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

Maria Rosaria Briglia

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2AI×2ML×1Vision×1

Frequent co-authors

Igor Maljkovic2×
Antonio Emanuele Cinà2×
Iacopo Masi2×
Fabio Roli2×
Luca Oneto1×

Research Timeline

2026
Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization

The paper introduces a robust, two-part framework (HyPE and HyPS) using hyperbolic geometry to efficiently detect and sanitize malicious prompts targeting Vision-Language Models (VLMs).

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering

Researchers demonstrate how malicious providers can embed architectural backdoors into Vision--Language Model (VLM) supply chains through representation steering.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.LGNEWEmpiricalJul 28, 2026

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering

Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cinà, Luca Oneto +2 more

Researchers demonstrate how malicious providers can embed architectural backdoors into Vision--Language Model (VLM) supply chains through representation steering.

View →
cs.CRcs.AI
cs.CV
Recent
Apr 7, 2026

Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization

Igor Maljkovic, Maria Rosaria Briglia, Iacopo Masi, Antonio Emanuele Cinà +1 more

The paper introduces a robust, two-part framework (HyPE and HyPS) using hyperbolic geometry to efficiently detect and sanitize malicious prompts targeting Vision-Language Models (VLMs).

View →