AI Researcher · IU Madinah

AliAkarma

Designing Safety-Aligned Agentic Systems.

I build agentic AI systems that know their own limits. My work focuses on the gap between autonomous capability and institutional accountability — designing architectures where AI agents can be stopped, audited, and corrected when they behave unexpectedly. I'm a 4th-year IT student at the Islamic University of Madinah and have published 15 peer-reviewed papers and manuscripts on AI governance, adversarial robustness, and constrained multi-agent systems.

I study how to make autonomous AI systems fail safely: designing governance architectures that prevent unintended actions before they propagate through real-world infrastructure.

Current Research Frontier

Autonomous Safety Governance

Safety-Critical Multi-Agent Systems

"Investigating cryptographic trust-anchors and constrained reasoning for large-scale agentic deployments."

0
Publications
peer-reviewed & in pipeline
0
Research Areas
Agentic AI • Safety & Alignment • Adversarial Misuse • Governance & Oversight • Cybersecurity • Digital Twins
0
Journal Venues
Nature Scientific Reports • PLoS ONE • MDPI Smart Cities • MDPI Sustainability • JDR • ETASR • IJEEE
0
Conference Venues
IEEE ICCA • ICBDT • ICETAS • MECON 2026
Scholar Metrics
Updated Jul 21, 2026
54
Citations
5
h-index
2
i10-index
Research Vision

Why This
Research
Matters

I study how to make autonomous AI systems fail safely: designing governance architectures that prevent unintended actions before they propagate through real-world infrastructure.

My work addresses the alignment problem in deployed agentic systems — exploring how we can build autonomous pipelines that remain safe and governable when exposed to adversarial inputs, distributional shift, or misaligned incentives. I approach this through the intersection of safety engineering, formal governance frameworks, and empirical failure-mode analysis.

Agentic AI & Autonomous Systems in High-Stakes EnvironmentsAI Safety & Alignment of Large Language ModelsPrompt Injection, Jailbreaks & Adversarial MisuseGovernance, Oversight & Constitutional AISecure AI for Cybersecurity & Critical InfrastructureDigital Twins & Smart City AI
Knowledge Graph

Research Landscape

Latest Work

Recent Publications

All 15 Papers

EAGF: A Four-Pillar Ethical AI Governance Framework for Trustworthy Cybersecurity in 5G Renewable Energy IoT Systems

Salman Jan, Ali Akarma, Toqeer Ali Syed, Munir Azam Muhammad, Shahid Kamal

AI GovernanceCybersecurityIoT
Journal Article · Nature Scientific Reports

Agentic AI-enhanced digital twins for Smart City civil infrastructure: A secure, autonomous and auditable management framework

Toqeer Ali Syed, Ali Akarma, Ali Alatify, Muhammad Tayyab Naqash, Abdulaziz Alqurashi

Agentic AIDigital TwinsSmart Cities
Journal Article · PLoS One

ADAPT: An Agentic AI Framework for People with Disabilities and Neurodivergence

Muhammad Shoaib Siddiqui, Toqeer Ali Syed, Ali Akarma

Agentic AIADAPTAssistive technology
Journal Article · Journal of Disability Research