activity
20182021
most citedMitigating Gradient-based Adversarial Attacks via Denoising and Compression

3 citations · 5 across the 4 of their papers we have counts for

collaborators

8 papers

cs.NI2021

Knowledge Distillation For Wireless Edge Learning

Ahmed P. Mohamed, Abu Shafin Mohammad Mahdee Jameel, Aly El Gamal

In this paper, we propose a framework for predicting frame errors in the collaborative spectrally congested wireless environments of the DARPA Spectrum Collaboration Challenge (SC2…

cs.CR20213 cited

Mitigating Gradient-based Adversarial Attacks via Denoising and Compression

Rehana Mahfuz, Rajeev Sahay, Aly El Gamal

Gradient-based adversarial attacks on deep neural networks pose a serious threat, since they can be deployed by adding imperceptible perturbations to the test data of any network,…

cs.CV2020

Data-driven Analysis of Turbulent Flame Images

Rathziel Roncancio, Jupyoung Kim, Aly El Gamal +1

Turbulent premixed flames are important for power generation using gas turbines. Improvements in characterization and understanding of turbulent flames continue particularly for tr…

cs.LG2020

Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networks

Kirthi Shankar Sivamani, Rajeev Sahay, Aly El Gamal

Recent studies have shown that deep learning models are vulnerable to specifically crafted adversarial inputs that are quasi-imperceptible to humans. In this letter, we propose a n…

cs.IT2019

Optimal Wireless Caching with Placement Cost

Yousef AlHassoun, Faisal Alotaibi, Aly El Gamal +1

Coded caching has been shown to result in significant throughput gains, but its gains were proved only by assuming a placement phase with no transmission cost. A free placement pha…

cs.LG20192 cited

A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks

Rajeev Sahay, Rehana Mahfuz, Aly El Gamal

The reliance on deep learning algorithms has grown significantly in recent years. Yet, these models are highly vulnerable to adversarial attacks, which introduce visually impercept…