1. 毕业设计（论文）的内容和要求

主要内容： 基于python设计一个用于分析人工神经网络鲁棒性的fuzz工具。

此工具通过优化的生成算法和覆盖值算法，可以快速浏览数据集并在短时间内生成指定数量的对抗样本，以用于对模型的分析和评价。

该工具主要由模型采集部分与模糊测试部分组成。

2. 参考文献

[1]周志华.机器学习 [M].北京：清华大学出版社，2016 [2]李航.统计学习方法[M]. 北京：清华大学出版社，2012 [3] Philip Hingston. A Turing test for computer game bots[J]. IEEE Transactions on Computational Intelligence and AI in Games. 2009, (3):169#8211;186. [4] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition[A]. In Proceedings of the IEEE conference on computer vision and pattern recognition[C]. IEEE Press, 2016, 770#8211;778. [5] Wicker M , Huang X , Kwiatkowska M . Feature-Guided Black-Box Safety Testing of Deep Neural Networks[A]. International Conference on Tools and Algorithms for the Construction and Analysis of Systems[C]. Springer, Cham, 2018, 50-78. [6] Moritz Helmstaedter, Kevin L Briggman, Srinivas C Turaga, Viren Jain, H Sebastian Seung, and Winfried Denk. Connectomic reconstruction of the inner plexiform layer in the mouse retina[J]. Nature 500, 2013, 7461 (2013), 168-169. [7] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael S. Bernstein, Alexander C. Berg, and Fei Fei Li. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3):211#8211;252. [8] Yann LeCun, L#233;on Bottou, Yoshua Bengio, and Patrick Haffner. Gradient based learning applied to document recognition[J]. Proc. IEEE 86, 1998，11 (1998), 2278#8211;2324. [9] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems[M].MIT Press,2012. [10] Jie Liang, Mingzhe Wang, Yuanliang Chen, Yu Jiang, and Renwei Zhang. Fuzz testing in practice: Obstacles and solutions[A]. In 2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER)[C].IEEE Press,2018,562#8211;566. [11] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. Human-level control through deep reinforcement learning[J].Nature 518, 2015, 7540 (2015), 529-530. [12] Micha#322; Kempka, Marek Wydmuch, Grzegorz Runc, Jakub Toczek, and Wojciech Jaskowski. Vizdoom: A Doom-based AI research platform for visual reinforcement learning[A]. In Computational Intelligence and Games (CIG), 2016 IEEE Conference on[C]. IEEE Press,2016,1-8. [13] Santiago Ontan#243;n, Gabriel Synnaeve, Alberto Uriarte, Florian Richoux, David Churchill, and Mike Preuss. A survey of real-time strategy game AI research and competition in StarCraft[J]. IEEE Transactions on Computational Intelligence and AI in games, 2013, 5(4):293#8211;311.

[14] Peter Harrington.机器学习实战[M].北京：人民邮电出版社，2013

[15] Ian Goodfellow.深度学习[M]. 北京：人民邮电出版社，2017

3. 毕业设计（论文）进程安排

起讫日期 设计（论文）各阶段工作内容 备 注 2018-12-25～2018-12-30 选题,初步了解毕业设计内容 2018-12-31～2019-1-12 查阅文献及资料，熟悉毕业设计内容 2019-1-13～2019-3-2 完成开题报告，熟悉Python及框架 2019-3-3～2019-4-5 完成本地模型训练与节点采集 2019-4-6～2019-5-10 完成模糊测试部分 2019-5-11～2019-5-24 撰写毕业论文，提交论文初稿 2019-5-25～2019-6-5 修正、打印装订、提交论文 2019-6-6～2019-6-11 评审、准备答辩，完成答辩PPT 2019-6-12～2019-6-14 论文答辩、归档