Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from teacher to student during knowledge distillation. We find that a large amount of robustness may be inherited by the student even when distilled on only clean images. Second, we introduce Adversarially Robust Distillation (ARD) for distilling robustness onto student networks. In addition to producing small models with high test accuracy like conventional distillation, ARD also passes the superior robustness of large networks onto the student. In our experiments, we find that ARD student models decisively outperform adversarially trained networks of identical architecture in terms of robust accuracy, surpassing state-of-the-art methods on standard robustness benchmarks. Finally, we adapt recent fast adversarial training methods to ARD for accelerated robust distillation.

Data poisoning and backdoor attacks manipulate victim models by maliciously modifying training data. In light of this growing threat, a recent survey of industry professionals revealed heightened fear in the private sector regarding data poisoning. Many previous defenses against poisoning either fail in the face of increasingly strong attacks, or they significantly degrade performance. However, we find that strong data augmentations, such as mixup and CutMix, can significantly diminish the threat of poisoning and backdoor attacks without trading off performance. We further verify the effectiveness of this simple defense against adaptive poisoning methods, and we compare to baselines including the popular differentially private SGD (DP-SGD) defense. In the context of backdoors, CutMix greatly mitigates the attack while simultaneously increasing validation accuracy by 9%.

No abstract

No abstract

Data Poisoning attacks involve an attacker modifying training data to maliciously control a model trained on this data. Previous poisoning attacks against deep neural networks have been limited in scope and success, working only in simplified settings or being prohibitively expensive for large datasets. In this work, we focus on a particularly malicious poisoning attack that is both "from scratch" and "clean label", meaning we analyze an attack that successfully works against new, randomly initialized models, and is nearly imperceptible to humans, all while perturbing only a small fraction of the training data. The central mechanism of this attack is matching the gradient direction of malicious examples. We analyze why this works, supplement with practical considerations. and show its threat to realworld practitioners, finding that it is the first poisoning method to cause targeted misclassification in modern deep networks trained from scratch on a full-sized, poisoned ImageNet dataset. Finally we demonstrate the limitations of existing defensive strategies against such an attack, concluding that data poisoning is a credible threat, even for large-scale deep learning systems.