Hassan Dbouk — accepted AI-conference papers

2025

Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits

Ashish J Khisti, MohammadReza Ebrahimi, Hassan Dbouk, Arash Behboodi, Roland Memisevic, Christos Louizos

ICLR 2025spotlight

We consider multi-draft speculative sampling, where the proposal sequences are sampled independently from different draft models. At each step, a token-level draft selection scheme takes a list of valid tokens as input and produces an output token whose distribution matches that of the target mode…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

On the Robustness of Randomized Ensembles to Adversarial Perturbations

Hassan Dbouk, Naresh Shanbhag

ICML 2023poster

Randomized ensemble classifiers (RECs), where one classifier is randomly selected during inference, have emerged as an attractive alternative to traditional ensembling methods for realizing adversarially robust classifiers with limited compute requirements. However, recent works have shown that exis…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2022

Adversarial Vulnerability of Randomized Ensembles

Hassan Dbouk, Naresh Shanbhag

ICML 2022spotlight

Despite the tremendous success of deep neural networks across various tasks, their vulnerability to imperceptible adversarial perturbations has hindered their deployment in the real world. Recently, works on randomized ensembles have empirically demonstrated significant improvements in adversarial r…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2021

Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks

Hassan Dbouk, Naresh Shanbhag

NeurIPS 2021spotlight

Despite their tremendous successes, convolutional neural networks (CNNs) incur high computational/storage costs and are vulnerable to adversarial perturbations. Recent works on robust model compression address these challenges by combining model compression techniques with adversarial training. But…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗

2020

DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks

Hassan Dbouk, Hetul Sanghvi, Mahesh Mehendale, Naresh Shanbhag

ECCV 2020poster

Deep neural networks have achieved state-of-the art performance on various computer vision tasks. However, their deployment on resource-constrained devices has been hindered due to their high computational and storage complexity. While various complexity reduction techniques, such as lightweight net…

Cited by 11 Source ↗PDF ↗Scholar ↗

2020

Low-Complexity Fixed-Point Convolutional Neural Networks For Automatic Target Recognition

Hassan Dbouk, Hanfei Geng, Craig M. Vineyard, Naresh R. Shanbhag

ICASSP 2020accepted

There has been growing interest in developing neural network based automatic target recognition systems for synthetic aperture radar applications. However, these networks are typically complex in terms of storage and computation which inhibits their deployment in the field, where such resources are…

Cited by 0 Source ↗Scholar ↗