Accelerating AI tasks while preserving data security

SecureLoop is an MIT-developed search engine that can identify an optimal design for a deep neural network accelerator that preserves data security while improving energy efficiency and boosting performance. This could enable device manufacturers to increase the speed of demanding AI applications, while ensuring sensitive data remain safe from attackers. Credits : Image: Jose-Luis Olivares, MIT The SecureLoop search tool efficiently identifies secure designs for hardware that can boost the performance of complex AI tasks, while requiring less energy. With the proliferation of computationally intensive machine-learning applications, such as chatbots that perform real-time language translation, device manufacturers often incorporate specialized hardware components to rapidly move and process the massive amounts of data these systems demand. Choosing the best design for these components, known as deep neural network accelerators, is challenging because they can have an enormous range of design options. This difficult problem becomes even thornier when a designer seeks to add cryptographic operations to keep data safe from attackers. Now, MIT researchers have developed a search engine that can efficiently identify optimal designs for deep neural network accelerators, that preserve data security while boosting performance.