Giorgio Piras

Orcid: 0000-0001-8225-6138

According to our database1, Giorgio Piras authored at least 18 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Latent-space Attacks for Refusal Evasion in Language Models.
CoRR, May, 2026

Evaluating line-level localization ability of learning-based code vulnerability detection models.
Mach. Learn., April, 2026

Label-efficient Training Updates for Malware Detection over Time.
CoRR, March, 2026

On the robustness of adversarial training against uncertainty attacks.
Pattern Recognit., 2026

SAGE-5GC: Security-Aware Guidelines for Evaluating Anomaly Detection in the 5G Core Network.
Proceedings of the Joint National Conference on Cybersecurity (ITASEC & SERICS 2026), 2026

SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
S2AP: Score-space Sharpness Minimization for Adversarial Pruning.
CoRR, October, 2025

LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback.
CoRR, October, 2025

Regression-aware Continual Learning for Android Malware Detection.
CoRR, July, 2025

Adversarial pruning: improving evaluations and methods.
PhD thesis, 2025

Adversarial pruning: A survey and benchmark of pruning methods for adversarial robustness.
Pattern Recognit., 2025

HO-FMN: Hyperparameter optimization for fast minimum-norm attacks.
Neurocomputing, 2025

An Experimental Analysis of Semi-supervised Learning for Malware Detection.
Proceedings of the Joint National Conference on Cybersecurity (ITASEC & SERICS 2025), 2025

2023
AI Security and Safety: The PRALab Research Experience.
Proceedings of the Italia Intelligenza Artificiale, 2023

Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks.
Proceedings of the International Conference on Machine Learning and Cybernetics, 2023

Adversarial Attacks Against Uncertainty Quantification.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization.
Proceedings of the 31st European Symposium on Artificial Neural Networks, 2023

2022
Explaining Machine Learning DGA Detectors from DNS Traffic Data.
Proceedings of the Italian Conference on Cybersecurity (ITASEC 2022), 2022


  Loading...