80 citations · 347 across the 29 of their papers we have counts for
30 papers
What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code
Cristina Improta, Pietro Liguori, Domenico Cotroneo
AI coding assistants are becoming co-authors of production software, yet their evaluation centers on functional correctness, leaving open whether their code differs from human code…
Beyond Fixed Fault Models: Comparing LLM-Based and Rule-Based Fault Injection in OpenStack
Giuseppe De Rosa, Pietro Liguori, Domenico Cotroneo
Software Fault Injection (SFI) supports testing of cloud systems by introducing software defects and observing their manifestation. Rule-based injectors such as ProFIPy provide con…
AI-Generated PowerShell Malware: An Experimental Framework and Dataset
Luciano Pianese, Vittorio Orbinato, Pietro Liguori +1
Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious purposes via scripting language…
Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration
Cristina Carleo, Pietro Liguori, Naghmeh Ivaki +1
Producing a labeled vulnerable code at scale is a recurring obstacle for learning-based vulnerability detection: mined corpora carry substantial label noise, and existing LLM-based…
Will It Break in Production? Metric-Driven Prediction of Residual Defects in Python Systems
Giuseppe De Rosa, Pietro Liguori
Python's dynamic nature complicates testing and increases the possibility that some defects evade detection, so an effective fault prediction becomes essential. We examine whether…
Human-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexity
Domenico Cotroneo, Cristina Improta, Pietro Liguori
As AI code assistants become increasingly integrated into software development workflows, understanding how their code compares to human-written programs is critical for ensuring r…
PyResBugs: A Dataset of Residual Python Bugs for Natural Language-Driven Fault Injection
Domenico Cotroneo, Giuseppe De Rosa, Pietro Liguori
This paper presents PyResBugs, a curated dataset of residual bugs, i.e., defects that persist undetected during traditional testing but later surface in production, collected from…
Quality In, Quality Out: Investigating Training Data's Role in AI Code Generation
Cristina Improta, Rosalia Tufano, Pietro Liguori +2
Deep Learning-based code generators have seen significant advancements in recent years. Tools such as GitHub Copilot are used by thousands of developers with the main promise of a…
CGP-Tuning: Structure-Aware Soft Prompt Tuning for Code Vulnerability Detection
Ruijun Feng, Hammond Pearce, Pietro Liguori +1
Large language models (LLMs) have been proposed as powerful tools for detecting software vulnerabilities, where task-specific fine-tuning is typically employed to provide vulnerabi…
Enhancing AI-based Generation of Software Exploits with Contextual Information
Pietro Liguori, Cristina Improta, Roberto Natella +2
This practical experience report explores Neural Machine Translation (NMT) models' capability to generate offensive security code from natural language (NL) descriptions, highlight…
The Power of Words: Generating PowerShell Attacks from Natural Language
Pietro Liguori, Christian Marescalco, Roberto Natella +2
As the Windows OS stands out as one of the most targeted systems, the PowerShell language has become a key tool for malicious actors and cybersecurity professionals (e.g., for pene…
Neural Fault Injection: Generating Software Faults from Natural Language
Domenico Cotroneo, Pietro Liguori
Traditional software fault injection methods, while foundational, face limitations in adequately representing real-world faults, offering customization, and requiring significant m…
DeVAIC: A Tool for Security Assessment of AI-generated Code
Domenico Cotroneo, Roberta De Luca, Pietro Liguori
Context: AI code generators are revolutionizing code writing and software development, but their training on large datasets, including potentially untrusted source code, raises sec…
AI Code Generators for Security: Friend or Foe?
Roberto Natella, Pietro Liguori, Cristina Improta +2
Recent advances of artificial intelligence (AI) code generators are opening new opportunities in software security research, including misuse by malicious actors. We review use cas…
Automating the Correctness Assessment of AI-generated Code for Security Contexts
Domenico Cotroneo, Alessio Foggia, Cristina Improta +2
Evaluating the correctness of code generated by AI is a challenging open problem. In this paper, we propose a fully automated method, named ACCA, to evaluate the correctness of AI-…
Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
Domenico Cotroneo, Cristina Improta, Pietro Liguori +1
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, of…
Enhancing Robustness of AI Offensive Code Generators via Data Augmentation
Cristina Improta, Pietro Liguori, Roberto Natella +2
Since manually writing software exploits for offensive security is time-consuming and requires expert knowledge, AI-base code generators are an attractive solution to enhance secur…
Run-time Failure Detection via Non-intrusive Event Analysis in a Large-Scale Cloud Computing Platform
Domenico Cotroneo, Luigi De Simone, Pietro Liguori +1
Cloud computing systems fail in complex and unforeseen ways due to unexpected combinations of events and interactions among hardware and software components. These failures are esp…
Who Evaluates the Evaluators? On Automatic Metrics for Assessing AI-based Offensive Code Generators
Pietro Liguori, Cristina Improta, Roberto Natella +2
AI-based code generators are an emerging solution for automatically writing programs starting from descriptions in natural language, by using deep neural networks (Neural Machine T…
Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation
Pietro Liguori, Cristina Improta, Simona De Vivo +3
Neural Machine Translation (NMT) has reached a level of maturity to be recognized as the premier method for the translation between different languages and aroused interest in diff…
Can We Generate Shellcodes via Natural Language? An Empirical Study
Pietro Liguori, Erfan Al-Hossami, Domenico Cotroneo +3
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…
EVIL: Exploiting Software via Natural Language
Pietro Liguori, Erfan Al-Hossami, Vittorio Orbinato +4
Writing exploits for security assessment is a challenging task. The writer needs to master programming and obfuscation techniques to develop a successful exploit. To make the task…
Enhancing the Analysis of Software Failures in Cloud Computing Systems with Deep Learning
Domenico Cotroneo, Luigi De Simone, Pietro Liguori +1
Identifying the failure modes of cloud computing systems is a difficult and time-consuming task, due to the growing complexity of such systems, and the large volume and noisiness o…
Shellcode_IA32: A Dataset for Automatic Shellcode Generation
Pietro Liguori, Erfan Al-Hossami, Domenico Cotroneo +3
We take the first step to address the task of automatically generating shellcodes, i.e., small pieces of code used as a payload in the exploitation of a software vulnerability, sta…