Publications

Pietro Liguori, Cristina Improta, Roberto Natella, Bojan Cukic, Domenico Cotroneo (2024). Enhancing AI-based Generation of Software Exploits with Contextual Information. arXiv preprint arXiv:2408.02402.
PDF Cite Dataset
Domenico Cotroneo, Alessio Foggia, Cristina Improta, Pietro Liguori, Roberto Natella (2024). Automating the correctness assessment of AI-generated code for security contexts. Journal of Systems and Software.
PDF Cite Code Dataset DOI
Domenico Cotroneo, Cristina Improta, Pietro Liguori, Roberto Natella (2024). Vulnerabilities in ai code generators: Exploring targeted data poisoning attacks. Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension.
PDF Cite Code DOI
Roberto Natella, Pietro Liguori, Cristina Improta, Bojan Cukic, Domenico Cotroneo (2024). AI Code Generators for Security: Friend or Foe?. IEEE Security & Privacy.
PDF Cite Dataset DOI
Cristina Improta (2023). Poisoning programs by un-repairing code: security concerns of AI-generated code. 2023 IEEE 34th International Symposium on Software Reliability Engineering Workshops (ISSREW).
PDF Cite DOI
Pietro Liguori, Cristina Improta, Roberto Natella, Bojan Cukic, Domenico Cotroneo (2023). Who evaluates the evaluators? On automatic metrics for assessing AI-based offensive code generators. Expert Systems with Applications.
PDF Cite DOI
Cristina Improta, Pietro Liguori, Roberto Natella, Bojan Cukic, Domenico Cotroneo (2023). Enhancing Robustness of AI Offensive Code Generators via Data Augmentation. arXiv preprint arXiv:2306.05079.
PDF Cite DOI
Pietro Liguori, Cristina Improta, Simona De Vivo, Roberto Natella, Bojan Cukic, Domenico Cotroneo (2022). Can NMT understand me? towards perturbation-based evaluation of NMT models for code generation. Proceedings of the 1st International Workshop on Natural Language-based Software Engineering.
PDF Cite DOI