Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks

no code implementations • 25 Apr 2023 • Ferheen Ayaz, Idris Zakariyya, José Cano, Sye Loong Keoh, Jeremy Singer, Danilo Pau, Mounia Kharbouche-Harrari

This paper reports the results of devising a tiny DNN model, robust to adversarial black and white box attacks, trained with an automatic quantizationaware training framework, i. e. QKeras, with deep quantization loss accounted in the learning loop, thereby making the designed DNNs more accurate for deployment on tiny devices.

Adversarial Robustness Quantization