VeriDL: Integrity Verification of Outsourced Deep Learning Services (Extended Version)
暂无分享,去创建一个
[1] Zahra Ghodsi,et al. SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud , 2017, NIPS.
[2] Junfeng Yang,et al. DeepXplore: Automated Whitebox Testing of Deep Learning Systems , 2017, SOSP.
[3] Roberto Tamassia,et al. Optimal Verification of Operations on Dynamic Sets , 2011, CRYPTO.
[4] Yoshua. Bengio,et al. Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..
[5] Hassan Takabi,et al. CryptoDL: Deep Neural Networks over Encrypted Data , 2017, ArXiv.
[6] Geoffrey E. Hinton,et al. Deep Learning , 2015, Nature.
[7] Michael Naehrig,et al. CryptoNets: applying neural networks to encrypted data with high throughput and accuracy , 2016, ICML 2016.
[8] Sanjit A. Seshia,et al. Towards Verified Artificial Intelligence , 2016, ArXiv.
[9] Ming Yang,et al. Compressing Deep Convolutional Networks using Vector Quantization , 2014, ArXiv.
[10] Kang Yang,et al. QuickSilver: Efficient and Affordable Zero-Knowledge Proofs for Circuits and Polynomials over Any Field , 2021, IACR Cryptol. ePrint Arch..
[11] Yoshua Bengio,et al. Training deep neural networks with low precision multiplications , 2014 .
[12] Shumo Chu,et al. ZEN: Efficient Zero-Knowledge Proofs for Neural Networks , 2021, IACR Cryptol. ePrint Arch..
[13] Ruby B. Lee,et al. VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting , 2018, ArXiv.