MERCURY: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator
DNN accelerators have been widely deployed in many scenarios to speed up the inference
process and reduce the energy consumption. One big concern about the usage of the …
process and reduce the energy consumption. One big concern about the usage of the …
UniGuard: A Unified Hardware-oriented Threat Detector for FPGA-based AI Accelerators
The proliferation of AI technology gives rise to a variety of security threats, significantly
compromising the confidentiality and integrity of AI applications. Existing software-based …
compromising the confidentiality and integrity of AI applications. Existing software-based …
A Unified Hardware-based Threat Detector for AI Accelerators
The proliferation of AI technology gives rise to a variety of security threats, which significantly
compromise the confidentiality and integrity of AI models and applications. Existing software …
compromise the confidentiality and integrity of AI models and applications. Existing software …
Design of a secure kernel for constrained devices
N Dejon - 2022 - theses.hal.science
This thesis invests the field of cybersecurity for small computer systems (embedded
systems/connected objects/low-end devices, of type microcontroller) and more precisely …
systems/connected objects/low-end devices, of type microcontroller) and more precisely …