DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-Based Incentive

By Jiasi Weng, Jian Weng, Ming Li, Weiqi Luo. IEEE Transactions on Dependable and Secure Computing, 2019

567 citations recorded by the source corpus.

Deep learning can achieve higher accuracy than traditional machine learning algorithms in a variety of machine learning tasks. Recently, privacy-preserving deep learning has drawn tremendous attention from information security community, in which neither training data nor the training model is expected to be exposed. Federated learning is a popular learning mechanism, where multiple parties upload local gradients to a server and the server updates model parameters with the collected gradients. However, there are many security problems neglected in federated learning, for example, the participants may behave incorrectly in gradient collecting or parameter updating, and the server may be malicious as well. In this article, we present a distributed, secure, and fair deep learning framework named DeepChain to solve these problems. DeepChain provides a value-driven incentive mechanism based on Blockchain to force the participants to behave correctly. Meanwhile, DeepChain guarantees data privacy for each participant and provides auditability for the whole training process. We implement a prototype of DeepChain and conduct experiments on a real dataset for different settings, and the results show that our DeepChain is promising.

Subfields: Artificial Intelligence, Building and Construction, Information Systems

View Paper: https://www.semanticscholar.org/paper/07f229cc6e5b80fc8ffbbb3e4db85142466f55a9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Building and Construction

In Information Systems

Citations in the corpus

CrowdBC: A Blockchain-Based Decentralized Framework for Crowdsourcing (2019, background): “Blockchain technology provides a new direction for us to reduce the role of the middleman in current society [33].”
Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “A similar blockchain-based model is also introduced in [169] to provide data confidentiality, computation auditability, and incentives for the participants of FL.”
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, background): “The incentive mechanisms may be helpful [79], [80], [185].”
Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges (2022, unknown): “In contrast to SFL protocols, Blockchain based FL enables a decentralized FL environment without single point of failure risks and improved scalability [153, 154].”
Mobile Edge Computing, Blockchain and Reputation-based Crowdsourcing IoT Federated Learning: A Secure, Decentralized and Privacy-preserving System (2019, background): “Weng et al. [9] proposed a deepchain system for collaborative learning.”
Towards Fair and Privacy-Preserving Federated Deep Models (2019, background): “[15], [16] investigated privacy-preserving deep learning on blockchain.”
Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices (2019, background): “For example, Weng et al. [21] proposed a system called DeepChain for the collaborative learning.”
Artificial Intelligence for the Metaverse: A Survey (2022, unknown): “For example, DeepChain [98], a CNN-based”
Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challenges (2021, background): “In line with the discussion, the work in [60] proposes a scalable privacy architecture for blockchain-based distributed learning by providing validation on the sources quality and conﬁdentiality on the model within a privacy-preserved coalition among untrusted learning parties.”
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly (2023, methodology): “…efforts that utilize traditional Privacy-Enhancing Technologies (e.g., zero-knowledge proofs, differential privacy, and federated learning) to tackle privacy challenges posed by LLMs. Exploring additional PETs techniques, whether they are established methods or innovative approaches, to…”