This is the code for my master's thesis work on improving the robustness and generalization properties of neural networks against adversarial examples. If you use this code in your work, please cite the following:
Sheikh Waqas Akhtar, Saad Rehman, Mahmood Akhtar, Farhan Riaz, Muazzam A. Khan, Qaiser Chaudry, Rupert Young, Improving robustness of neural networks using K-support norm based adversarial training, in IEEE Access, vol. 4, no. , pp. 9501-9511, 2016. doi: 10.1109/ACCESS.2016.2643678