ICSE 2025 (series) / EnCyCriS 2025 (series) / EnCyCriS 2025 /
Enhanced Detection of Code Vulnerability with Synergy between Data-Driven, Rule-Based and Unsupervised Learnings
Code vulnerabilities pose risks to software security. This paper combines data-driven (deep learning) and rulebased methods to enhance vulnerability detection, leveraging unsupervised learning to prune the hybrid model. A neural network encodes source code into vectors preserving semantic syntactic properties, which are classified using a Random Forest ensemble. A novel pruning algorithm, utilizing clustering techniques, removes low-impact trees to prevent overfitting. Evaluation on Java and C datasets shows that the proposed approach outperforms state-of-the-art rule-based, neural network, and vulnerability detection methods in accurately classifying methodlevel vulnerabilities
Sat 3 MayDisplayed time zone: Eastern Time (US & Canada) change
Sat 3 May
Displayed time zone: Eastern Time (US & Canada) change
11:00 - 12:30 | |||
11:00 20mPaper | Cyberspace Vigilante or Security Sleuth: Understanding Who Threat Hunters Are EnCyCriS Samantha Hill University of Victoria, Alessandra Maciel Paz Milani University of Victoria, Callum Curtis University of Victoria, Arty Starr University of Victoria, Enrique Larios Vargas University of Victoria, Marcus Dunn University of Victoria, Margaret-Anne Storey University of Victoria | ||
11:20 20mPaper | Enhanced Detection of Code Vulnerability with Synergy between Data-Driven, Rule-Based and Unsupervised Learnings EnCyCriS Hibah Mohammed Ghouse Hubspot, Samiha Shimmi Northern Illinois University, Mona Rahimi Northern Illinois University | ||
11:40 20mPaper | Evaluating the Integration of Aurora zkSNARK in the Zupply Framework EnCyCriS | ||
12:00 30mPanel | Panel based discussions and open questions - morning session EnCyCriS |