一、報告時間

2023年6月19日（周一）9:00-11:30

二,、報告地點

電航樓219

三,、主講人

謝肖飛博士，新加坡管理大學助理教授,。謝博士于2018年在天津大學獲得博士學位,，并獲得了中國CCF優(yōu)秀博士論文獎（2019）。他的研究主要集中在傳統(tǒng)軟件和AI軟件的質(zhì)量保證上,，在軟件工程,、安全和AI領(lǐng)域頂級會議/期刊如ICSE、ESEC/FSE,、ISSTA,、ASE、TSE,、TOSEM,、ICLR、NeurIPS,、ICML,、TPAMI,、Usenix Security和CCS 上發(fā)表多篇論文，并獲得了三個ACM SIGSOFT杰出論文獎（FSE'16,、ASE'19和ISSTA'22）,。

四、內(nèi)容簡介

在過去數(shù)十年,，基于學習的軟件應(yīng)用在人臉識別,、自動駕駛和內(nèi)容生成等多個領(lǐng)域已經(jīng)展示了其巨大的潛力。軟件的發(fā)展從傳統(tǒng)的基于代碼的程序擴展到了AI驅(qū)動的軟件（也稱為智能軟件）,。然而，與傳統(tǒng)的軟件一樣,，智能軟件也可能表現(xiàn)出不正確的行為,，從而導(dǎo)致嚴重的事故和損失。因此,，智能軟件的質(zhì)量和安全性是非常重要的,。相比傳統(tǒng)軟件，智能軟件的“黑盒”特性使在分析和解釋其行為時帶來了重大挑戰(zhàn),。本次演講將從傳統(tǒng)的軟件分析到基于深度學習模型的軟件分析展開系統(tǒng)的介紹,，在此基礎(chǔ)上為給定的軟件（例如代碼或深度神經(jīng)網(wǎng)絡(luò)）構(gòu)建抽象模型?；谠撃Ｐ?，我們可以進行全面的分析、測試,、故障定位和自動化修復(fù),，以提高軟件的質(zhì)量和安全性。

Abstract: Over the past decade, the application of learning-based software in various domains, such as face recognition, autonomous driving, and content generation, has shown tremendous potential. The evolution of software has led to a diverse landscape, ranging from traditional code-based programs to AI-driven software (a.k.a., intelligent software). However, like traditional software, intelligent software can exhibit incorrect behaviors, which may result in severe accidents and losses. Ensuring the quality and security of software, particularly in safety- and security-critical scenarios, is of utmost importance. However, the black-box nature of intelligent software poses significant challenges in analyzing and explaining its behaviors. In this talk, I will present the model-based analysis from traditional software to deep learning-based software. Our approach involves constructing an abstract model for a given software (e.g., code or a deep neural network). Based on this model, we can perform comprehensive analysis, testing, fault localization, and automated repair to enhance its quality and security.

信息科學技術(shù)學院

2023年6月9日