적대적 공격을 방어하기 위한 StarGAN 기반의 탐지 및 정화 연구
StarGAN-Based Detection and Purification Studies to Defend against Adversarial Attacks
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
인공지능은 빅데이터와 딥러닝 기술을 이용해 다양한 분야에서 삶의 편리함을 주고 있다. 하지만, 딥러닝 기술은 적대적 예제에 매우 취약하여 적대적 예제가 분류 모델의 오분류를 유도한다. 본 연구는 StarGAN을 활용해 다양한 적대적 공격을 탐지 및 정화하는 방법을 제안한다. 제안 방법은 Categorical Entropy loss를 추가한 StarGAN 모델에 다양한 공격 방법으로 생성된 적대적 예제를 학습시켜 판별자는 적대적 예제를 탐지하고, 생성자는 적대적 예제를 정화한다. CIFAR-10 데이터셋을 통해 실험한 결과 평균 탐지 성능은 약 68.77%, 평균 정화 성능은 약 72.20%를 보였으며 정화 및 탐지 성능으로 도출되는 평균 방어 성능은 약 93.11%를 보였다.
Abstract
Artificial Intelligence is providing convenience in various fields using big data and deep learning technologies. However, deep learning technology is highly vulnerable to adversarial examples, which can cause misclassification of classification models. This study proposes a method to detect and purification various adversarial attacks using StarGAN. The proposed method trains a StarGAN model with added Categorical Entropy loss using adversarial examples generated by various attack methods to enable the Discriminator to detect adversarial examples and the Generator to purification them. Experimental results using the CIFAR-10 dataset showed an average detection performance of approximately 68.77%, an average purification performance of approximately 72.20%, and an average defense performance of approximately 93.11% derived from restoration and detection performance.
참고문헌 (22)
- G. Ryu, "A ResearchTrends in Artificial Intelligence SecurityAttacks and Countermeasures", Review of KIISC, 30(5), pp.93~99 (2020)
- SZE, Vivienne, "Efficient processing of deep neural networks: A tutorial and survey", Proceedings of the IEEE (2017)
- Goodfellow, Ian, "Generative adversarial networks", Communications of the ACM, 63(11), pp.139~144 (2020)
- Liao, Fangzhou, "Defense against adversarial attacks using high-level representation guided denoiser", Proceedings of the IEEE conference on computer vision and pattern recognition (2018)
- Akhtar, Naveed, "Threat of adversarial attacks on deep learning in computer vision: A survey", Ieee Access, 6, pp.14410~14430 (2018)
- Goodfellow, Ian J., "Explaining and harnessing adversarial examples", and Christian Szegedy. "Explaining and harnessing adversarial examples. "arXiv preprint arXiv : (2014)
- Kurakin, Alexey, "Artificial intelligence safety and security", pp.2018, Chapman and Hall
- Madry, Aleksander, "Towards deep learning models resistant to adversarial attacks" (2017)
- Carlini, Nicholas, "Towards evaluating the robustness of neural networks", 2017 ieee symposium on security and privacy(sp) (2017), Ieee
- Moosavi-Dezfooli, "Deepfool : a simple and accurate method to fool deep neural networks", Proceedings of the IEEE conference on computer vision and pattern recognition (2016)
- Dong, Yinpeng, "Boosting adversarial attacks with momentum", Proceedings of the IEEE conference on computer vision and pattern recognition (2018)
- Meng, Dongyu, "Magnet: a two-pronged defense against adversarial examples", Proceedings of the 2017 ACM SIGSAC conference on computer and communications security (2017)
- Freitas, Scott, "Unmask : Adversarial detection and defense through robust feature alignment", 2020 IEEE International Conference on Big Data(Big Data) (2020), IEEE
- Samangouei, Pouya, "Defense-gan: Protecting classifiers against adversarial attacks using generative models" (2018)
- Choi, Yunjey, "Stargan : Unified generative adversarial networks for multi-domain image-to-image translation", Proceedings of the IEEE conference on computer vision and pattern recognition (2018)
- Ronneberger, Olaf, "U-net: Convolutional networks for biomedical image segmentation", Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference (2015), Springer International Publishing
- Ryu, Gwonsang, "Feature-based adversarial training for deep learning models resistant to transferable adversarial examples", IEICE TRANSACTIONS on Information and Systems, 105(5), pp.1039~1049 (2022)
- Ryu, Gwonsang, "A hybrid adversarial training for deep learning model and denoising network resistant to adversarial examples", Applied Intelligence, pp.1~14 (2022)
- Zhang, Hongyang, "Theoretically principled trade-off between robustness and accuracy", International conference on machine learning. PMLR (2019)
- Xu, Weilin, "Feature squeezing: Detecting adversarial examples in deep neural networks" (2017)
- Ma, Shiqing, "Nic: Detecting adversarial samples with neural network invariant checking", Annual Network And Distributed System Security Symposium (NDSS 2019) (2019), Internet Soc
- Ye, Dengpan, "Detection defense against adversarial attacks with saliency map", International Journal of Intelligent Systems, 37(12), pp.10193~10210 (2022)