most citedMuxLink: Circumventing Learning-Resilient MUX-Locking Using Graph Neural Network-based Link Prediction

7 citations · 13 across the 2 of their papers we have counts for

collaborators

28 papers

eess.IV2024

Embedded Deployment of Semantic Segmentation in Medicine through Low-Resolution Inputs

Erik Ostrowski, Muhammad Shafique

When deploying neural networks in real-life situations, the size and computational effort are often the limiting factors. This is especially true in environments where big, expensi…

cs.AI20242 cited

MedAide: Leveraging Large Language Models for On-Premise Medical Assistance on Edge Devices

Abdul Basit, Khizar Hussain, Muhammad Abdullah Hanif +1

Large language models (LLMs) are revolutionizing various domains with their remarkable natural language processing (NLP) abilities. However, deploying LLMs in resource-constrained…

cs.LG20248 cited

A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends

Abolfazl Younesi, Mohsen Ansari, MohammadAmin Fazli +3

In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning (DL), are widely used for various computer vision tasks such as image classification, object…

cs.CR20246 cited

An Empirical Evaluation of LLMs for Solving Offensive Security Challenges

Minghao Shao, Boyuan Chen, Sofija Jancheska +4

Capture The Flag (CTF) challenges are puzzles related to computer security scenarios. With the advent of large language models (LLMs), more and more CTF participants are using LLMs…

cs.CV2024

Anomaly Unveiled: Securing Image Classification against Adversarial Patch Attacks

Nandish Chattopadhyay, Amira Guesmi, Muhammad Shafique

Adversarial patch attacks pose a significant threat to the practical deployment of deep learning systems. However, existing research primarily focuses on image pre-processing defen…

cs.AR2023

Reduce: A Framework for Reducing the Overheads of Fault-Aware Retraining

Muhammad Abdullah Hanif, Muhammad Shafique

Fault-aware retraining has emerged as a prominent technique for mitigating permanent faults in Deep Neural Network (DNN) hardware accelerators. However, retraining leads to huge ov…