Zobrazeno 1 - 10
of 551
pro vyhledávání: '"Khreishah, A."'
The capability of generating high-quality source code using large language models (LLMs) reduces software development time and costs. However, they often introduce security vulnerabilities due to training on insecure open-source data. This highlights
Externí odkaz:
http://arxiv.org/abs/2409.12699
Autor:
Ton, Khiem, Nguyen, Nhi, Nazzal, Mahmoud, Khreishah, Abdallah, Borcea, Cristian, Phan, NhatHai, Jin, Ruoming, Khalil, Issa, Shen, Yelong
This paper introduces SGCode, a flexible prompt-optimizing system to generate secure code with large language models (LLMs). SGCode integrates recent prompt-optimization approaches with LLMs in a unified system accessible through front-end and back-e
Externí odkaz:
http://arxiv.org/abs/2409.07368
Autor:
Vungarala, Deepak, Nazzal, Mahmoud, Morsali, Mehrdad, Zhang, Chao, Ghosh, Arnob, Khreishah, Abdallah, Angizi, Shaahin
In the ever-evolving landscape of Deep Neural Networks (DNN) hardware acceleration, unlocking the true potential of systolic array accelerators has long been hindered by the daunting challenges of expertise and time investment. Large Language Models
Externí odkaz:
http://arxiv.org/abs/2404.10875
Autor:
Nazzal, Mahmoud, Aljaafari, Nura, Sawalmeh, Ahmed, Khreishah, Abdallah, Anan, Muhammad, Algosaibi, Abdulelah, Alnaeem, Mohammed, Aldalbahi, Adel, Alhumam, Abdulaziz, Vizcarra, Conrado P., Alhamed, Shadan
Federated learning enables multiple clients to collaboratively contribute to the learning of a global model orchestrated by a central server. This learning scheme promotes clients' data privacy and requires reduced communication overheads. In an appl
Externí odkaz:
http://arxiv.org/abs/2310.06855
Malicious domain detection (MDD) is an open security challenge that aims to detect if an Internet domain is associated with cyber-attacks. Among many approaches to this problem, graph neural networks (GNNs) are deemed highly effective. GNN-based MDD
Externí odkaz:
http://arxiv.org/abs/2308.11754
In this paper, we propose IMA-GNN as an In-Memory Accelerator for centralized and decentralized Graph Neural Network inference, explore its potential in both settings and provide a guideline for the community targeting flexible and efficient edge com
Externí odkaz:
http://arxiv.org/abs/2303.14162
Autor:
Nazzal, Mahmoud, Khreishah, Abdallah, Lee, Joyoung, Angizi, Shaahin, Al-Fuqaha, Ala, Guizani, Mohsen
Prediction of taxi service demand and supply is essential for improving customer's experience and provider's profit. Recently, graph neural networks (GNNs) have been shown promising for this application. This approach models city regions as nodes in
Externí odkaz:
http://arxiv.org/abs/2303.00524
In this paper, we propose a new method of applying the XOR and XNOR gates on exponentially large superpositions in Instantaneous Noise-Based Logic. These new gates are repeatable, and they can achieve an exponential speed up in computation with a pol
Externí odkaz:
http://arxiv.org/abs/2302.06449
Autor:
Tran, Khang, Lai, Phung, Phan, NhatHai, Khalil, Issa, Ma, Yao, Khreishah, Abdallah, Thai, My, Wu, Xintao
Graph neural networks (GNNs) are susceptible to privacy inference attacks (PIAs), given their ability to learn joint representation from features and edges among nodes in graph data. To prevent privacy leakages in GNNs, we propose a novel heterogeneo
Externí odkaz:
http://arxiv.org/abs/2211.05766
Trojan backdoor is a poisoning attack against Neural Network (NN) classifiers in which adversaries try to exploit the (highly desirable) model reuse property to implant Trojans into model parameters for backdoor breaches through a poisoned training p
Externí odkaz:
http://arxiv.org/abs/2209.01721