farshad-jafari / amirkabir-artificial-intelligence-summer-summit-2020

Resources for the AAISS 2020 presentation of fundamentals of Adversarial Machine Learning, its libraries, papers and code samples.

Amirkabir Artificial Intelligence Summer Summit 2020

The material used in my representation Introduction to Fundamentals, Applications and Libraries of Adversarial Attacks for AAISS 2020.

Link to the presentation video: https://aparat.com/v/NTrEG

Papers explained:

• FGSM: https://arxiv.org/abs/1412.6572
• DeepFool: https://arxiv.org/abs/1511.04599
• Boundary Attack: https://arxiv.org/abs/1712.04248
• Audio Adversarial Examples: https://arxiv.org/abs/1801.01944
• Ensemble Adversarial Training: https://arxiv.org/abs/1705.07204
• Defensive Distillation: https://arxiv.org/abs/1511.04508
• Stateful Defense: https://arxiv.org/abs/1907.05587

Code Resources:

• Audio Adversarial Examples: https://github.com/carlini/audio_adversarial_examples
• Defensive Distillation: https://github.com/carlini/nn_robust_attacks
• Stateful Detection: https://github.com/schoyc/blackbox-detection
• FGSM: https://www.tensorflow.org/tutorials/generative/adversarial_fgsm
• Neural Structure Learning for Adversarial regularization: https://www.tensorflow.org/neural_structured_learning/tutorials/adversarial_keras_cnn_mnist