Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clients
This research demonstrates a novel attack where a reinforcement learning agent manipulates client sensor observations to induce repetitive, clustered memory updates on a federated learning server. These updates, facilitated by communication optimizations like sparse gradients and RDMA, create predictable memory access patterns that can be used to remotely trigger Rowhammer attacks. The finding shows that physical interference at the client level can lead to server memory corruption.