Skip to content
conftrace_

harmful data detection

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (1) embedding perturbation (1) harmful fine-tuning (1) embedding drift (1) robust alignment (1) model robustness (1) adversarial robustness (1) adversarial learning (1)

Papers

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack NeurIPS 2024