Write a Blog >>
ICSE 2022
Sun 8 - Fri 27 May 2022
Mon 9 May 2022 21:15 - 21:20 at ICSE room 3-odd hours - Software Security 3 Chair(s): Nancy Mead
Tue 10 May 2022 04:10 - 04:15 at ICSE room 3-even hours - Apps and Security Chair(s): Alessio Ferrari

Software-intensive systems produce logs for troubleshooting purposes. Recently, many deep learning models have been proposed to automatically detect system anomalies based on log data. These models typically claim very high detection accuracy. For example, most models report an F-measure greater than 0.9 on the commonly-used HDFS dataset. To achieve a profound understanding of how far we are from solving the problem of log-based anomaly detection, in this paper, we conduct an in-depth analysis of five state-of-the-art deep learning-based models for detecting system anomalies on four public log datasets. Our experiments focus on several aspects of model evaluation, including training data selection, data grouping, class distribution, data noise, and early detection ability. Our results point out that all these aspects have significant impact on the evaluation, and that all the studied models do not always work well. The problem of log-based anomaly detection has not been solved yet. Based on our findings, we also suggest possible future work.

Mon 9 May

Displayed time zone: Eastern Time (US & Canada) change

21:00 - 22:00
21:00
5m
Talk
Omni: automated ensemble with unexpected models against adversarial evasion attack
Journal-First Papers
Rui Shu North Carolina State University, Tianpei Xia North Carolina State University, Laurie Williams North Carolina State University, Tim Menzies North Carolina State University
Link to publication DOI Media Attached
21:05
5m
Talk
What are Weak Links in the npm Supply Chain?
SEIP - Software Engineering in Practice
Nusrat Zahan North Carolina State University, Laurie Williams North Carolina State University, Thomas Zimmermann Microsoft Research, Patrice Godefroid Microsoft Research, USA, Brendan Murphy Microsoft Research, Chandra Sekhar Maddila Microsoft Research
Pre-print Media Attached
21:10
5m
Talk
Automated Detection of Password Leakage from Public GitHub RepositoriesNominated for Distinguished Paper
Technical Track
Runhan Feng Shanghai Jiao Tong University, Ziyang Yan Shanghai Jiao Tong University, Shiyan Peng Shanghai Jiao Tong University, Yuanyuan Zhang Shanghai Jiao Tong University
Pre-print Media Attached
21:15
5m
Talk
Log-based Anomaly Detection with Deep Learning: How Far Are We
Technical Track
Van-Hoang Le The University of Newcastle, Hongyu Zhang University of Newcastle
DOI Pre-print
21:20
5m
Talk
Rotten Apples Spoil the Bunch: An Anatomy of Google Play Malware
Technical Track
Michael Cao University of British Columbia, Khaled Ahmed University of British Columbia (UBC), Julia Rubin University of British Columbia
Pre-print Media Attached
21:25
5m
Talk
What the Fork? Finding Hidden Code Clones in npm
Technical Track
Elizabeth Wyss University of Kansas, Lorenzo De Carli Worcester Polytechnic Institute, Drew Davidson University of Kansas
DOI Pre-print Media Attached

Tue 10 May

Displayed time zone: Eastern Time (US & Canada) change

04:00 - 05:00
04:00
5m
Talk
An Empirical Study on Implicit Constraints in Smart Contract Static Analysis
SEIP - Software Engineering in Practice
Tingting Yin Tsinghua University, China, Chao Zhang Tsinghua University, Yuandong Ni Institute for Network Science and Cyberspace of Tsinghua University, Yixiong Wu Institute for Network Science and Cyberspace of Tsinghua University, Taiyu Wong Department of Computer Science and Technology, Tsinghua University, Xiapu Luo Hong Kong Polytechnic University, Zheming Li Tsinghua University, Yu Guo SECBIT labs
Pre-print Media Attached
04:05
5m
Talk
Automated Detection of Password Leakage from Public GitHub RepositoriesNominated for Distinguished Paper
Technical Track
Runhan Feng Shanghai Jiao Tong University, Ziyang Yan Shanghai Jiao Tong University, Shiyan Peng Shanghai Jiao Tong University, Yuanyuan Zhang Shanghai Jiao Tong University
Pre-print Media Attached
04:10
5m
Talk
Log-based Anomaly Detection with Deep Learning: How Far Are We
Technical Track
Van-Hoang Le The University of Newcastle, Hongyu Zhang University of Newcastle
DOI Pre-print
04:15
5m
Talk
RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation
Technical Track
Zhen Li University of Texas at San Antonio, Guenevere (Qian) Chen University of Texas at San Antonio, Chen Chen University of Central Florida, Yayi Zou Northeastern University, Shouhuai Xu University of Colorado Colorado Springs
Pre-print Media Attached
04:20
5m
Talk
Where is Your App Frustrating Users?
Technical Track
Yawen Wang Institute of Software, Chinese Academy of Sciences, Junjie Wang Institute of Software at Chinese Academy of Sciences, Hongyu Zhang University of Newcastle, Xuran Ming Institute of Software, Chinese Academy of Sciences, Lin Shi ISCAS, Qing Wang Institute of Software at Chinese Academy of Sciences
DOI Pre-print Media Attached
04:25
5m
Talk
Towards Automatically Repairing Compatibility Issues in Published Android Apps
Technical Track
Yanjie Zhao Monash University, Li Li Monash University, Kui Liu Nanjing University of Aeronautics and Astronautics, China, John Grundy Monash University
Pre-print Media Attached

Information for Participants
Mon 9 May 2022 21:00 - 22:00 at ICSE room 3-odd hours - Software Security 3 Chair(s): Nancy Mead
Info for room ICSE room 3-odd hours:

Click here to go to the room on Midspace

Tue 10 May 2022 04:00 - 05:00 at ICSE room 3-even hours - Apps and Security Chair(s): Alessio Ferrari
Info for room ICSE room 3-even hours:

Click here to go to the room on Midspace