新闻动态

2020

talks
软件漏洞挖掘方法探索

10:00-11:30am August 22, 2020

academic talk @ tencent, Tsinghua University, Beijing

Speaker: 张超,清华大学

Download slides

Abstract:

模糊测试近年来成为安全研究人员的必备的漏洞挖掘工具。实践中最有效的模糊测试工具通常包含种子测试例生成、选择、变异、测试、评估、反馈等多个环节,每个环节都可以被优化改进以提升漏洞挖掘效率。我们通过改进经典模糊测试方案,提出了多个新的漏洞挖掘方案,在四大安全会议发表多篇论文,取得了不错的效果。本次报告中,演讲者将与大家分享其部分研究成果。

talks
Revisited AI Security: From Adversarial Attacks to Application and Foundation

14:00-15:30pm July 09, 2020

academic talk @ zoom, Tsinghua University, Beijing

Speaker: 纪守领,浙江大学

Abstract:

Recently, AI security has drawn significant attention from the academia and industry. Various kinds of adversarial attacks and defenses spring up like bamboo shoots. Now, considering more and more AI systems have been deployed and are being deployed, it is the time to comprehensively understand what is the performance of the attacks against real world systems? Furthermore, in security-critical applications, in addition to empirical evaluation, how to understand/quantify the security space of deep models is also important. In this talk, based on our previous research, I will introduce some AI security projects, as well as some recent interesting results from the adversarial example transferability and robustness quantification perspectives.

talks
iOS/macOS 漏洞挖掘经验谈之温故知新

14:00-15:30pm June 11, 2020

academic talk @ zoom, Tsinghua University, Beijing

Speaker: 王铁磊,盘古

Abstract:

iOS/macOS系统的漏洞挖掘是当前业界的热点。这个议题里我将分享自己在iOS/macOS 安全研究工作中的一些经验和心得,回顾我们在公开报告中埋藏过的一些彩蛋,希望对刚刚进入iOS/macOS系统漏洞挖掘领域的同学有所帮助和启发。