Search Results for author:
Found 3 papers, 1 papers with code
Semantic-Based Neural Network Repair
The results show that we are able to repair 100% of a set of randomly generated neural networks (which are produced with an existing AI framework testing approach) effectively and efficiently (with an average repair time of 21. 08s) and 93. 75% of a collection of real neural network bugs (with an average time of 3min 40s).
ExAIS: Executable AI Semantics
In this new paradigm, AI frameworks such as TensorFlow and PyTorch play a key role, which is as essential as the compiler for traditional programs.
The Security Reference Architecture for Blockchains: Towards a Standardized Model for Studying Vulnerabilities, Threats, and Defenses
We propose the security reference architecture (SRA) for blockchains, which adopts a stacked model (similar to the ISO/OSI) describing the nature and hierarchy of various security and privacy aspects.
Cryptography and Security Distributed, Parallel, and Cluster Computing
