Oguzhan Ersoy

Our method, F-TIS, enables diverse models to collaborate in decentralised GRPO by combining truncated importance sampling with filtering. Across model-size, expertise, and PEFT heterogeneity, F-TIS matches on-policy convergence and, in some cases, improves out-of-distribution reasoning.

Most works on adversarial robustness in distributed training focus on data parallelism, e.g., poisoned gradients, malicious clients, or aggregation attacks. Pipeline parallelism has a different attack surface. Here, the model itself is partitioned across nodes.

Our paper, “Hail to the Thief: Exploring Attacks and Defenses in Decentralized GRPO”, is the first systematic study that explores both the attack vectors and defense strategies in decentralised reinforcement learning for Large Language Models (LLMs).