Adding Context to Automated Vulnerability Detection for Teaching Software Security

Antoine Dorard; Bastian Küppers; Ashish Rajendra Sai; Theodor Schnitzler

doi:10.1145/3724389.3730794

Adding Context to Automated Vulnerability Detection for Teaching Software Security

Antoine Dorard^*
, Bastian Küppers
, Ashish Rajendra Sai
, Theodor Schnitzler

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

21 Downloads (Pure)

Abstract

Considering the recent developments in the fiel of generative AI, large language models (LLMs) can be leveraged to enhance static application security testing (SAST) tools and teaching about this topic. These models provide contextual information about identified vulnerabilities which can help students to differentiate genuine issues from false alarms while learning about software security. The approach includes analyzing vulnerabilities in android applications using SAST tools, clustering related code functionalities, and generating multi-level summaries for detected vulnerabilities. The process employs advanced clustering techniques and consensus-building methods to ensure accuracy.

Original language	English
Title of host publication	ITiCSE 2025 - Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education
Publisher	Association for Computing Machinery
Pages	790
Number of pages	1
Volume	2
ISBN (Electronic)	9798400715693
DOIs	https://doi.org/10.1145/3724389.3730794
Publication status	Published - 27 Jun 2025
Event	30th Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE 2025 - Nijmegen, Netherlands Duration: 30 Jun 2025 → 2 Jul 2025 https://iticse.acm.org/2025/

Publication series

Series	Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE, Proceedings
Volume	2
ISSN	1942-647X

Conference

Conference	30th Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE 2025
Abbreviated title	ITiCSE 2025
Country/Territory	Netherlands
City	Nijmegen
Period	30/06/25 → 2/07/25
Internet address	https://iticse.acm.org/2025/

Keywords

automated vulnerability detection
computer security education
sast
static application security testing

Access to Document

10.1145/3724389.3730794

Full TextFinal published version, 759 KBLicence: Taverne

Cite this

Dorard, Antoine ; Küppers, Bastian ; Sai, Ashish Rajendra et al. / Adding Context to Automated Vulnerability Detection for Teaching Software Security. ITiCSE 2025 - Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education. Vol. 2 Association for Computing Machinery, 2025. pp. 790 (Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE, Proceedings, Vol. 2).

@inproceedings{b460475426bb4d77b6e2c479bc422358,

title = "Adding Context to Automated Vulnerability Detection for Teaching Software Security",

abstract = "Considering the recent developments in the fiel of generative AI, large language models (LLMs) can be leveraged to enhance static application security testing (SAST) tools and teaching about this topic. These models provide contextual information about identified vulnerabilities which can help students to differentiate genuine issues from false alarms while learning about software security. The approach includes analyzing vulnerabilities in android applications using SAST tools, clustering related code functionalities, and generating multi-level summaries for detected vulnerabilities. The process employs advanced clustering techniques and consensus-building methods to ensure accuracy.",

keywords = "automated vulnerability detection, computer security education, sast, static application security testing",

author = "Antoine Dorard and Bastian K{\"u}ppers and Sai, \{Ashish Rajendra\} and Theodor Schnitzler",

note = "Publisher Copyright: {\textcopyright} 2025 Owner/Author.; 30th Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE 2025, ITiCSE 2025 ; Conference date: 30-06-2025 Through 02-07-2025",

year = "2025",

month = jun,

day = "27",

doi = "10.1145/3724389.3730794",

language = "English",

volume = "2",

series = "Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE, Proceedings",

publisher = "Association for Computing Machinery",

pages = "790",

booktitle = "ITiCSE 2025 - Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education",

address = "United States",

url = "https://iticse.acm.org/2025/",

}

Dorard, A, Küppers, B , Sai, AR & Schnitzler, T 2025, Adding Context to Automated Vulnerability Detection for Teaching Software Security. in ITiCSE 2025 - Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education. vol. 2, Association for Computing Machinery, Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE, Proceedings, vol. 2, pp. 790, 30th Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE 2025, Nijmegen, Netherlands, 30/06/25. https://doi.org/10.1145/3724389.3730794

Adding Context to Automated Vulnerability Detection for Teaching Software Security. / Dorard, Antoine; Küppers, Bastian ; Sai, Ashish Rajendra et al.
ITiCSE 2025 - Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education. Vol. 2 Association for Computing Machinery, 2025. p. 790 (Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE, Proceedings, Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Adding Context to Automated Vulnerability Detection for Teaching Software Security

AU - Dorard, Antoine

AU - Küppers, Bastian

AU - Sai, Ashish Rajendra

AU - Schnitzler, Theodor

PY - 2025/6/27

Y1 - 2025/6/27

N2 - Considering the recent developments in the fiel of generative AI, large language models (LLMs) can be leveraged to enhance static application security testing (SAST) tools and teaching about this topic. These models provide contextual information about identified vulnerabilities which can help students to differentiate genuine issues from false alarms while learning about software security. The approach includes analyzing vulnerabilities in android applications using SAST tools, clustering related code functionalities, and generating multi-level summaries for detected vulnerabilities. The process employs advanced clustering techniques and consensus-building methods to ensure accuracy.

AB - Considering the recent developments in the fiel of generative AI, large language models (LLMs) can be leveraged to enhance static application security testing (SAST) tools and teaching about this topic. These models provide contextual information about identified vulnerabilities which can help students to differentiate genuine issues from false alarms while learning about software security. The approach includes analyzing vulnerabilities in android applications using SAST tools, clustering related code functionalities, and generating multi-level summaries for detected vulnerabilities. The process employs advanced clustering techniques and consensus-building methods to ensure accuracy.

KW - automated vulnerability detection

KW - computer security education

KW - sast

KW - static application security testing

U2 - 10.1145/3724389.3730794

DO - 10.1145/3724389.3730794

M3 - Conference article in proceeding

VL - 2

T3 - Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE, Proceedings

SP - 790

BT - ITiCSE 2025 - Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education

PB - Association for Computing Machinery

T2 - 30th Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE 2025

Y2 - 30 June 2025 through 2 July 2025

ER -

Dorard A, Küppers B , Sai AR , Schnitzler T. Adding Context to Automated Vulnerability Detection for Teaching Software Security. In ITiCSE 2025 - Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education. Vol. 2. Association for Computing Machinery. 2025. p. 790. (Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE, Proceedings, Vol. 2). doi: 10.1145/3724389.3730794

Adding Context to Automated Vulnerability Detection for Teaching Software Security

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this