01/2020

MetaPoison: Practical General-purpose Clean-label Data Poisoning

Data poisoning–the process by which an attacker takes control of a model...

Please sign up or login with your details

Forgot password? Click here to reset