1 code implementation • 7 Feb 2024 • Shashank Kotyan, PoYuan Mao, Danilo Vasconcellos Vargas
Deep neural networks are exploited using natural adversarial samples, which have no impact on human perception but are misclassified.
Evolutionary Algorithms Misclassification Rate - Natural Adversarial Samples
1 code implementation • 7 Dec 2023 • Shashank Kotyan, Ueda Tatsuya, Danilo Vasconcellos Vargas
While these methods effectively capture the overall sample distribution in the entire learned latent space, they tend to distort the structure of sample distributions within specific classes in the subset of the latent space.
no code implementations • 24 Nov 2023 • Mao Po-Yuan, Shashank Kotyan, Tham Yik Foong, Danilo Vasconcellos Vargas
To understand the impact of the initial seed vector on generated samples, we propose a reliability evaluation framework that evaluates the generated samples of a diffusion model when the initial seed vector is subjected to various synthetic shifts.
no code implementations • 22 Nov 2023 • Tham Yik Foong, Shashank Kotyan, Po Yuan Mao, Danilo Vasconcellos Vargas
Recent advances in text-to-image generators have led to substantial capabilities in image generation.
no code implementations • 16 Nov 2023 • Shashank Kotyan, Danilo Vasconcellos Vargas
Through this contribution, the paper aims to foster a deeper understanding of neural network limitations and proposes a practical approach to enhance their resilience in the face of evolving and unpredictable conditions.
no code implementations • 14 Nov 2023 • Shashank Kotyan, Danilo Vasconcellos Vargas
Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision.
no code implementations • 1 Nov 2023 • Shashank Kotyan, Danilo Vasconcellos Vargas
In conclusion, this work contributes to the ongoing research on Vision Transformers by introducing Dynamic Scanning Augmentation as a technique for improving the accuracy and robustness of ViT.
no code implementations • 7 Aug 2023 • Shashank Kotyan
A particular branch of research, Adversarial Machine Learning, exploits and understands some of the vulnerabilities that cause the neural networks to misclassify for near original input.
no code implementations • 10 Jun 2021 • Shashank Kotyan, Danilo Vasconcellos Vargas
We also analyse how different adversarial samples distort the attention of the neural network compared to original samples.
no code implementations • 25 Sep 2019 • Danilo Vasconcellos Vargas, Shashank Kotyan, Moe Matsuki
The main idea lies in the fact that some features are present on unknown classes and that unknown classes can be defined as a combination of previous learned features without representation bias (a bias towards representation that maps only current set of input-outputs and their boundary).
1 code implementation • 27 Jun 2019 • Shashank Kotyan, Danilo Vasconcellos Vargas
By creating a novel neural architecture search with options for dense layers to connect with convolution layers and vice-versa as well as the addition of concatenation layers in the search, we were able to evolve an architecture that is inherently accurate on adversarial samples.
1 code implementation • 15 Jun 2019 • Shashank Kotyan, Danilo Vasconcellos Vargas, Moe Matsuki
A crucial step to understanding the rationale for this lack of robustness is to assess the potential of the neural networks' representation to encode the existing features.
1 code implementation • 14 Jun 2019 • 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.
no code implementations • 26 Apr 2019 • Shashank Kotyan, Danilo Vasconcellos Vargas, Venkanna U
Intrinsically, driving is a Markov Decision Process which suits well the reinforcement learning paradigm.
no code implementations • 23 Apr 2019 • Shashank Kotyan, Nishant Kumar, Pankaj Kumar Sahu, Venkanna Udutalapally
In this paper, we propose an aid system developed using object detection and depth perceivement to navigate a person without dashing into an object.
no code implementations • 23 Apr 2019 • Shashank Kotyan, Nishant Kumar, Pankaj Kumar Sahu, Venkanna Udutalapally
Today, many of the home automation systems deployed are mostly controlled by humans.