Evolutionary Approaches for Adversarial Attacks on Neural Source Code Classifiers

• Published in: Algorithms Vol. 16; no. 10; p. 478
• Main Authors: Mercuri, Valeria, Saletta, Martina, Ferretti, Claudio
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.10.2023
• Subjects: adversarial examples; Algorithms; Artificial intelligence; Classification; Classifiers; Cybersecurity; Deep learning; Evolution; evolution strategies; evolutionary algorithms; Iterative methods; Machine learning; Methods; Neural networks; Resilience; Security management; Software; Source code; source code analysis; vulnerability detection
• ISSN: 1999-4893; 1999-4893
• DOI: 10.3390/a16100478

As the prevalence and sophistication of cyber threats continue to increase, the development of robust vulnerability detection techniques becomes paramount in ensuring the security of computer systems. Neural models have demonstrated significant potential in identifying vulnerabilities; however, they are not immune to adversarial attacks. This paper presents a set of evolutionary techniques for generating adversarial instances to enhance the resilience of neural models used for vulnerability detection. The proposed approaches leverage an evolution strategy (ES) algorithm that utilizes as the fitness function the output of the neural network to deceive. By starting from existing instances, the algorithm evolves individuals, represented by source code snippets, by applying semantic-preserving transformations, while utilizing the fitness to invert their original classification. This iterative process facilitates the generation of adversarial instances that can mislead the vulnerability detection models while maintaining the original behavior of the source code. The significance of this research lies in its contribution to the field of cybersecurity by addressing the need for enhanced resilience against adversarial attacks in vulnerability detection models. The evolutionary approach provides a systematic framework for generating adversarial instances, allowing for the identification and mitigation of weaknesses in AI classifiers.