Watch 车人王/Proper-Interpretability

Codes for reproducing the experimental results in "Proper Network Interpretability Helps Adversarial Robustness in Classification", published at ICML 2020

Watch 车人王/Bayesian-Adversarial-Learning

Watch 车人王/Automold--Road-Augmentation-Library

This library augments road images to introduce various real world scenarios that pose challenges for training neural networks of Autonomous vehicles. Automold is created to train CNNs in specific weather and road conditions.

Watch 车人王/Foggy-CycleGAN

Code for MSc Thesis: Simulating Weather Conditions on Digital Images, uses a modified CycleGAN model to synthesize fog on clear images

Watch 车人王/forgery_localization_HLED

Implementation of "Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries" paper.

Watch 车人王/advml-traffic-sign

Code for the 'DARTS: Deceiving Autonomous Cars with Toxic Signs' paper

Watch 车人王/DeepConcolic

Concolic Testing for Deep Neural Networks

Watch 车人王/imbalanced-semi-self

[NeurIPS 2020] Semi-Supervision (Unlabeled Data) & Self-Supervision Improve Class-Imbalanced / Long-Tailed Learning

Watch 车人王/MultiRobustness

Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019

Watch 车人王/MetaAttack_ICLR2020