llm-adaptive-attacks

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

understanding-fast-adv-training

Understanding and Improving Fast Adversarial Training [NeurIPS 2020]

adv-training-corruptions

On the effectiveness of adversarial training against common corruptions [UAI 2022]

long-is-more-for-alignment

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [arXiv, Feb 2024]