데이터 예측 클래스 기반 적대적 공격 탐지 및 분류 모델
Adversarial Example Detection and Classification Model Based on the Class Predicted by Deep Learning Model
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
딥러닝 분류 모델에 대한 공격 중 하나인 적대적 공격은 입력 데이터에 인간이 구별할 수 없는 섭동을 추가하여 딥러닝 분류 모델이 잘못 분류하도록 만드는 공격이며, 다양한 적대적 공격 알고리즘이 존재한다. 이에 따라 적대적 데이터를 탐지하는 연구는 많이 진행되었으나 적대적 데이터가 어떤 적대적 공격 알고리즘에 의해 생성되었는지 분류하는 연구는 매우 적게 진행되었다. 적대적 공격을 분류할 수 있다면, 공격 간의 차이를 분석하여 더욱 견고한 딥러닝 분류 모델을 구축할 수 있을 것이다. 본 논문에서는 공격 대상 딥러닝 모델이 예측하는 클래스를 기반으로 은닉층의 출력값에서 특징을 추출하고 추출된 특징을 입력으로 하는 랜덤 포레스트 분류 모델을 구축하여 적대적 공격을 탐지 및 분류하는 모델을 제안한다. 실험 결과 제안한 모델은 최신의 적대적 공격 탐지 및 분류 모델보다 정상 데이터의 경우 3.02%, 적대적 데이터의 경우 0.80% 높은 정확도를 보였으며, 기존 연구에서 분류하지 않았던 새로운 공격을 분류한다.
Abstract
Adversarial attack, one of the attacks on deep learning classification model, is attack that add indistinguishable perturbations to input data and cause deep learning classification model to misclassify the input data. There are various adversarial attack algorithms. Accordingly, many studies have been conducted to detect adversarial attack but few studies have been conducted to classify what adversarial attack algorithms to generate adversarial input. if adversarial attacks can be classified, more robust deep learning classification model can be established by analyzing differences between attacks. In this paper, we proposed a model that detects and classifies adversarial attacks by constructing a random forest classification model with input features extracted from a target deep learning model. In feature extraction, feature is extracted from a output value of hidden layer based on class predicted by the target deep learning model. Through Experiments the model proposed has shown 3.02% accuracy on clean data, 0.80% accuracy on adversarial data higher than the result of pre-existing studies and classify new adversarial attack that was not classified in pre-existing studies.
참고문헌 (21)
- H. Caesar, "nuScenes: A multimodal dataset for autonomous driving", Proceedings of the IEEE, 2020, 11621~11631
- G. Litjens, "A survey on deep learning in medical image analysis", Medical Image Analysis, 42, pp.60~88 (2017)
- Ian J. Goodfellow, "Explaining and Harnessing Adversarial Examples", arXiv preprint arXiv: 1412.6572v3, ~ (2015)
- A. Madry, "Towards Deep Learning Models Resistant to Adversarial Attacks", arXiv preprint arXiv:1706.06083v4, ~ (2019)
- N. Papernot, "The Limitations of Deep Learning in Adversarial Settings", IEEE European Symposium on Security and Privacy (EuroS&P), pp.372~387 (2016)
- S.M. Moosavi-Dezfooli, "DeepFool: a simple and accurate method to fool deep neural networks", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2574~2582 (2016)
- N. Carlini, "Towards Evaluating the Robustness of Neural Networks", IEEE Symposium on Security and Privacy, pp.39~57 (2017)
- F. Croce, "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks", Proceedings of the 37th International Conference on Machine Learning (PMLR), 119, pp.2206~2216 (2020)
- F. Tramèr, "Ensemble Adversarial Training: Attacks and Defenses", arXiv preprint arXiv: 1705.07204v5, ~ (2020)
- A. Shafahi, "Adversarial Training for Free!", Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp.3358~3369 (2019)
- A. Prakash, "Deflecting adversarial attacks with pixel deflection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.8571~8580 (2018)
- N. Papernot, "Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks", IEEE Symposium on Security and Privacy, pp.582~597 (2016)
- A. Aldahdooh, "Adversarial Example Detection for DNN Models: A Review", arXiv preprint arXiv:2105.00203v2, ~ (2021)
- X. Li, "Adversarial examples detection in deep networks with convolutional filter statistics", Proceedings of the IEEE International Conference on Computer Vision (ICCV),, pp.5764~5772 (2017)
- HF. Eniser, "RAID: Randomized adversarial-input detection for neural networks", arXiv preprint arXiv:2002.02776v1, ~ (2020)
- S. Pertigkiozoglou, "Detecting Adversarial Examples in Convolutional Neural Networks", arXiv preprint arXiv: 1812.03303v1, ~ (2018)
- J. Lu, "SafetyNet: Detecting and Rejecting Adversarial Examples Robustly", Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp.446~454 (2017)
- F. Carrara, "Detecting adversarꠓial example attacks to deep neural networks", Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing, pp.1~7 (2017)
- W. Xu, "Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks", arXiv preprint arXiv: 1704.01155v2, ~ (2017)
- N. Manohar-Alers, "Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples", arXiv preprint arXiv:2107.00561v1, ~ (2021)
- S. Zagoruyko, "Wide Residual Networks", arXiv preprint arXiv: 1605.07146v4, ~ (2017)