Tian Yu Liu

Tian Yu Liu, Yu Yang, Baharan Mirzasoleiman

A powerful category of (invisible) data poisoning attacks modify a subset of training examples by small adversarial perturbations to change the prediction of certain test-time data. Existing defense mechanisms are not desirable to deploy in practice, as they often either drastically harm the generalization performance, or are attack-specific, and prohibitively slow to apply. Here, we propose a simple but highly effective approach that unlike existing methods breaks various types of invisible poisoning attacks with the slightest drop in the generalization performance. We make the key observation that attacks introduce local sharp regions of high training loss, which when minimized, results in learning the adversarial perturbations and makes the attack successful. To break poisoning attacks, our key idea is to alleviate the sharp loss regions introduced by poisons. To do so, our approach comprises two components: an optimized friendly noise that is generated to maximally perturb examples without degrading the performance, and a randomly varying noise component. The combination of both components builds a very light-weight but extremely effective defense against the most powerful triggerless targeted and hidden-trigger backdoor poisoning attacks, including Gradient Matching, Bulls-eye Polytope, and Sleeper Agent. We show that our friendly noise is transferable to other architectures, and adaptive attacks cannot break our defense due to its random noise component. Our code is available at: https://github.com/tianyu139/friendly-noise

Yu Yang, Tian Yu Liu, Baharan Mirzasoleiman

Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data. Existing defenses are often effective only against a specific type of targeted attack, significantly degrade the generalization performance, or are prohibitive for standard deep learning pipelines. In this work, we propose an efficient defense mechanism that significantly reduces the success rate of various data poisoning attacks, and provides theoretical guarantees for the performance of the model. Targeted attacks work by adding bounded perturbations to a randomly selected subset of training data to match the targets' gradient or representation. We show that: (i) under bounded perturbations, only a number of poisons can be optimized to have a gradient that is close enough to that of the target and make the attack successful; (ii) such effective poisons move away from their original class and get isolated in the gradient space; (iii) dropping examples in low-density gradient regions during training can successfully eliminate the effective poisons, and guarantees similar training dynamics to that of training on full data. Our extensive experiments show that our method significantly decreases the success rate of state-of-the-art targeted attacks, including Gradient Matching and Bullseye Polytope, and easily scales to large datasets.