Amjad Alghamdi
Cybersecurity Analyst
Saudi Aramco
Amjad Alghamdi is a Cybersecurity Analyst at Saudi Aramco, Security Information Protection Unit, where she develops innovative platforms supporting digital transformation in industrial security and upstream. She began her journey in cybersecurity after earning a Bachelor's Degree in Computer Science with honors from Imam Abdulrahman Bin Faisal University in 2022. Passionate about advancing the field, Amjad holds professional certifications including Security+, Certified Identity and Access Manager (CIAM), and COBIT5, and has a growing interest in AI and its impact on security.
Speaker sessions
Briefings and Arsenals | Confirmed Speakers | No Session Assigned
Placeholder session for confirmed speakers without an assigned session, allowing them to be pushed to Swapcard and Visit.
- 07:30
- Tue
- 01 Dec
Stage:
Briefing Stage 2
Sessions Type:
Keynote
When Guardrails Aren�t Enough: The AI Agent Kill Chain
Autonomous AI agents have evolved from text generators into active computational actors executing multi-step workflows, invoking tools, and making decisions with real-world impact. While organizations increasingly rely on AI guardrails to reduce risk, these controls alone are insufficient against sophisticated attacks that exploit the agent's reasoning process, memory, tool integrations, identities, and decision-making capabilities.This session introduces the AI Agent Kill Chain as a framework for understanding how attacks against AI agents evolve from initial interaction to business impact. Rather than examining threats such as prompt injection, tool abuse, memory poisoning, or data exfiltration as isolated events, the session connects them into a structured attack lifecycle that reflects how adversaries progressively manipulate AI agents in real-world enterprise environments.Each phase of the kill chain is examined through the defender's perspective, highlighting where security teams gain visibility, what indicators reveal malicious activity, how attacks can be detected, and where defensive controls can interrupt adversarial activity before it reaches critical systems or sensitive data. The discussion also explores the limitations of traditional guardrails, identifies common blind spots in AI agent deployments, and demonstrates how layered security controls improve resilience across the entire attack lifecycle.Designed for cybersecurity practitioners, SOC analysts, and security leaders, this session provides a practical methodology for analyzing AI agent attacks and strengthening enterprise defenses. Attendees will leave with a structured approach for evaluating AI agent security, understanding emerging attack paths, and building more effective detection and response strategies for the next generation of autonomous AI systems.
- 15:20
- Tue
- 01 Dec
Stage:
Briefing Stage 2
Sessions Type:
Keynote
From Scanner Noise to Real Risk: A Practical Methodology for AI-Assisted Vulnerability Prioritization
Autonomous AI agents have evolved from text generators into active computational actors executing multi-step workflows, invoking tools, and making decisions with real-world impact. While organizations increasingly rely on AI guardrails to reduce risk, these controls alone are insufficient against sophisticated attacks that exploit the agent's reasoning process, memory, tool integrations, identities, and decision-making capabilities.This session introduces the AI Agent Kill Chain as a framework for understanding how attacks against AI agents evolve from initial interaction to business impact. Rather than examining threats such as prompt injection, tool abuse, memory poisoning, or data exfiltration as isolated events, the session connects them into a structured attack lifecycle that reflects how adversaries progressively manipulate AI agents in real-world enterprise environments.Each phase of the kill chain is examined through the defender's perspective, highlighting where security teams gain visibility, what indicators reveal malicious activity, how attacks can be detected, and where defensive controls can interrupt adversarial activity before it reaches critical systems or sensitive data. The discussion also explores the limitations of traditional guardrails, identifies common blind spots in AI agent deployments, and demonstrates how layered security controls improve resilience across the entire attack lifecycle.Designed for cybersecurity practitioners, SOC analysts, and security leaders, this session provides a practical methodology for analyzing AI agent attacks and strengthening enterprise defenses. Attendees will leave with a structured approach for evaluating AI agent security, understanding emerging attack paths, and building more effective detection and response strategies for the next generation of autonomous AI systems.
- 17:30
- Thu
- 03 Dec
Stage:
Briefing Stage 1
Sessions Type:
Keynote