Backdoor Mitigation in Decentralized LLM Fine-Tuning

arXiv:2609.37367 · cs.CR, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.CR, cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/tatsu-lab/stanford_alpaca

Terminology

• Fine-Tuning — 22× in this paper · explained in 5 episodes
• Federated Learning — 7× in this paper · explained in 14 episodes
• Instruction Tuning — 7× in this paper · explained in 2 episodes
• Aggregation — 6× in this paper · explained in 1 episode
• Adaptation — 5× in this paper · explained in 1 episode
• Communication Overhead — 4× in this paper · explained in 2 episodes
• Decode — 4× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 3× in this paper · explained in 2 episodes
• Decentralized Learning — 3× in this paper · explained in 2 episodes
• Non-IID Data — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Parameter-Efficient Fine-Tuning — 2× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Decentralized Federated Learning — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Federated Learning (FL) — 1× in this paper · explained in 7 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Local Optimization — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Stochastic Gradient Descent (SGD) — 1× in this paper · explained in 5 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• Weight space Detection of Backdoors in LoRA Adapters
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• BloombergGPT: A Large Language Model for Finance
• Qwen3 Technical Report
• Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs