Adversarial Learning for Safety and Security

Literature Survey on Adversarial Attacks and their defense

9 minute read

Published: May 23, 2019

With the coming up of so many applications on which deep learning is proving to be impactful with high accuracies and precision. it is important to ensure it’s safety and security against adversarial attacks. It has been observed that deep neural networks are susceptible to adversarial attacks even in the form of small perturbations which are not conceivable by humans. My literature survey on this topic consists of the following papers and their details :

Literature Survey on Attacks and Defense of Variational Auto-Encoders

5 minute read

Published: May 30, 2019

As discussed in the previous meet, we shifted out attention to generative models, especially Variational autoencoders. So, I thoroughly read the following papers :

Nazi Element Classification

1 minute read

Published: June 09, 2019

The task of last week was to make a dataset for nazism element detection. I was provided with the positive examples, and I had to generate the negative ones. The initial given dataset consisted of around 2800 images in total belonging to various categories like :

• 88_heil_hitler
• nazi_eagle
• nazi_swastikas
• blut_und_ehre
• nazi_flags
• nazi_tattoo
• crossed_grenade_emblem_nazism
• nazi_parade
• schwarze_sonne
• hitler_salute
• nazi_party
• sieg_heil
• meine_ehre_heisst_treue
• nazi_propaganda
• ss_death’s_head
• nazi_bolts
• nazi_rally
• ss_iron_crosses

Semi-Supervised Learning using Variational Auto-Encoders

2 minute read

Published: June 14, 2019

As discussed in the meeting, to improve the accuracy of the classification task, it is required to have a semi-supervised learning. Hence, the following paper provided a cue to this kind of approach:
Resisting Adversarial Attacks Using Gaussian Mixture Variational Autoencoders

Semi-supervised learning using varitional autoencoders results

less than 1 minute read

Published: June 28, 2019

The model trained on data size of 5714 and 36 classes didn’t perform that good. I tried with approaches based on unlabeled data as well as fully labeled data, however, the accuracy still remained low. The graphs are attached as follows :