Follow
Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning. (arXiv:2312.05720v2 [cs.LG] UPDATED)
Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning. (arXiv:2312.05720v2 [cs.LG] UPDATED)