skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 5:00 PM ET until 11:00 PM ET on Friday, June 21 due to maintenance. We apologize for the inconvenience.


Title: Efficient Adversarial Training With Transferable Adversarial Examples
Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can re- quire orders of magnitude additional training time due to high cost of generating strong adversarial examples dur- ing training. In this paper, we first show that there is high transferability between models from neighboring epochs in the same training process, i.e., adversarial examples from one epoch continue to be adversarial in subsequent epochs. Leveraging this property, we propose a novel method, Adversarial Training with Transferable Adversarial Examples (ATTA), that can enhance the robustness of trained models and greatly improve the training efficiency by accumulating adversarial perturbations through epochs. Compared to state-of-the-art adversarial training methods, ATTA enhances adversarial accuracy by up to 7.2% on CIFAR10 and requires 12 ∼ 14× less training time on MNIST and CIFAR10 datasets with comparable model robustness.  more » « less
Award ID(s):
1646392
NSF-PAR ID:
10205623
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Page Range / eLocation ID:
1178 to 1187
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Machine learning (ML) models have shown promise in classifying raw executable files (binaries) as malicious or benign with high accuracy. This has led to the increasing influence of ML-based classification methods in academic and real-world malware detection, a critical tool in cybersecurity. However, previous work provoked caution by creating variants of malicious binaries, referred to as adversarial examples, that are transformed in a functionality-preserving way to evade detection. In this work, we investigate the effectiveness of using adversarial training methods to create malware-classification models that are more robust to some state-of-the-art attacks. To train our most robust models, we significantly increase the efficiency and scale of creating adversarial examples to make adversarial training practical, which has not been done before in raw-binary malware detectors. We then analyze the effects of varying the length of adversarial training, as well as analyze the effects of training with various types of attacks. We find that data augmentation does not deter state-of-the-art attacks, but that using a generic gradient-guided method, used in other discrete domains, does improve robustness. We also show that in most cases, models can be made more robust to malware-domain attacks by adversarially training them with lower-effort versions of the same attack. In the best case, we reduce one state-of-the-art attack’s success rate from 90% to 5%. We also find that training with some types of attacks can increase robustness to other types of attacks. Finally, we discuss insights gained from our results, and how they can be used to more effectively train robust malware detectors. 
    more » « less
  2. Machine learning (ML) models have shown promise in classifying raw executable files (binaries) as malicious or benign with high accuracy. This has led to the increasing influence of ML-based classification methods in academic and real-world malware detection, a critical tool in cybersecurity. However, previous work provoked caution by creating variants of malicious binaries, referred to as adversarial examples, that are transformed in a functionality-preserving way to evade detection. In this work, we investigate the effectiveness of using adversarial training methods to create malware-classification models that are more robust to some state-of-the-art attacks. To train our most robust models, we significantly increase the efficiency and scale of creating adversarial examples to make adversarial training practical, which has not been done before in raw-binary malware detectors. We then analyze the effects of varying the length of adversarial training, as well as analyze the effects of training with various types of attacks. We find that data augmentation does not deter state-of-the-art attacks, but that using a generic gradient-guided method, used in other discrete domains, does improve robustness. We also show that in most cases, models can be made more robust to malware-domain attacks by adversarially training them with lower-effort versions of the same attack. In the best case, we reduce one state-of-the-art attack’s success rate from 90% to 5%. We also find that training with some types of attacks can increase robustness to other types of attacks. Finally, we discuss insights gained from our results, and how they can be used to more effectively train robust malware detectors. 
    more » « less
  3. Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small Linf-noise). For other perturbations, these defenses offer no guarantees and, at times, even increase the model’s vulnerability. Our aim is to understand the reasons underlying this robustness trade-off, and to train models that are simultaneously robust to multiple perturbation types. We prove that a trade-off in robustness to different types of Lp-bounded and spatial perturbations must exist in a natural and simple statistical setting. We corroborate our formal analysis by demonstrating similar robustness trade-offs on MNIST and CIFAR10. Building upon new multi-perturbation adversarial training schemes, and a novel efficient attack for finding L1-bounded adversarial examples, we show that no model trained against multiple attacks achieves robustness competitive with that of models trained on each attack individually. In particular, we uncover a pernicious gradient-masking phenomenon on MNIST, which causes adversarial training with first-order Linf, L1 and L2 adversaries to achieve merely 50% accuracy. Our results question the viability and computational scalability of extending adversarial robustness, and adversarial training, to multiple perturbation types. 
    more » « less
  4. Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small ℓ∞-noise). For other perturbations, these defenses offer no guarantees and, at times, even increase the model’s vulnerability. Our aim is to understand the reasons underlying this robustness trade-off, and to train models that are simultaneously robust to multiple perturbation types. We prove that a trade-off in robustness to different types of ℓp-bounded and spatial perturbations must exist in a natural and simple statistical setting. We corroborate our formal analysis by demonstrating similar robustness trade-offs on MNIST and CIFAR10. We propose new multi-perturbation adversarial training schemes, as well as an efficient attack for the ℓ1-norm, and use these to show that models trained against multiple attacks fail to achieve robustness competitive with that of models trained on each attack individually. In particular, we find that adversarial training with first-order ℓ∞, ℓ1 and ℓ2 attacks on MNIST achieves merely 50% robust accuracy, partly because of gradient-masking. Finally, we propose affine attacks that linearly interpolate between perturbation types and further degrade the accuracy of adversarially trained models. 
    more » « less
  5. Several recent works have developed methods for training classifiers that are certifiably robust against norm-bounded adversarial perturbations. However, these methods assume that all the adversarial transformations provide equal value for adversaries, which is seldom the case in real-world applications. We advocate for cost-sensitive robustness as the criteria for measuring the classifier's performance for specific tasks. We encode the potential harm of different adversarial transformations in a cost matrix, and propose a general objective function to adapt the robust training method of Wong & Kolter (2018) to optimize for cost-sensitive robustness. Our experiments on simple MNIST and CIFAR10 models and a variety of cost matrices show that the proposed approach can produce models with substantially reduced cost-sensitive robust error, while maintaining classification accuracy. 
    more » « less