Hail To The Thief: Exploring Attacks And Defenses In Decentralised GRPO | Awesome LLM Papers Add your paper to Awesome LLM Papers

Awesome LLM Papers

A continuously updated collection of research papers on LLMs. Maintained by Sean Moran.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Hail To The Thief: Exploring Attacks And Defenses In Decentralised GRPO

Nikolay Blagoev, Oğuzhan Ersoy, Lydia Yiyu Chen . No Venue 2025

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Compositional Generalization Efficiency Image Text Integration Interdisciplinary Approaches Multimodal Semantic Representation Reinforcement Learning Security Training Techniques

Group Relative Policy Optimization (GRPO) has demonstrated great utilization in post-training of Large Language Models (LLMs). In GRPO, prompts are answered by the model and, through reinforcement learning, preferred completions are learnt. Owing to the small communication volume, GRPO is inherently suitable for decentralised training as the prompts can be concurrently answered by multiple nodes and then exchanged in the forms of strings. In this work, we present the first adversarial attack in decentralised GRPO. We demonstrate that malicious parties can poison such systems by injecting arbitrary malicious tokens in benign models in both out-of-context and in-context attacks. Using empirical examples of math and coding tasks, we show that adversarial attacks can easily poison the benign nodes, polluting their local LLM post-training, achieving attack success rates up to 100% in as few as 50 iterations. We propose two ways to defend against these attacks, depending on whether all users train the same model or different models. We show that these defenses can achieve stop rates of up to 100%, making the attack impossible.

Similar Work