Author

Bang An

h-index 1 View on Semantic Scholar

We have 1 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

This work proposes HyperSafe, a framework that restores safety behavior by generating a model-specific Safe Side Network (SSN) for each fine-tuned checkpoint by using layer-wise activation fingerprints to capture how fine-tuning changes the model's inner representations.

Aznaur Aliev, Carlos Hinojosa, A. Eldesokey et al. · 0 citations