| Who evaluates the evaluators? On automatic metrics for assessing AI-based offensive code generators P Liguori, C Improta, R Natella, B Cukic, D Cotroneo Expert Systems with Applications 225, 120073, 2023 | 9 | 2023 |
| Vulnerabilities in ai code generators: Exploring targeted data poisoning attacks D Cotroneo, C Improta, P Liguori, R Natella arXiv preprint arXiv:2308.04451, 2023 | 6 | 2023 |
| Can NMT understand me? towards perturbation-based evaluation of NMT models for code generation P Liguori, C Improta, S De Vivo, R Natella, B Cukic, D Cotroneo Proceedings of the 1st International Workshop on Natural Language-based …, 2022 | 4 | 2022 |
| Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code C Improta 2023 IEEE 34th International Symposium on Software Reliability Engineering …, 2023 | 2 | 2023 |
| AI Code Generators for Security: Friend or Foe? R Natella, P Liguori, C Improta, B Cukic, D Cotroneo IEEE Security & Privacy, 2024 | 1 | 2024 |
| Enhancing Robustness of AI Offensive Code Generators via Data Augmentation C Improta, P Liguori, R Natella, B Cukic, D Cotroneo arXiv preprint arXiv:2306.05079, 2023 | 1 | 2023 |
| Automating the Correctness Assessment of AI-generated Code for Security Contexts D Cotroneo, A Foggia, C Improta, P Liguori, R Natella arXiv preprint arXiv:2310.18834, 2023 | | 2023 |
| Who Evaluates the Evaluators? On Automatic Metrics for Assessing AI-based Offensive Code Generators C Improta, P Liguori, R Natella, B Cukic, D Cotroneo arXiv e-prints, arXiv: 2212.06008, 2022 | | 2022 |
