Decentralized method detects and blocks backdoors in shared language models
Backdoor Mitigation in Decentralized LLM Fine-Tuning
Cryptography and SecurityMachine Learning
Summary
When organizations train shared language models together, some can sneak in hidden backdoors that make the model behave badly when a secret trigger appears. The paper shows that even one bad participant can affect many others who never saw the bad data. The authors propose Chorus, a way for each participant to spot and reject these backdoors by working together and comparing the behavior of updates before accepting them. Their tests show Chorus drastically reduces attacks without extra data or revealing secrets.
What this means in practice
- •For machine learning engineers: Protect collaborative decentralized language model training from hidden backdoors without sharing data or triggers.
- •For security teams in ai companies: Detect and block backdoor attacks in peer-to-peer model fine-tuning to maintain model integrity.
Authors
Sayan Biswas, Jade Garcia Bourrée, Rachid Guerraoui, Maxime Jacovella, Anne-Marie Kermarrec, Sathwika Peechara, Martijn de Vos, Milos Vujasinovic
Abstract
Decentralized large language model (LLM) fine-tuning lets organizations collaboratively train a shared LLM on data they cannot pool, without a central coordinator. In every round, each node exchanges a trainable adapter with its neighbors over a communication graph, and then aggregates them. This setting, however, is vulnerable to propagated backdoors, which is a hidden behavior that lets a model perform normally on clean inputs but produce an attacker-chosen output whenever a secret trigger appears. We show that a single node poisoning its own model can backdoor adapters of nodes that have never seen a poisoned example, making them refuse prompts that contain a secret trigger. We present Chorus, a decentralized mechanism that lets each node detect and reject backdoored adapters from its neighbors before aggregation, without requiring shared validation data or any knowledge of the attacker's trigger or target. Chorus judges each adapter by its behavior, using the receiver's own adapter as a trusted reference. Crucially, no node in Chorus judges adapters alone: the receivers of each adapter update probe it independently, pool their findings in the neighborhood, and vote to make a decision. So a backdoor that slips past one receiver is still caught by the others. We evaluate the effectiveness of Chorus using two instruction-tuning datasets and LLM architectures, and against a state-of-the-art baseline. Chorus cuts the average attack success rate (ASR) of the attacker's neighbors from 48-63% to at most 2.2%, within 0.6 percentage points of an omniscient oracle that knows the exact malicious nodes. Even the worst-affected honest node never exceeds 10% ASR, the same bound as the oracle, against up to 78% without defense. This all comes at a negligible communication overhead.