most citedIs ReLU Adversarially Robust?

1 citations · 3 across the 5 of their papers we have counts for

collaborators

6 papers

quant-ph2024

Learning Robust Observable to Address Noise in Quantum Machine Learning

Bikram Khanal, Pablo Rivas

Quantum Machine Learning (QML) has emerged as a promising field that combines the power of quantum computing with the principles of machine learning. One of the significant challen…

cs.CV20241 cited

Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations

Pablo Rivas, Gisela Bichler, Tomas Cerny +2

Unbiased representation learning is still an object of study under specific applications and contexts. Novel architectures are usually crafted to resolve particular problems using…

cs.CV20241 cited

From Latent to Engine Manifolds: Analyzing ImageBind's Multimodal Embedding Space

Andrew Hamara, Pablo Rivas

This study investigates ImageBind's ability to generate meaningful fused multimodal embeddings for online auto parts listings. We propose a simplistic embedding fusion workflow tha…

cs.LG2024

On Adversarial Examples for Text Classification by Perturbing Latent Representations

Korn Sooksatra, Bikram Khanal, Pablo Rivas

Recently, with the advancement of deep learning, several applications in text classification have advanced significantly. However, this improvement comes with a cost because deep l…

cs.LG20241 cited

Is ReLU Adversarially Robust?

Korn Sooksatra, Greg Hamerly, Pablo Rivas

The efficacy of deep learning models has been called into question by the presence of adversarial examples. Addressing the vulnerability of deep learning models to adversarial exam…

cs.LG2023

Combatting Human Trafficking in the Cyberspace: A Natural Language Processing-Based Methodology to Analyze the Language in Online Advertisements

Alejandro Rodriguez Perez, Pablo Rivas

This project tackles the pressing issue of human trafficking in online C2C marketplaces through advanced Natural Language Processing (NLP) techniques. We introduce a novel methodol…