AI safety researcher

Battista Biggio

University of Cagliari

Google Scholar dblp ORCID

Last 12 months12 papers

Evaluation and benchmarks 2Other 1Defenses 1

AI safety papers from the last year

On this site: 83 papers

September 2026

Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
Sep 21OtherarXiv ↗
Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness
Sep 8DefensesarXiv ↗

July 2026

EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability
Jul 27Evaluation and benchmarksarXiv ↗
Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation
Jul 22Evaluation and benchmarksarXiv ↗

June 2026

DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors
Jun 25arXiv ↗

May 2026

Latent-space Attacks for Refusal Evasion in Language Models
May 20arXiv ↗

March 2026

Label-efficient Training Updates for Malware Detection over Time
Mar 30arXiv ↗

February 2026

December 2025

Counterfeit Answers: Adversarial Forgery against OCR-Free Document Visual Question Answering
Dec 4arXiv ↗

November 2025

SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
Nov 11arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.