4 papers
A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots
Gulshan Saleem, Nisar Ahmed, Muhammad Imran Zaman +1
Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applications, yet existing defenses operate at i…
Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B
Nisar Ahmed, Muhammad Imran Zaman, Gulshan Saleem +1
Benchmarks for large language models (LLMs) often rely on rubric-scented prompts that request visible reasoning and strict formatting, whereas real deployments demand terse, contra…
Deep Learning-Based Age Estimation and Gender Deep Learning-Based Age Estimation and Gender Classification for Targeted Advertisement
Muhammad Imran Zaman, Nisar Ahmed
This paper presents a novel deep learning-based approach for simultaneous age and gender classification from facial images, designed to enhance the effectiveness of targeted advert…
Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function
Muhammad Azeem Aslam, Wang Jun, Nisar Ahmed +5
In multi-label emotion classification, particularly for low-resource languages like Arabic, the challenges of class imbalance and label correlation hinder model performance, especi…