activity
20242026
collaborators

8 papers

cs.CR2026

Human Society-Inspired Approaches to Agentic AI Security: The 4C Framework

Alsharif Abuadbba, Nazatul Sultan, Surya Nepal +1

AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a…

cs.CL2025

Adversarial Attacks Against Automated Fact-Checking: A Survey

Fanzhen Liu, Alsharif Abuadbba, Kristen Moore +5

In an era where misinformation spreads freely, fact-checking (FC) plays a crucial role in verifying claims and promoting reliable information. While automated fact-checking (AFC) h…

cs.CY2025

RINSER: Accurate API Prediction Using Masked Language Models

Muhammad Ejaz Ahmed, Christopher Cody, Muhammad Ikram +5

Malware authors commonly use obfuscation to hide API identities in binary files, making analysis difficult and time-consuming for a human expert to understand the behavior and inte…

cs.LG2025

Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies

Fanzhen Liu, Xiaoxiao Ma, Jian Yang +6

Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate e…

cs.CR2025

Adaptive alert prioritisation in security operations centres via learning to defer with human feedback

Fatemeh Jalalvand, Mohan Baruwal Chhetri, Surya Nepal +1

Alert prioritisation (AP) is crucial for security operations centres (SOCs) to manage the overwhelming volume of alerts and ensure timely detection and response to genuine threats,…

cs.CR2025

Enhancing Malware Fingerprinting through Analysis of Evasive Techniques

Alsharif Abuadbba, Sean Lamont, Ejaz Ahmed +6

As malware detection evolves, attackers adopt sophisticated evasion tactics. Traditional file-level fingerprinting, such as cryptographic and fuzzy hashes, is often overlooked as a…