Anvesh Reddy Yenugu

Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning

This work proposes VaccineBooster, a single alignment procedure that combines embedding perturbation and weight-level gradient attenuation within each training step, and indicates a trade-off: embedding perturbation primarily reduces flagged harmful content, whereas gradient attenuation primarily preserves explicit ref...