Poisoning Attacks with Generative Adversarial Nets

Abstract

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-level optimization problem. Solving these problems is computationally demanding and has limited applicability for some models such as deep networks. In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers generating adversarial training examples, i.e. samples that look like genuine data points but that degrade the classifier's accuracy when used for training. We propose a Generative Adversarial Net with three components: generator, discriminator, and the target classifier. This approach allows us to model naturally the detectability constrains that can be expected in realistic attacks and to identify the regions of the underlying data distribution that can be more vulnerable to data poisoning. Our experimental evaluation shows the effectiveness of our attack to compromise machine learning classifiers, including deep networks.

References in corpus (11)

• Conditional Generative Adversarial Nets
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Understanding Black-box Predictions via Influence Functions
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Poisoning Attacks against Support Vector Machines
• Is feature selection secure against training data poisoning?
• Generating Adversarial Examples with Adversarial Networks
• Generative Poisoning Attack Method Against Neural Networks
• Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
• Stronger Data Poisoning Attacks Break Data Sanitization Defenses
• Security Analysis of Online Centroid Anomaly Detection

Cited by in corpus (9)

• Security and Privacy Issues in Deep Learning
• Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
• Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective
• Regularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation
• Model-Targeted Poisoning Attacks with Provable Convergence
• Disrupting Model Training with Adversarial Shortcuts
• Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters
• De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks
• FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection