AT, adversarial perturbations are applied to the model’s latent state instead of its inputs arxiv.orghttps://arxiv.org/pdf/2403.05030targeted LATlatent-adversarial-trainingaengusl • Updated 2024 Dec 5 14:55arxiv.orghttps://arxiv.org/pdf/2407.15549LLM-LAT (LLM Latent Adversarial Training)Org profile for LLM Latent Adversarial Training on Hugging Face, the AI community building the future.https://huggingface.co/LLM-LAT