Corpus ID: 221095725

Trustworthy AI Inference Systems: An Industry Research View.

  title={Trustworthy AI Inference Systems: An Industry Research View.},
  author={R. Cammarota and M. Schunter and Anand Rajan and F. Boemer and 'Agnes Kiss and A. Treiber and Christian Weinert and T. Schneider and E. Stapf and A. Sadeghi and Daniel Demmler and Huili Chen and Siam U. Hussain and Sadegh Riazi and F. Koushanfar and Saransh Gupta and Tajan Simunic Rosing and K. Chaudhuri and Hamid Nejatollahi and N. Dutt and M. Imani and K. Laine and Anuj Dubey and Aydin Aysu and F. Hosseini and C. Yang and Eric Wallace and P. Norton},
  journal={arXiv: Cryptography and Security},
  • R. Cammarota, M. Schunter, +25 authors P. Norton
  • Published 2020
  • Computer Science
  • arXiv: Cryptography and Security
  • In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized inferences to aid their decision, while at the same time utilizing appropriate security protection mechanisms for AI models. Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time. To approach the… CONTINUE READING


    Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
    • 17
    • PDF
    Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
    • 84
    • PDF
    CryptoSPN: Privacy-preserving Sum-Product Network Inference
    • 4
    • PDF
    SANCTUARY: ARMing TrustZone with User-space Enclaves
    • 30
    • PDF
    Stealing Machine Learning Models via Prediction APIs
    • 609
    • PDF
    HEAX: An Architecture for Computing on Encrypted Data
    • 11
    • PDF
    Toward Scalable Fully Homomorphic Encryption Through Light Trusted Computing Assistance
    • 2
    • PDF
    Fairplay - Secure Two-Party Computation System
    • 616
    • PDF