Home Page of Cristina Improta

Cristina Improta

PhD candidate @ Federico II, UniNa

About Me

Hey! 👋🏻 I’m Cristina, I’m a PhD candidate in Information Technology and Electrical Engineering (ITEE) at the University of Naples Federico II. My research activity focuses on the security and robustness of AI-based code generators, on the quality of AI-generated code, and the application of LLMs for offensive security. I am a member of the DESSERT (DEpendable and Secure Software Engineering and Real-Time Systems) group.

Interests

AI Code Generation
Software Security
Code Quality

Education

MSc Computer Engineering

University of Naples Federico II, Italy
BSc Computer Engineering

University of Naples Federico II, Italy
Diploma Apple Developer Academy

University of Naples Federico II in partnership with Apple, Naples, Italy

📚 My Research

My research focuses on the trustworthiness of AI-based code generators, particularly on their ability to generate functionally correct and secure source code from natural language descriptions. My goal is to address the limitations of these tools, such as their vulnerability to generating incorrect or insecure code due to ambiguous descriptions or training data poisoning, and to develop strategies to effectively mitigate these threats.

Recent Publications

Domenico Cotroneo, Cristina Improta, Pietro Liguori (2025). Human-Written vs. AI-Generated Code A Large-Scale Study of Defects, Vulnerabilities, and Complexity. 2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE).

PDF Cite Code Dataset

Cristina Improta (2025). Detecting Stealthy Data Poisoning Attacks in AI Code Generators. 2025 IEEE 36th International Symposium on Software Reliability Engineering Workshops (ISSREW).

PDF Cite Dataset

Cristina Improta, Rosalia Tufano, Pietro Liguori, Domenico Cotroneo, Gabriele Bavota (2025). Quality In, Quality Out: Investigating Training Data's Role in AI Code Generation. IEEE/ACM 33rd International Conference on Program Comprehension (ICPC 2025).

PDF Cite Code Dataset DOI

Cristina Improta, Pietro Liguori, Roberto Natella, Bojan Cukic, Domenico Cotroneo (2025). Enhancing robustness of ai offensive code generators via data augmentation. Empirical Software Engineering.

PDF Cite Code Dataset DOI

Pietro Liguori, Cristina Improta, Roberto Natella, Bojan Cukic, Domenico Cotroneo (2024). Enhancing AI-based Generation of Software Exploits with Contextual Information. 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE).

PDF Cite Dataset DOI

See all publications

Talks