ML Security PapersLiFeChain: Lightweight Blockchain for Secure and Efficient Federated Lifelong Learning in IoT
Handi Chen , Jing Deng , Xiuzhe Wu , Zhihan Jiang , Xinchen Zhang , Xianhao Chen , Edith C.H. Ngai
Published on arXiv
2509.01434
Data Poisoning Attack
OWASP ML Top 10 — ML02
Key Finding
LiFeChain enhances model robustness against two long-term poisoning attacks while maintaining high efficiency and scalability in federated lifelong learning on IoT devices
LiFeChain (PoMC + Seg-ZA)
Novel technique introduced
The expansion of Internet of Things (IoT) devices constantly generates heterogeneous data streams, driving demand for continuous, decentralized intelligence. Federated Lifelong Learning (FLL) provides an ideal solution by incorporating federated and lifelong learning to overcome catastrophic forgetting. The extended lifecycle of FLL in IoT systems increases their vulnerability to persistent attacks, and these risks may be obscured by performance degradation caused by spatial-temporal data heterogeneity. Moreover, this problem is exacerbated by the standard single-server architecture, as its single point of failure makes it difficult to maintain a reliable audit trail for long-term threats. Blockchain provides a tamper-proof foundation for trustworthy FLL systems. Nevertheless, directly applying blockchain to FLL significantly increases computational and retrieval costs with the expansion of the knowledge base, slowing down the training on IoT devices. To address these challenges, we propose LiFeChain, a lightweight blockchain for secure and efficient federated lifelong learning by providing a tamper-resistant ledger with minimal on-chain disclosure and bidirectional verification. To the best of our knowledge, LiFeChain is the first blockchain tailored for FLL. LiFeChain incorporates two complementary mechanisms: the proof-of-model-correlation (PoMC) consensus on the server, which couples learning and unlearning mechanisms to mitigate negative transfer, and segmented zero-knowledge arbitration (Seg-ZA) on the client, which detects and arbitrates abnormal committee behavior without compromising privacy. LiFeChain is designed as a plug-and-play component that can be seamlessly integrated into existing FLL algorithms. Experimental results demonstrate that LiFeChain not only enhances model performance against two long-term attacks but also sustains high efficiency and scalability.
Key Contributions
- LiFeChain: a lightweight blockchain tailored for federated lifelong learning providing a tamper-resistant ledger with minimal on-chain overhead
- Proof-of-Model-Correlation (PoMC) consensus that couples learning and unlearning to detect and mitigate malicious model updates (memory contamination attacks)
- Segmented Zero-Knowledge Arbitration (Seg-ZA) for privacy-preserving detection of abnormal client committee behavior
🛡️ Threat Analysis
The paper defends against 'memory contamination' attacks — malicious clients injecting corrupted model updates or mislabeled data that gradually degrade the global FL model. The PoMC consensus and Seg-ZA arbitration mechanisms constitute Byzantine-fault-tolerant FL defenses, which directly fall under ML02 (data/model poisoning defense in federated learning).