Classification Auto-Encoder based Detector against Diverse Data Poisoning Attacks
arXiv:2108.04206
Abstract
Poisoning attacks are a category of adversarial machine learning threats in which an adversary attempts to subvert the outcome of the machine learning systems by injecting crafted data into training data set, thus increasing the machine learning model's test error. The adversary can tamper with the data feature space, data labels, or both, each leading to a different attack strategy with different strengths. Various detection approaches have recently emerged, each focusing on one attack strategy. The Achilles heel of many of these detection approaches is their dependence on having access to a clean, untampered data set. In this paper, we propose CAE, a Classification Auto-Encoder based detector against diverse poisoned data. CAE can detect all forms of poisoning attacks using a combination of reconstruction and classification errors without having any prior knowledge of the attack strategy. We show that an enhanced version of CAE (called CAE+) does not have to employ a clean data set to train the defense model. Our experimental results on three real datasets MNIST, Fashion-MNIST and CIFAR demonstrate that our proposed method can maintain its functionality under up to 30% contaminated data and help the defended SVM classifier to regain its best accuracy.
arXiv commentThis work has been submitted to the IEEE for possible publication
References in corpus (10)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Poisoning Attacks against Support Vector Machines
- Is feature selection secure against training data poisoning?
- Support Vector Machines under Adversarial Label Contamination
- MagNet: a Two-Pronged Defense against Adversarial Examples
- Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
- Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
- Stronger Data Poisoning Attacks Break Data Sanitization Defenses
- Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations
- Curie: A method for protecting SVM Classifier from Poisoning Attack