Write a Blog >>
MSR 2022
Mon 23 - Tue 24 May 2022
co-located with ICSE 2022
Thu 19 May 2022 21:14 - 21:21 at MSR Main room - odd hours - Session 13: Security & Quality Chair(s): Gias Uddin

Software vulnerabilities are prevalent in software systems, causing a variety of problems including deadlock, information loss, or system failures. Thus, early predictions of software vulnerabilities are critically important in safety-critical software systems. Various ML/DL-based approaches have been proposed to predict vulnerabilities at the file/function/method level. Recently, IVDetect (a graph-based neural network) is proposed to predict vulnerabilities at the function level. Yet, the IVDetect approach is still inaccurate and coarse-grained. In this paper, we propose LineVul, a Transformer-based line-level vulnerability prediction approach in order to address several limitations of the state-of-the-art IVDetect approach. Through an empirical evaluation of a large-scale real-world dataset with 188k+ C/C++ functions, we show that LineVul achieves (1) 160%-379% higher F1-measure for function-level predictions; (2) 12%-25% higher Top-10 Accuracy for line-level predictions; and (3) 29%-53% less Effort@20%Recall than the state-of-the-art approaches. The substantial improvement of our approach highlights the significant contributions towards more accurate, more cost-effective, and more finer-grained software vulnerability predictions.

Thu 19 May

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

21:00 - 21:50
Session 13: Security & QualityTechnical Papers / Data and Tool Showcase Track / Registered Reports / Industry Track at MSR Main room - odd hours
Chair(s): Gias Uddin University of Calgary, Canada
21:00
7m
Talk
On the Use of Fine-grained Vulnerable Code Statements for Software Vulnerability Assessment Models
Technical Papers
Triet Le Huynh Minh The University of Adelaide, Muhammad Ali Babar University of Adelaide
Pre-print
21:07
7m
Talk
LineVD: Statement-level Vulnerability Detection using Graph Neural Networks
Technical Papers
David Hin The University of Adelaide, Andrey Kan The University of Adelaide, Huaming Chen The University of Adelaide, Muhammad Ali Babar University of Adelaide
21:14
7m
Talk
LineVul: A Transformer-based Line-Level Vulnerability Prediction
Technical Papers
Michael Fu Monash University, Chakkrit Tantithamthavorn Monash University
Pre-print
21:21
4m
Talk
ECench: An Energy Bug Benchmark of Ethereum Client Software
Data and Tool Showcase Track
Jinyoung Kim Sungkyunkwan University, Misoo Kim Sungkyunkwan University, Eunseok Lee Sungkyunkwan University
21:25
7m
Talk
Microsoft CloudMine: Data Mining for the Executive Order on Improving the Nation’s Cybersecurity
Industry Track
Kim Herzig Tools for Software Engineers, Microsoft, Luke Gostling Microsoft Corporation, Maximilian Grothusmann Microsoft Corporation, Nora Huang Microsoft Corporation, Sascha Just Microsoft, Alan Klimowski Microsoft Corporation, Yashasvini Ramkumar Microsoft Corporation, Myles McLeroy Microsoft Corporation, Kıvanç Muşlu Microsoft, Hitesh Sajnani Microsoft , Varsha Vadaga Microsoft Corporation
21:32
4m
Talk
Evaluating few shot and Contrastive learning Methods for Code Clone Detection
Registered Reports
Mohamad Khajezade University of British Columbia, Fatemeh Hendijani Fard University of British Columbia, Mohamed S Shehata University of British Columbia
Pre-print
21:36
14m
Live Q&A
Discussions and Q&A
Technical Papers


Information for Participants
Thu 19 May 2022 21:00 - 21:50 at MSR Main room - odd hours - Session 13: Security & Quality Chair(s): Gias Uddin
Info for room MSR Main room - odd hours:

Click here to go to the room on Midspace