基本信息

梁瑞刚  男  中国科学院信息工程研究所
电子邮件:liangruigang AT iie.ac.cn
通信地址:海淀区树村路19号
邮政编码:100085

研究领域

​软件与系统安全,人工智能安全,智能终端安全,隐私保护

教育背景

2017-09--2021-06   中国科学院大学(信息工程研究所)   博士
2014-09--2017-06   中国科学院大学(信息工程研究所)   硕士
2010-09--2014-06   大连理工大学   本科

工作经历

2023-10~现在, 中国科学院信息工程研究所, 高级工程师
2021-07~2023-10, 中国科学院信息工程研究所, 工程师

专利与奖励

专利:

(1)一种检测Android应用软件用户隐私信息泄露的方法,CN201710198595.X.

(2)一种提高模糊测试效率的方法和系统,CN201811257109.8.

(3)一种移动应用立体防御方法和系统,CN201910163513.

(4)一种针对图像分类模型的后门检测及修复方法及系统, CN202110796626.8.

(5)一种并发应用运行时加固方法与装置, CN202110677805.X.

(6)一种针对图像语义分割模型的图像预检方法和系统, CN202210223847.0.

(7)一种基于深度学习的优化代码反编译方法和系统, CN202210271791.6.

(8)基于动静态分析的恶意软件家族谱系分析方法和装置, CN202211723014.7.

(9)基于网络流量分析的攻击代码在线检测方法和装置, CN202211723016.6.

(10)一种基于大语言模型的反编译结果优化方法和系统,CN202311326842.1.

(11)一种针对神经网络分类模型的隐私保护方法及装置,CN202311541102.X.

(12)一种针对卷积神经网络的可解释性方法及系统,CN202311761097.3.

(13)一种针对增强语言模型中知识图谱所有权验证方法,CN202311803323.X.


奖励:

(1)中国电子学会科技进步奖, 一等奖, 部委级, 2023.

(2)电力科技创新奖, 二等奖, 部委级, 2021.

(3)中国科学院信息工程研究所重大科技进展奖, 研究所(学校), 2018.


出版信息

发表论文20余篇,部分论文如下:

[ISSTA] Ying Cao, Runze Zhang, Ruigang Liang​, Kai Chen, "Evaluating the Effectiveness of Decompilers", ISSTA 2024.

[S&P] Peizhuo Lv, Hualong Ma, Kai Chen, Jiachen Zhou, Shengzhi Zhang, Ruigang Liang, Shenchen Zhu, Pan Li, Yingjun Zhang, "MEA-Defender: A Robust Watermark against Model Extraction Attack", S&P 2024.

[NDSS] Peiwei Hu, Ruigang Liang, Kai Chen, "DeGPT: Optimizing Decompiler Output with LLM", NDSS 2024.

[NDSS] Peizhuo Lv, Pan Li, Shenchen Zhu, Shengzhi Zhang, Kai Chen, Ruigang Liang, Chang Yue, Fang Xiang, Yuling Cai, Hualong Ma, Yingjun Zhang, Guozhu Meng, "SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-Supervised Learning", NDSS 2024.

[USENIX Security] Peiwei Hu, Ruigang Liang, Ying Cao, Kai Chen, Runze Zhang, "AURC: Detecting Errors in Program Code and Documentation", USENIX Security 2023.

[USENIX Security] Peizhuo Lv, Chang Yue, Ruigang Liang, Yunfei Yang, Shengzhi Zhang, Hualong Ma, Kai Chen, "A Data-free Backdoor Injection Approach in Neural Networks", USENIX Security 2023.

[TDSC] Peizhuo Lv, Pan Li, Shengzhi Zhang, Kai Chen, Ruigang Liang, Hualong Ma, Yue Zhao, and Yingjiu Li, "A Robustness-Assured White-Box Watermark in Neural Networks", TDSC 2023.

[ECAI] Chang Yue, Peizhuo Lv, Ruigang Liang, Kai Chen, "Invisible backdoor attacks using data poisoning in the frequency domain", ECAI 2023.

[ICME] Peizhuo Lv, Hualong Ma, Jiachen Zhou, Ruigang Liang, Kai Chen, Shengzhi Zhang, Yunfei Yang, "DBIA: Data-free Backdoor Injection Attack against Transformer Networks", ICME 2023.

[Cybersecurity] Zhixiu Guo, Ruigang Liang, Guozhu Meng, Kai Chen, "SkillSim: voice apps similarity detection", Cybersecurity 2023.

[ACSAC] Ying Cao, Ruigang Liang (co-first author), Kai Chen, Peiwei Hu, "Boosting Neural Networks to Decompile Optimized Binaries", ACSAC 2022.

[Cybersecurity] Ruigang Liang, Ying Cao, Peiwei Hu, Kai Chen, "Neutron: an attention-based neural decompiler", Cybersecurity 2021.

[Cybersecurity] Yuhang Zhao, Ruigang Liang, Xiang Chen, Jing Zou, "Evaluation indicators for open-source software: a review", Cybersecurity 2021.

[USENIX Security] Peiyuan Zong, Tao Lv, Dawei Wang, Zizhuang Deng, Ruigang Liang, Kai Chen, "FuzzGuard: Filtering out Unreachable Inputs in Directed Grey-box Fuzzing through Deep Learning", USENIX Security 2020.

[JSC] 梁瑞刚, 吕培卓, 赵月, 陈鹏, 邢豪, 张颖君, 韩冀中, 赫然, 赵险峰, 李明, 陈恺, "视听觉深度伪造检测技术研究综述", 信息安全学报 2020.

[CCS] Yue Zhao, Hong Zhu, Ruigang Liang, Qintao Shen, Shengzhi Zhang, Kai Chen, "Seeing isn’t Believing: Towards More Robust Adversarial Attack Against Real World Object Detectors", CCS 2019.

[Industrial IoT] Aohui Wang, Ruigang Liang, Xiaokang Liu, Yingjun Zhang, Kai Chen, Jin Li, "An inside look at IoT malware", Industrial IoT 2017.



科研项目

(1)编译器优化场景下的智能软件逆向,主持,国家自然科学青年基金,2024-01--2026-12.

(2) 可解释、可通用的下一代人工智能方法--深度学习隐私保护计算新型体系框架与模型,课题负责人,国家自然科学基金(重大研究计划-重点项目),2023-01--2026-12.

(3)基于漏洞数据集的漏洞特征库分析与预测方法研究,参与,国家自然科学基金(重点项目),2019-01--2022-12.