2 papers
cs.CR2022
BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks
Behnam Ghavami, Mani Sadati, Mohammad Shahidzadeh +2
Adversarial bit-flip attack (BFA) on Neural Network weights can result in catastrophic accuracy degradation by flipping a very small number of bits. A major drawback of prior bit f…
cs.CR2021
An Efficient Communication Protocol for FPGA IP Protection
Farzane Khajuyi, Behnam Ghavami, Human Nikmehr
We introduce a protection-based IP security scheme to protect soft and firm IP cores which are used on FPGA devices. The scheme is based on Finite State Machin (FSM) obfuscation an…