2 citations · 4 across the 10 of their papers we have counts for
11 papers
Linking Robustness and Generalization: A k* Distribution Analysis of Concept Clustering in Latent Space for Vision Models
Shashank Kotyan, Pin-Yu Chen, Danilo Vasconcellos Vargas
Most evaluations of vision models use indirect methods to assess latent space quality. These methods often involve adding extra layers to project the latent space into a new one. T…
Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models!
Shashank Kotyan, Po-Yuan Mao, Pin-Yu Chen +1
Deep neural networks can be exploited using natural adversarial samples, which do not impact human perception. Current approaches often rely on deep neural networks' white-box natu…
k* Distribution: Evaluating the Latent Space of Deep Neural Networks using Local Neighborhood Analysis
Shashank Kotyan, Tatsuya Ueda, Danilo Vasconcellos Vargas
Most examinations of neural networks' learned latent spaces typically employ dimensionality reduction techniques such as t-SNE or UMAP. These methods distort the local neighborhood…
Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion Models
Mao Po-Yuan, Shashank Kotyan, Tham Yik Foong +1
Recent advances in Conditional Diffusion Models have led to substantial capabilities in various domains. However, understanding the impact of variations in the initial seed vector…
The Challenges of Image Generation Models in Generating Multi-Component Images
Tham Yik Foong, Shashank Kotyan, Po Yuan Mao +1
Recent advances in text-to-image generators have led to substantial capabilities in image generation. However, the complexity of prompts acts as a bottleneck in the quality of imag…
Towards Improving Robustness Against Common Corruptions using Mixture of Class Specific Experts
Shashank Kotyan, Danilo Vasconcellos Vargas
Neural networks have demonstrated significant accuracy across various domains, yet their vulnerability to subtle input alterations remains a persistent challenge. Conventional meth…
Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning
Shashank Kotyan, Danilo Vasconcellos Vargas
Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to s…
Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation
Shashank Kotyan, Danilo Vasconcellos Vargas
Vision Transformer (ViT) has demonstrated promising performance in computer vision tasks, comparable to state-of-the-art neural networks. Yet, this new type of deep neural network…
Deep neural network loses attention to adversarial images
Shashank Kotyan, Danilo Vasconcellos Vargas
Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the…
Perceptual Deep Neural Networks: Adversarial Robustness through Input Recreation
Danilo Vasconcellos Vargas, Bingli Liao, Takahiro Kanzaki
Adversarial examples have shown that albeit highly accurate, models learned by machines, differently from humans, have many weaknesses. However, humans' perception is also fundamen…
Continual General Chunking Problem and SyncMap
Danilo Vasconcellos Vargas, Toshitake Asabuki
Humans possess an inherent ability to chunk sequences into their constituent parts. In fact, this ability is thought to bootstrap language skills and learning of image patterns whi…