Latent Adversarial Training

Creator

Creator

Created

Created

2025 Jan 18 2:39

Editor

Editor

Edited

Edited

2025 Jan 18 2:48

Refs

Refs

AT, adversarial perturbations are applied to the model’s latent state instead of its inputs

https://arxiv.org/pdf/2403.05030

targeted LAT

latent-adversarial-training

aengusl • Updated 2024 Dec 5 14:55

https://arxiv.org/pdf/2407.15549

LLM-LAT (LLM Latent Adversarial Training)

Org profile for LLM Latent Adversarial Training on Hugging Face, the AI community building the future.

LLM-LAT (LLM Latent Adversarial Training)

https://huggingface.co/LLM-LAT

LLM-LAT (LLM Latent Adversarial Training)

Recommendations

/////////