Using Explainability Methods to Uncover Shortcuts in Language Models - WebThesis

WebThesis

Using Explainability Methods to Uncover Shortcuts in Language Models

Using Explainability Methods to Uncover Shortcuts in Language Models

Fabio Marmello

Using Explainability Methods to Uncover Shortcuts in Language Models.

Rel. Luca Vassio, Marco Mellia, Idilio Drago. Politecnico di Torino, Master of science program in Cybersecurity, 2025

[thumbnail of Tesi_di_laurea]

Preview

PDF (Tesi_di_laurea) - Thesis
Licence: Creative Commons Attribution Non-commercial No Derivatives.
Download (5MB) | Preview

Abstract

Innovation on LLM for smart firewall

Publication type

Electronic

URI

https://webthesis.biblio.polito.it/id/eprint/38707

Modify record (reserved for operators)

Modify record (reserved for operators)