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

Antonino Nocera

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Crypto×5AI×3ML×2NLP×1

Frequent co-authors

Serena Nicolazzo3×
Marco Arazzi3×
Vignesh Kumar Kembu3×
Asmitha K. A.2×
Vinod P.2×
Saraga Sakthidharan2×

Research Timeline

2026
SecureBreak -- A dataset towards safe and secure models

The paper introduces SecureBreak, a manually annotated, safety-oriented dataset designed to help detect harmful outputs from large language models (LLMs) that bypass existing security alignments.

Security in LLM-as-a-Judge: A Comprehensive SoK

This paper provides the first comprehensive Systematization of Knowledge (SoK) on the security aspects of LLM-as-a-Judge (LaaJ) systems, identifying key vulnerabilities and proposing a taxonomy for future research.

Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks

The paper proposes a certifiably robust malware detection framework using randomized smoothing and feature ablation to guarantee detection accuracy against metamorphic evasion attacks.

You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation

The paper introduces NeWTral, a framework that restores safety alignment to specialized LLM adapters without sacrificing their domain-specific knowledge, achieving a significant reduction in attack success rates while maintaining high fidelity.

A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution

A unified multi-task malware analysis framework based on Mixture of Experts (MoE) architectures is proposed for malware family classification, packed versus unpacked detection, and malware versus benign identification.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIEmpiricalRecentJun 29, 2026

A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution

Jithin S., Roshin Sleeba C., Anvin Mariya P. B., Asmitha K. A. +3 more

A unified multi-task malware analysis framework based on Mixture of Experts (MoE) architectures is proposed for malware family classification, packed versus unpacked detection, and malware versus beni…

View →
cs.CRRecent
May 6, 2026

You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation

Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera, Stjepan Picek +1 more

The paper introduces NeWTral, a framework that restores safety alignment to specialized LLM adapters without sacrificing their domain-specific knowledge, achieving a significant reduction in attack su…

View →
cs.CRcs.LGRecentApr 22, 2026

Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks

Nandakrishna Giri, Asmitha K. A., Serena Nicolazzo, Antonino Nocera +1 more

The paper proposes a certifiably robust malware detection framework using randomized smoothing and feature ablation to guarantee detection accuracy against metamorphic evasion attacks.

View →
cs.CRcs.AIRecentMar 31, 2026

Security in LLM-as-a-Judge: A Comprehensive SoK

Aiman Al Masoud, Antony Anju, Marco Arazzi, Mert Cihangiroglu +5 more

This paper provides the first comprehensive Systematization of Knowledge (SoK) on the security aspects of LLM-as-a-Judge (LaaJ) systems, identifying key vulnerabilities and proposing a taxonomy for fu…

View →
cs.CRcs.AIcs.CLRecentMar 23, 2026

SecureBreak -- A dataset towards safe and secure models

Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera

The paper introduces SecureBreak, a manually annotated, safety-oriented dataset designed to help detect harmful outputs from large language models (LLMs) that bypass existing security alignments.

View →