AI models are increasingly prevalent in high-stakes environments, necessitating1 thorough assessment oftheir capabilities and risks.

Here, we propose that extra-synaptic diffusion of local neuromodulators such as neuropeptides may afford an effective mode of backpropagation lying within the bounds of biological plausibility.

In this work, we introduce the Assisted Learning framework for organizations to assist each other in supervised learning tasks without revealing anyorganization'salgorithm,data,oreventask.

Albeit, the objective of the learner is to achieve low task loss at an individual instance level.