Author

George Drayson

1 paper indexed here

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.

#machine learning Preprint Sep 2026

Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation

This work proposes NEEDLE, a training-free method for targeted backdoor removal that achieves the lowest mean Attack Success Rate (ASR) among the evaluated defences, including 0% on challenging code injection attacks, while resulting in the lowest KL divergence and minimal changes in capability and safety.

Minoo Kim, Vasileios Lampos, George Drayson · 0 citations