Rafael Pinot

Adversarial Evasion on LLMs

Byzantine-Robust Federated Representation Learning

We study federated learning (FL) with adversarial clients, where the goal is to minimize the average loss of the honest (non-adversarial) clients without knowing their identity. Under heterogeneity, a single shared model parameter is statistically inappropriate: it cannot capture the distinct data-generating processes...

On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression

It is demonstrated that, for any $(f,\kappa)$-robust aggregator with coefficient $\kappa = O(f/n)$, where f is the number of adversarial clients and n is the total number of clients, convergence holds after an explicit sample burn-in.