
叶傲霜,男,1992年1月生,讲师,工学博士,硕士生导师。2022年12月毕业于武汉大学国家网络安全学院,获工学博士学位;2018年3月毕业于日本北陆先端科学技术大学院大学情报工学研究科,获信息科学硕士学位。发表论文20余篇,引用300余次,担任TASLP、NN、IST、MM、ICME等多个CCF推荐期刊与会议审稿人,CASA、BDDM等国际会议程序委员与分会主席。
邮箱:asye@wtu.edu.cn
1. 主要研究方向
AI安全、软件安全
2. 教学、科研项目
1) 湖北省自然科学基金青年项目(B类),2025.03-2027.02,主持
2) 湖北省教育厅科学研究青年人才项目,2024.10-2025.12,主持
3) 先进密码技术与系统安全四川省重点实验室开放课题,2023.11-2025.12,主持
4) 武汉纺织大学校基金培育A类,2025.05-2027.05,主持
5) 武汉纺织大学博士科研启动基金,2023.05-2026.05,主持
6) ********漏洞利用方法,2024.11-2025.11,参与(武汉大学主持)
7) 国家自然科学基金面上项目, 2025.01-2028.12, 参与
8) 十三五国家重点研发计划项目“网络空间安全”重点专项, 2016.12-2020.12, 参与
3. 论文与专利
[1] Ye A, Zhang S, Yan R, Ke J, Zhu F, Tang B. CtrlFuzz: A controllable diffusion-based fuzz testing for deep neural networks via coverage-aware manifold guidance[J]. Information and Software Technology, 2025, 187: 107856.(CCF-B/中科院二区期刊)
[2] Ye A, Zhang S, Tang B, Ke J, Zhao Y, Peng T. DeFinder: Error-sensitive testing of deep neural networks via vulnerability interpretation[J]. Journal of Network and Computer Applications, 2025, 241: 104212.(中科院二区期刊)
[3] Tang B, Zhang S, Zhu F, Ye A*. CAPRA: Context-aware patch risk assessment for detecting immature vulnerability in open-source software[J]. Computers & Security, 2025, 157: 104540.(通讯作者,CCF-B/中科院二区期刊)
[4] Yan R, Tang B, Ke J, Ren W, Ye A*. PRISM: Fusing prediction-inference evidence for test selection in deep neural networks[C]//The 28th International Conference on Information and Communications Security, 2026.(通讯作者,CCF-C类会议)
[5] Zhang S, Tang B, Ke J, Ye A*, Zhao Y, Zhao L*. SCOUT: Structural coverage-guided diffusion for testing deep classifiers[C]//The 28th International Conference on Information and Communications Security, 2026.(通讯作者,CCF-C类会议)
[6] Ke J, Liu Y, Tian C, Wang W, Ye A*. ColorFool: Three color elements to fool deepfake detectors[C]//The 28th International Conference on Information and Communications Security, 2026.(通讯作者,CCF-C类会议)
[7] Ye A, Wang L, Zhao L, Ke J. Ex^2: Monte Carlo Tree Search based test inputs prioritization for fuzzing deep neural networks[J]. International Journal of Intelligent Systems, 2022.(CCF-C/中科院二区期刊)
[8] Ye A, Wang L, Zhao L, Wang W, Ke J, Liu Q. RapidFuzz: Accelerating fuzzing via generative adversarial networks[J]. Neurocomputing, 2021, 460: 195-204.(CCF-C/中科院二区期刊)
[9] Ye A, Wang L, Zhao L, Ke J. DANCe: Dynamic adaptive neuron coverage for fuzzing deep neural networks[C]//International Joint Conference on Neural Networks, 2022.(CCF-C类会议)
[10] Wang W, Wang R, Wang L, Wang Z, Ye A. Towards a robust deep neural network against adversarial texts: A survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2023.(CCF A/中科院一区期刊)
[11] Wang W, Wang L, Wang R, Ye A, Ke J. Better constraints of imperceptibility, better adversarial examples in the text[J]. International Journal of Intelligent Systems, 2021.(CCF-C/中科院二区期刊)
[12] Wang L, Yang K, Wang W, Wang R, Ye A. MGAAttack: Toward more query-efficient black-box attack by microbial genetic algorithm[C]//ACM Multimedia, 2020: 2592-2600.(CCF-A类会议)
[13] Wang W, Wang L, Yang K, Ye A, Wang R, Ke J. Omni-detection of adversarial examples with diverse magnitudes[J]. China Communications, 2021, 18(7): 103-118.(中科院三区期刊)
[14] Luo Z, Wang L, Wang W, Ye A. Annealing attention networks for user feature-based rumor early detection on Weibo[C]//International Joint Conference on Neural Networks, 2021.(CCF-C类会议)
[15] Ke J, Wang L, Ye A, Fu J. Combating multi-level adversarial text with pruning based adversarial training[C]//International Joint Conference on Neural Networks, 2022.(CCF-C类会议)
专利:
[1]基于多粒度组件级覆盖的深度神经网络模糊测试方法,202610559343.4 (实质审查)
[2]一种基于蒙特卡洛搜索树种子调度的深度学习模糊测试方法,ZL202110946922.1
[3]一种基于三元特征的深度注意力谣言鉴别方法及装置,ZL201911074952.7
[4]一种基于用户特征的退火注意力谣言鉴别方法及装置,ZL202110389173.7
[5]一种基于微生物遗传算法的黑盒对抗样本生成方法,ZL202010585924.8
4.个人荣誉和指导学生获奖
指导学生:
[1] 2026年,美国大学生数学建模竞赛,省奖
[2] 2026年,睿抗机器人开发者大赛(RAICOM),省一等奖
[3] 2026年,睿抗机器人开发者大赛(RAICOM),省一等奖
[4] 2025年,全球校园人工智能算法精英大赛,国家三等奖
[5] 2025年,全球校园人工智能算法精英大赛,省二等奖
[6] 2025年,“华数杯”全国大学生数学建模竞赛,国家一等奖
个人荣誉:
[1] 2021年,华为奖学金
[2] 2017年,JAIST校长奖
[3] 2016年,日本石川县私费留学生奖学金
