SPQR: A Multi-dimensional Benchmark for Safety Alignment Under Benign Model Adaptation

Read full text
Authors: Mohammed Talha Alam, Nada Saadi, Fahad Shamshad, Nils Lukas, Karthik Nandakumar, Fakhri Karray, Samuele Poppi
Cited by: 0

Fields of Study & Subjects

Generative Adversarial Networks and Image Synthesis Adversarial Robustness in Machine Learning Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Lecture notes in computer science
Pages
60–77
Publication date
1 January 2026
Language
EN