Pietro Liguori

Dr. Pietro Liguori

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 August 2019
Verified
Conference Paper
Open access
DCDomenico Cotroneo
Domenico Cotroneo
Luigi De SimoneLuigi De Simone
Luigi De Simone
Pietro LiguoriPietro Liguori
Pietro Liguori
RNRoberto Natella
Roberto Natella
NBNematollah Bidokhti
Nematollah Bidokhti

15 April 2024
Verified
Conference Paper
Open access
DCDomenico Cotroneo
Domenico Cotroneo
CICristina Improta
Cristina Improta
Pietro LiguoriPietro Liguori
Pietro Liguori
Roberto NatellaRoberto Natella
Roberto Natella
AI-based code generators have become pivotal in assisting developers in writing software starting from natural language (NL). However, they are trained on large amounts of data, often collected from unsanitized online sources (e.g., GitHub, HuggingFace). As a consequence, AI models become an easy target for data poisoning, i.e., an attack that injects malicious samples into the training data to generate vulnerable code. To address this threat, this work investigates the security of AI code generators by devising a targeted data poisoning strategy. We poison the training data by injecting increasing amounts of code containing security vulnerabilities and assess the attack's success on different state-of-the-art models for code generation. Our study shows that AI code generators are vulnerable to even a small amount of poison. Notably, the attack success strongly depends on the model architecture and poisoning rate, whereas it is not influenced by the type of vulnerabilities. Moreover, since the attack does not impact the correctness of code generated by pre-trained models, it is hard to detect. Lastly, our work offers practical insights into understanding and potentially mitigating this threat.

13 April 2023 in Expert Systems with Applications
Verified
Journal Article
Open access
Pietro LiguoriPietro Liguori
Pietro Liguori
CICristina Improta
Cristina Improta
Roberto NatellaRoberto Natella
Roberto Natella
BCBojan Cukic
Bojan Cukic
DCDomenico Cotroneo
Domenico Cotroneo

24 May 2024 in Journal of Systems and Software
Verified
Journal Article
Open access
DCDomenico Cotroneo
Domenico Cotroneo
AFAlessio Foggia
Alessio Foggia
CICristina Improta
Cristina Improta
Pietro LiguoriPietro Liguori
Pietro Liguori
Roberto NatellaRoberto Natella
Roberto Natella

5 March 2022 in Automated Software Engineering
Verified
Journal Article
Open access
PDF file
Pietro LiguoriPietro Liguori
Pietro Liguori
EAErfan Al-Hossami
Erfan Al-Hossami
DCDomenico Cotroneo
Domenico Cotroneo
Roberto NatellaRoberto Natella
Roberto Natella
BCBojan Cukic
Bojan Cukic
SSSamira Shaikh
Samira Shaikh
Writing software exploits is an important practice for offensive security analysts to investigate and prevent attacks. In particular, shellcodes are especially time-consuming and a technical challenge, as they are written in assembly language. In this work, we address the task of automatically generating shellcodes, starting purely from descriptions in natural language, by proposing an approach based on Neural Machine Translation (NMT). We then present an empirical study using a novel dataset (Shellcode_IA32), which consists of 3200 assembly code snippets of real Linux/x86 shellcodes from public databases, annotated using natural language. Moreover, we propose novel metrics to evaluate the accuracy of NMT at generating shellcodes. The empirical analysis shows that NMT can generate assembly code snippets from the natural language with high accuracy and that in many cases can generate entire shellcodes with no errors.

21 September 2020 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
DCDomenico Cotroneo
Domenico Cotroneo
Luigi De SimoneLuigi De Simone
Luigi De Simone
Pietro LiguoriPietro Liguori
Pietro Liguori
Roberto NatellaRoberto Natella
Roberto Natella
Cloud computing systems fail in complex and unexpected ways, due to unexpected combinations of events and interactions between hardware and software components. Fault injection is an effective means to bring out these failures in a controlled environment. However, fault injection experiments produce massive amounts of data, and manually analyzing these data is inefficient and error-prone, as the analyst can miss severe failure modes that are yet unknown. This paper introduces a new paradigm (fault injection analytics) that applies unsupervised machine learning on execution traces of the injected system, to ease the discovery and interpretation of failure modes. We evaluated the proposed approach in the context of fault injection experiments on the OpenStack cloud computing platform, where we show that the approach can accurately identify failure modes with a low computational cost.