Reaching Data Confidentiality and Model Accountability on the CalTrain
arXiv:1812.03230
Abstract
Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusting multi-party participants. Data confidentiality is guaranteed by retaining private training data on each participant's local infrastructure. However, this approach to achieving data confidentiality makes today's DCL designs fundamentally vulnerable to data poisoning and backdoor attacks. It also limits DCL's model accountability, which is key to backtracking the responsible "bad" training data instances/contributors. In this paper, we introduce CALTRAIN, a Trusted Execution Environment (TEE) based centralized multi-party collaborative learning system that simultaneously achieves data confidentiality and model accountability. CALTRAIN enforces isolated computation on centrally aggregated training data to guarantee data confidentiality. To support building accountable learning models, we securely maintain the links between training instances and their corresponding contributors. Our evaluation shows that the models generated from CALTRAIN can achieve the same prediction accuracy when compared to the models trained in non-protected environments. We also demonstrate that when malicious training participants tend to implant backdoors during model training, CALTRAIN can accurately and precisely discover the poisoned and mislabeled training data that lead to the runtime mispredictions.
References in corpus (18)
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Deep Learning with Differential Privacy
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- How To Backdoor Federated Learning
- Poisoning Attacks against Support Vector Machines
- Mitigating Sybils in Federated Learning Poisoning
- SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Execution
- Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
- Support Vector Machines under Adversarial Label Contamination
- Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
- A Berkeley View of Systems Challenges for AI
- Chiron: Privacy-preserving Machine Learning as a Service
- Efficient Deep Learning on Multi-Source Private Data
- Contamination Attacks and Mitigation in Multi-Party Machine Learning
- Machine Learning Models that Remember Too Much