SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation

A new benchmark, SPQR, evaluates the stability of safety alignment in text-to-image models when subjected to common downstream fine-tuning techniques.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.