Search Results for author:
Found 5 papers, 0 papers with code
RobustPdM: Designing Robust Predictive Maintenance against Adversarial Attacks
We observe that approximate adversarial training can significantly improve the robustness of PdM models (up to 54X) and outperforms the state-of-the-art PdM defense methods by offering 3X more robustness.
Security-Aware Approximate Spiking Neural Networks
Therefore, researchers in the recent past have extensively studied the robustness and defense of DNNs and SNNs under adversarial attacks.
Improving Reliability of Spiking Neural Networks through Fault Aware Threshold Voltage Optimization
Our proposed FalVolt mitigation method improves the performance of systolicSNNs by enabling them to operate at fault rates of up to 60\%, with a negligible drop in classification accuracy (as low as 0. 1\%).
Is Approximation Universally Defensive Against Adversarial Attacks in Deep Neural Networks?
Approximate computing is known for its effectiveness in improvising the energy efficiency of deep neural network (DNN) accelerators at the cost of slight accuracy loss.
Exploring Fault-Energy Trade-offs in Approximate DNN Hardware Accelerators
Our quantitative analysis shows that the permanent faults exacerbate the accuracy loss in AxDNNs when compared to the accurate DNN accelerators.
