activity
20242026
collaborators

5 papers

cs.CR2026

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…

cs.CL2025

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…

cs.CV2025

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…

cs.CV2025

A Robust Deep Networks based Multi-Object MultiCamera Tracking System for City Scale Traffic

Muhammad Imran Zaman, Usama Ijaz Bajwa, Gulshan Saleem +1

Vision sensors are becoming more important in Intelligent Transportation Systems (ITS) for traffic monitoring, management, and optimization as the number of network cameras continu…

cs.CV2024

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…