activity
20192026
most citedEvolving Robust Neural Architectures to Defend from Adversarial Attacks

19 citations · 36 across the 18 of their papers we have counts for

collaborators
Showing 2019Show all

7 papers · 1 filter

cs.NE2019★ 19 cited

Evolving Robust Neural Architectures to Defend from Adversarial Attacks

Shashank Kotyan, Danilo Vasconcellos Vargas

Neural networks are prone to misclassify slightly modified input images. Recently, many defences have been proposed, but none have improved the robustness of neural networks consis…

cs.CV2019★ 1 cited

Representation Quality Of Neural Networks Links To Adversarial Attacks and Defences

Shashank Kotyan, Danilo Vasconcellos Vargas, Moe Matsuki

Neural networks have been shown vulnerable to a variety of adversarial algorithms. A crucial step to understanding the rationale for this lack of robustness is to assess the potent…

cs.LG2019★ 9 cited

Adversarial Robustness Assessment: Why both and Attacks Are Necessary

Shashank Kotyan, Danilo Vasconcellos Vargas

There exists a vast number of adversarial attacks and defences for machine learning algorithms of various types which makes assessing the robustness of algorithms a daunting task.…

cs.RO2019

Self Training Autonomous Driving Agent

Shashank Kotyan, Danilo Vasconcellos Vargas, Venkanna U

Intrinsically, driving is a Markov Decision Process which suits well the reinforcement learning paradigm. In this paper, we propose a novel agent which learns to drive a vehicle wi…

eess.SP2019

Analysis and Comparison of Different Fuzzy Inference Systems used in Decision Making for Secondary Users in Cognitive Radio Network

Ashish Upadhyay, Shashank Kotyan, Shrivishal Tripathi +1

Spectrum scarcity is one of the major challenges that the modern communication engineers are going through because of inefficient utilization of allocated frequency spectrum. The s…

cs.HC2019★ 1 cited

HAUAR: Home Automation Using Action Recognition

Shashank Kotyan, Nishant Kumar, Pankaj Kumar Sahu +1

Today, many of the home automation systems deployed are mostly controlled by humans. This control by humans restricts the automation of home appliances to an extent. Also, most of…

cs.HC2019

Drishtikon: An advanced navigational aid system for visually impaired people

Shashank Kotyan, Nishant Kumar, Pankaj Kumar Sahu +1

Today, many of the aid systems deployed for visually impaired people are mostly made for a single purpose. Be it navigation, object detection, or distance perceiving. Also, most of…