activity
20212024
most citedML Attack Models: Adversarial Attacks and Data Poisoning Attacks

31 citations · 47 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CR2024

Exploring Feature Importance and Explainability Towards Enhanced ML-Based DoS Detection in AI Systems

Paul Badu Yakubu, Evans Owusu, Lesther Santana +3

Denial of Service (DoS) attacks pose a significant threat in the realm of AI systems security, causing substantial financial losses and downtime. However, AI systems' high computat…

cs.CR20248 cited

Redefining DDoS Attack Detection Using A Dual-Space Prototypical Network-Based Approach

Fernando Martinez, Mariyam Mapkar, Ali Alfatemi +4

Distributed Denial of Service (DDoS) attacks pose an increasingly substantial cybersecurity threat to organizations across the globe. In this paper, we introduce a new deep learnin…

cs.CR20247 cited

Advancing DDoS Attack Detection: A Synergistic Approach Using Deep Residual Neural Networks and Synthetic Oversampling

Ali Alfatemi, Mohamed Rahouti, Ruhul Amin +3

Distributed Denial of Service (DDoS) attacks pose a significant threat to the stability and reliability of online systems. Effective and early detection of such attacks is pivotal…

cs.RO20231 cited

A Decentralized Cooperative Navigation Approach for Visual Homing Networks

Mohamed Rahouti, Damian Lyons, Senthil Kumar Jagatheesaperumal +1

Visual homing is a lightweight approach to visual navigation. Given the stored information of an initial 'home' location, the navigation task back to this location is achieved from…

cs.LG2023

Improving Machine Learning Robustness via Adversarial Training

Long Dang, Thushari Hapuarachchi, Kaiqi Xiong +1

As Machine Learning (ML) is increasingly used in solving various tasks in real-world applications, it is crucial to ensure that ML algorithms are robust to any potential worst-case…

cs.LG202131 cited

ML Attack Models: Adversarial Attacks and Data Poisoning Attacks

Jing Lin, Long Dang, Mohamed Rahouti +1

Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However,…