Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Domenico Cotroneo

Domenico Cotroneo

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Software Eng.×3Crypto×2AI×2ML×1

Frequent co-authors

Pietro Liguori2×
Francesco Crescenzo Grasso1×
Roberto Natella1×
Bojan Cukic1×
Cristina Carleo1×
Naghmeh Ivaki1×

Research Timeline

2026
Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

The paper introduces 'abliteration,' a weight editing technique that successfully bypasses the refusal mechanism of safety-aligned Code LLMs, enabling scalable synthesis of vulnerable code from safe inputs.

Characterizing Software Aging in GPU-Based LLM Serving Systems

This paper studies software aging in GPU-based LLM serving systems using a 216-hour campaign.

VulDec: Vulnerability Detection in Binaries via Neural Decompilation

The paper introduces VulDec, a framework for binary vulnerability detection using neural decompilation.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGcs.SEEmpiricalRecentOct 24, 2026

VulDec: Vulnerability Detection in Binaries via Neural Decompilation

Francesco Crescenzo Grasso, Pietro Liguori, Roberto Natella, Domenico Cotroneo

The paper introduces VulDec, a framework for binary vulnerability detection using neural decompilation.

View →
cs.SEcs.AIEmpirical
Recent
Jun 10, 2026

Characterizing Software Aging in GPU-Based LLM Serving Systems

Domenico Cotroneo, Bojan Cukic

This paper studies software aging in GPU-based LLM serving systems using a 216-hour campaign.

View →
cs.CRcs.AIcs.SERecentJun 3, 2026

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

Cristina Carleo, Pietro Liguori, Naghmeh Ivaki, Domenico Cotroneo

The paper introduces 'abliteration,' a weight editing technique that successfully bypasses the refusal mechanism of safety-aligned Code LLMs, enabling scalable synthesis of vulnerable code from safe i…

View →