黄承超

时间:2023-09-08

姓名

黄承超

研究领域

代数计算、自动推理、量子计算、人工智能

联系方式

固定电话:

电子邮箱:chengchao@nj.iscas.ac.cn

招生信息

招生专业:计算机科学与技术、电子信息

招生方向:

人工智能安全,包括神经网络模型的验证、攻击、修复等基础算法,及其在智能交互与控制系统(如自动驾驶)中的应用

个人简介(教育背景、工作经历、社会兼职等)

2021 -中科南京软件技术研究院软件安全与可信实验室副主任

2019 - 2021广州市智能软件产业研究院高可靠智能软件实验室副主任

2014 - 2019华东师范大学计算机软件与理论硕博

2010 - 2014华东师范大学计算机科学与技术学士

目前承担课题情况(项目负责人)

中科院稳定支持基础研究专项“开放环境下的可信智能算法”子课题

研究院项目“深度神经网络的可信赖保障技术”

学术成果(代表性论文、专利等)

AI Safety:

[1] VeRe: verification guided synthesis for repairing deep neural networks,Ma J., Yang P., Wang J., Sun Y., Huang C.-C., and Wang Z. in ICSE 2024.

[2] TrajPAC: towards robustness verification of pedestrian trajectory prediction models,Zhang L., Xu N., Yang P., Jin G., Huang C.-C, and Zhang L. in ICCV 2023.

[3] Towards practical robustness analysis for DNNs based on PAC-model learning, Li R., Yang P., Huang C.-C., Sun Y., Xue B., and Zhang L. in ICSE 2022.

[4] Improving neural network verification through spurious region guided refinement. Yang P., Li R., Li J., Huang C.-C., Wang J., Sun J., Xue B., and Zhang L. in TACAS 2021.

[5] Prodeep: a platform for robustness verification of deep neural networks. Li R., Li J., Huang C.-C., Yang P., Huang X., Zhang L., Xue B., and Hermanns H. in ESEC/FSE 2020.

Fundamental Theories & Algorithms:

[6] Explicit bounds for linear forms in the exponentials of algebraic numbers, Huang C.-C. in ISSAC 2022.

[7] Measuring the constrained reachability in quantum Markov chains. Xu M., Huang C.-C., and Feng Y. Acta Informatica (2021).

[8] A conflict-driven solving procedure for poly-power constraints. Huang C.-C., Xu M., and Li Z.-B. Journal of Automated Reasoning (2020).

[9] Positive root isolation for poly-powers by exclusion and differentiation. Huang C.-C., Li J.-C., Xu M., and Li Z.-B. Journal of Symbolic Computation (2018).

[10] Analyzing ultimate positivity for solvable systems, Xu M., Huang C.-C., Li Z.-B.,and Zeng Z. Theoretical Computer Science (2016).

获奖情况


江苏省南京市江宁区天泉路188号

211135

© 中国科学院大学南京学院版权所有 All Right Reserved.苏ICP备05004321号