AI is rapidly evolving from chatbots to autonomous agents. But as these systems become more capable, they also become more vulnerable.
Hosted by Dr. Honghui Xu and his PhD students, this podcast explores the foundations, attacks, defenses, and future of AI security.
Through research-driven discussions, we break down topics such as prompt injection, indirect attacks, multi-agent security, backdoors, model robustness, and secure AI deployment.
Whether you’re a researcher, engineer, student, or simply curious about the future of AI, this podcast helps you understand how to build and secure the
In Episode 8, host Honghui Xu talks with Shiva Shrestha and Kazi Sharif about what big tech companies are actually doing for AI security. They discuss real-world practices, challenges, and lessons from industry AI deployments.
12 Jun 2026
Build a Secure Physical AI System under Real-world Constraints?
In Episode 12, host Honghui Xu talks with Shiva Shrestha about building a secure Physical AI systems under real-world constraints. They discuss how to balance security, usability, cost, and performance in practical AI deployments.
12 Jun 2026
Hidden in Meaning: The Next Generation of Backdoor Attacks
In Episode 11, host Honghui Xu talks with Tahmid Imtiaz Imu about backdoor attacks in LLM agents. They discuss how hidden triggers can affect agent behavior and why detecting these attacks is important for building safer AI systems.
12 Jun 2026
When LLMs meet Quantum: Model-Level Defense
In Episode 10, host Honghui Xu talks with Emama Nahid about model-level defense for LLMs. They discuss how quantum-inspired ideas can help improve model robustness and security.
12 Jun 2026
Detection-Based Defense for Multimodal LLMs
In Episode 9, host Honghui Xu talks with Md Abdullahil Oaphy about detection-based defense for multimodal LLMs. They discuss how to detect risks across text and image inputs, and how these defenses can make multimodal AI systems safer and more trustworthy.
12 Jun 2026
Defense Evolution: From Prompt Tricks to Architectural Security
In Episode 7, host Honghui Xu talks with Shiva Shrestha and Kazi Sharif about how AI security defenses are evolving. They discuss why prompt-based tricks are not enough and why stronger architectural security is needed for real-world AI systems.
12 Jun 2026
Beyond Single Agents: Multi-Agent & System-Level Attacks
In Episode 6, host Honghui Xu talks with Shiva Shrestha and Kazi Sharif about multi-agent and system-level attacks. They discuss how attackers can exploit interactions between agents, tools, and systems, and why stronger system-level defenses are needed.
12 Jun 2026
The Real Danger: Indirect Injection & Data Poisoning
In Episode 5, host Honghui Xu talks with Shiva Shrestha and Kazi Sharif about indirect injection and data poisoning. They discuss how these hidden attacks can compromise LLM systems and why they are difficult to detect and defend against.
12 Jun 2026
Attacks on LLMs: From Prompt Injection to Agent Hijacking
In Episode 4, host Honghui Xu talks with Shiva Shrestha and Kazi Sharif about attacks on LLMs. They discuss prompt injection, jailbreaks, data leakage, and agent hijacking, and explain why these attacks matter for real-world AI systems.
12 Jun 2026
The Root Cause: Why LLMs Are Fundamentally Vulnerable
In Episode 3, host Honghui Xu talks with Shiva Shrestha and Kazi Sharif about why LLMs are fundamentally vulnerable. They discuss how these risks come from the way LLMs are trained, designed, and used in real-world AI systems.
12 Jun 2026
The Five-Layer Stack: A New Lens for AI Security
In Episode 2, host Honghui Xu talks with Shiva Shrestha and Kazi Sharif about the Five-Layer Stack as a new way to understand AI security. They discuss how different layers of AI systems create different risks and require different defenses.
12 Jun 2026
From LLMs to Agents: Why Security is No Longer Just Text
In Episode 1, host Honghui Xu talks with Shiva Shrestha and Kazi Sharif about how AI security changes as LLMs evolve into agents. They discuss why security is no longer just about text, but also about tools, actions, data, and real-world systems.
Contact Securing AI: From Models to Agents
Guest appearances
Books guests
Based on episode analysis; this does not confirm that the show is currently accepting guests.
Host of Securing AI: From Models to Agents?
Claim your podcast to manage its listing and keep your show details accurate.
Pod Engine is an independent podcast discovery and analytics service and is not affiliated with or endorsed by this podcast. Artwork and show content belong to their owners. Full legal notice.
Explore this show Podcast research with Pod Engine
