10 papers
Budget-Constrained Online Retrieval-Augmented Generation: The Chunk-as-a-Service Model
Shawqi Al-Maliki, Ammar Gharaibeh, Mohamed Rahouti +4
Large Language Models (LLMs) have revolutionized the field of natural language processing. However, they exhibit some limitations, including a lack of reliability and transparency:…
A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness
Naseem Machlovi, Maryam Saleki, Ruhul Amin +5
As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholdi…
Resource Constraint Estimation of In-Quantum Implementated Mini-AES
Syed Shahmir, Ghulam Murtaza, Ala-Al-Fuqaha +2
The advancement in quantum technology has brought the implementation of Grover's Search attack on cybersecurity algorithms much closer to reality. For such tasks, the Hilbert space…
Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content
Abdullah Mushtaq, Rafay Naeem, Ezieddin Elmahjub +5
Large language models are increasingly used for Islamic guidance, but risk misquoting texts, misapplying jurisprudence, or producing culturally inconsistent responses. We pilot an…
Large Language Model Enhanced Particle Swarm Optimization for Hyperparameter Tuning for Deep Learning Models
Saad Hameed, Basheer Qolomany, Samir Brahim Belhaouari +3
Determining the ideal architecture for deep learning models, such as the number of layers and neurons, is a difficult and resource-intensive process that frequently relies on human…
A Survey of Social Cybersecurity: Techniques for Attack Detection, Evaluations, Challenges, and Future Prospects
Aos Mulahuwaish, Basheer Qolomany, Kevin Gyorick +5
In today's digital era, the Internet, especially social media platforms, plays a significant role in shaping public opinions, attitudes, and beliefs. Unfortunately, the credibility…