Zobrazeno 1 - 10
of 1 540
pro vyhledávání: '"A, Abuhamad"'
Autor:
Arslan, Muhammad, Madrigal, Manuel Sandoval, Abuhamad, Mohammed, Hall, Deborah L., Silva, Yasin N.
Social media continues to have an impact on the trajectory of humanity. However, its introduction has also weaponized keyboards, allowing the abusive language normally reserved for in-person bullying to jump onto the screen, i.e., cyberbullying. Cybe
Externí odkaz:
http://arxiv.org/abs/2409.12263
Deep Learning (DL) is rapidly maturing to the point that it can be used in safety- and security-crucial applications. However, adversarial samples, which are undetectable to the human eye, pose a serious threat that can cause the model to misbehave a
Externí odkaz:
http://arxiv.org/abs/2405.01963
Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robots, and surveillance systems. These advancements include applying varia
Externí odkaz:
http://arxiv.org/abs/2405.01934
Deep learning has been rapidly employed in many applications revolutionizing many industries, but it is known to be vulnerable to adversarial attacks. Such attacks pose a serious threat to deep learning-based systems compromising their integrity, rel
Externí odkaz:
http://arxiv.org/abs/2307.11906
Autor:
Abdukhamidov, Eldor, Abuhamad, Mohammed, Thiruvathukal, George K., Kim, Hyoungshick, Abuhmed, Tamer
In this paper, we present a novel Single-class target-specific Adversarial attack called SingleADV. The goal of SingleADV is to generate a universal perturbation that deceives the target model into confusing a specific category of objects with a targ
Externí odkaz:
http://arxiv.org/abs/2307.06484
Deep learning models are susceptible to adversarial samples in white and black-box environments. Although previous studies have shown high attack success rates, coupling DNN models with interpretation models could offer a sense of security when a hum
Externí odkaz:
http://arxiv.org/abs/2307.06496
Authorship attribution has become increasingly accurate, posing a serious privacy risk for programmers who wish to remain anonymous. In this paper, we introduce SHIELD to examine the robustness of different code authorship attribution approaches agai
Externí odkaz:
http://arxiv.org/abs/2304.13255
Deep learning methods have gained increased attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper use of data artifacts and the accurate problem formulation of a given ta
Externí odkaz:
http://arxiv.org/abs/2211.15926
Autor:
Abuhamad, Asmaa Y.1 (AUTHOR) asmaaabuhamad@ukm.edu.my, Masri, Syafira1 (AUTHOR) p110574@siswa.ukm.edu.my, Fadilah, Nur Izzah Md1,2 (AUTHOR) izzahfadilah@ukm.edu.my, Alamassi, Mohammed Numan3 (AUTHOR) 22114650@siswa.um.edu.my, Maarof, Manira1,2 (AUTHOR) manira@ppukm.ukm.edu.my, Fauzi, Mh Busra1,2 (AUTHOR) fauzibusra@ukm.edu.my
Publikováno v:
Polymers (20734360). Sep2024, Vol. 16 Issue 17, p2456. 29p.
Autor:
Asmaa Y. Abuhamad, Syafira Masri, Nur Izzah Md Fadilah, Mohammed Numan Alamassi, Manira Maarof, Mh Busra Fauzi
Publikováno v:
Polymers, Vol 16, Iss 17, p 2456 (2024)
Chronic wounds, such as diabetic foot ulcers, pressure ulcers, and venous ulcers, pose significant clinical challenges and burden healthcare systems worldwide. The advent of 3D bioprinting technologies offers innovative solutions for enhancing chroni
Externí odkaz:
https://doaj.org/article/db018264d9ee493b82692788a1d6934e