8 papers
Characterizing Software Aging in GPU-Based LLM Serving Systems
Domenico Cotroneo, Bojan Cukic
This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems. Traditional aging studies focus on CPU-centric software with relatively regul…
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…
What Makes Software Bugs Escape Testing? Evidence from a Large-Scale Empirical Study
Domenico Cotroneo, Giuseppe De Rosa, Cristina Improta +1
Understanding how software defects manifest and evolve in production environments is critical for improving reliability. While previous research has largely focused on pre-release…
Elevating Cyber Threat Intelligence against Disinformation Campaigns with LLM-based Concept Extraction and the FakeCTI Dataset
Domenico Cotroneo, Roberto Natella, Vittorio Orbinato
The swift spread of fake news and disinformation campaigns poses a significant threat to public trust, political stability, and cybersecurity. Traditional Cyber Threat Intelligence…
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…