CanSecWest 2019 | 如何用AI“欺骗”AI？

Zhou, W., Hou, X., Chen, Y., Tang, M., Huang, X., Gan, X., & Yang, Y. (2018). Transferable Adversarial Perturbations. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 452-467).

https://console.aws.amazon.com/rekognition/home?region=us-east-1#/celebrity-detection

https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/

Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (pp. 91-99).

https://cloud.google.com/vision/

Papernot, N., McDaniel, P., Wu, X., Jha, S., & Swami, A. (2016, May). Distillation as a defense to adversarial perturbations against deep neural networks. In 2016 IEEE Symposium on Security and Privacy (SP) (pp. 582-597). IEEE.

【本文为51CTO专栏作者“腾讯技术工程”原创稿件，转载请联系原作者（微信号：Tencent_TEG）】

戳这里，看该作者更多好文

【编辑推荐】

1. 容器赋能AI-人工智能在360私有云容器服务上的实践
2. 浅显易懂！「高中数学」读懂梯度下降的数学原理
3. 采购AI/ML安全工具前要先回答这11个问题
4. 如何做一枚合格的数据产品经理
5. 基于物理的渲染（PBR）白皮书 | 迪士尼原则的BRDF与BSDF相关总结

（编辑：网站开发网_马鞍山站长网）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!