期刊文献+

人工智能算法安全研究现状与对策 被引量:4

Research status and countermeasures of artificial intelligence algorithm security
下载PDF
导出
摘要 机器学习助推的新一代人工智能再一次成为学术界和产业界关注的焦点,已取得的进展和深度应用,正在成为世界各国新一轮战略性技术和核心驱动力。然而,数据、算法和算力作为新一代人工智能的核心要素,在支撑数字经济发展的同时,也面临技术和社会双重安全风险。以人工智能算法为主线,聚焦人工智能技术潜在的安全风险,综述分析了人工智能算法面临的不可解释性、逆向攻击、后门攻击、投毒攻击和对抗样本攻击等方面的潜在技术安全问题与挑战,从隐私保护机器学习、算法鲁棒性增强和算法安全评估等几个方面,从技术角度归纳或提出人工智能算法安全的解决对策,旨在为解决人工智能的应用和安全之间的矛盾提供一种研究思路和方向。 The new generation of artificial intelligence(AI) boosted by machine learning has once again become the focus of academic and industry.The progress and in-depth application that has been made are becoming a new round of strategic technology and core driving force all round the world.However,as the core elements of the new generation of artificial intelligence,data,algorithms and computility are also facing double security risks of technology and society while supporting the development of digital economy.Focusing on the potential security risks of AI technology taking AI algorithm as the principal line,this paper reviews and analyzes the potential technical security problems and challenges faced by AI algorithm in terms of non interpretability,reverse attack,backdoor attack,poison attack,and adversarial attacks.From several aspects such as privacy protection machine learning,the robustness enhancement for algorithms,and the security evaluation of algorithms,this paper proposes solutions to the security of artificial intelligence algorithms from viewpoint of technology.It aims to provide a research idea and direction for solving the contradiction between the application and security of artificial intelligence.
作者 彭长根 何兴 谭伟杰 刘海 PENG Changgen;HE Xing;TAN Weijie;LIU Hai(Guizhou Big Data Academy,Guizhou University,Guiyang,Guizhou 550025,China;State Key Laboratory of Public Big Data,College of Computer Science and Technology,Guizhou University,Guiyang,Guizhou 550025,China)
出处 《贵州师范大学学报(自然科学版)》 CAS 2022年第6期1-16,共16页 Journal of Guizhou Normal University:Natural Sciences
基金 国家自然科学基金项目(62272124,U1836205) 贵州省科技计划项目(黔科合平台人才[2020]5017)。
关键词 机器学习 数据安全 算法安全 密码技术 隐私计算 machine learning data security algorithm security cryptography privacy computing
  • 相关文献

参考文献3

二级参考文献8

共引文献71

同被引文献26

引证文献4

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部