SecDD: Efficient and Secure Method for Remotely Training Neural Networks
We leverage what are typically considered the worst qualities of deep learning algorithms - high computational cost, requirement for large data, no explainability, high dependence on hyper-parameter choice, overfitting, and vulnerability to adversarial perturbations - in order to create a method for the secure and efficient training of remotely deployed neural networks over unsecured channels.
Code (1)
Similar Papers 제목 키워드 기반
An Observer-Based Key Agreement Scheme for Remotely Controlled Mobile Robots
Remotely controlled mobile robots are important examples of Cyber-Physical Systems (CPSs). Recently, these robots are being deployed in many safety critical applications. Therefore, ensuring their cyber-security is of pa…
Robust Remote Sensing Scene Classification with Multi-View Voting and Entropy Ranking
Deep convolutional neural networks have been widely used in scene classification of remotely sensed images. In this work, we propose a robust learning method for the task that is secure against partially incorrect catego…
Scene ClassificationA multiagent based framework secured with layered SVM-based IDS for remote healthcare systems
Since the number of elderly and patients who are in hospitals and healthcare centers are growing, providing efficient remote healthcare services seems very important. Currently, most such systems benefit from the distrib…
Intrusion DetectionRobust two-degrees-of-freedom control of hydraulic drive with remote wireless operation
In this paper, a controller design targeting the remotely operated hydraulic drive system is presented. A two-degrees-of-freedom PID position controller is used, which is designed so that to maximize the integral action …
PositionSecure state estimation over Markov wireless communication channels (extended version)
This note studies state estimation in wireless networked control systems with secrecy against eavesdropping. Specifically, a sensor transmits a system state information to the estimator over a legitimate user link, and a…
State Estimation