Bare Metal Cyber · Free, ad-free audio course
A focused course on the risks, controls, governance questions, and defensive practices that surround modern AI systems.
Complete Lesson Directory
Search by topic or narrow the directory by exam domain. Courses with multiple editions are organized below so every season remains easy to find. Each lesson includes its own audio player, full description, transcript when available, and previous-or-next navigation.
50 lessons available
Architecture, Trust Boundaries and Data Security
This opening episode provides a structured orientation to the AI Security and Threats Audio course series, helping listeners understand what the program covers and how to best engage with the material.…
Architecture, Trust Boundaries and Data Security
This episode defines the AI security landscape by mapping the assets, attack surfaces, and emerging threats that distinguish AI from classical application security.…
Architecture, Trust Boundaries and Data Security
This episode explains the architecture of AI systems, breaking down their stages and components to show how trust boundaries shift across the lifecycle.…
Architecture, Trust Boundaries and Data Security
This episode examines data lifecycle security, covering the journey of data from collection and labeling through storage, retention, deletion, and provenance management.…
AI Attacks, Privacy, RAG and Agent Controls
This episode introduces prompt injection and jailbreaks as fundamental AI-specific security risks. It defines prompt injection as malicious manipulation of model inputs to alter behavior and describes jailbreaks as methods for bypassing built-in safeguards.…
AI Attacks, Privacy, RAG and Agent Controls
This episode examines indirect and cross-domain prompt injections, which expand the attack surface by embedding malicious instructions in external sources such as documents, websites, or email content.…
AI Attacks, Privacy, RAG and Agent Controls
This episode explains the distinction and overlap between content safety and security in AI systems, a concept often emphasized in both professional practice and certification exams.…
AI Attacks, Privacy, RAG and Agent Controls
This episode introduces data poisoning as a high-priority threat in AI security, where adversaries deliberately insert malicious samples into training or fine-tuning datasets.…
AI Attacks, Privacy, RAG and Agent Controls
This episode covers training-time integrity, focusing on the assurance that data, processes, and infrastructure used in model development remain uncompromised.…
AI Attacks, Privacy, RAG and Agent Controls
This episode introduces privacy attacks in AI systems, focusing on techniques that reveal sensitive or personal information from training data or model behavior.…
AI Attacks, Privacy, RAG and Agent Controls
This episode explores privacy-preserving techniques designed to reduce the risk of sensitive information exposure in AI systems while maintaining utility of the models.…
AI Attacks, Privacy, RAG and Agent Controls
This episode addresses model theft and extraction, highlighting how adversaries can replicate or steal valuable AI models.…
AI Attacks, Privacy, RAG and Agent Controls
This episode introduces adversarial evasion, a class of attacks in which maliciously crafted inputs cause AI systems to misclassify or behave incorrectly.…
AI Attacks, Privacy, RAG and Agent Controls
This episode explores retrieval-augmented generation (RAG) security, focusing on retrieval and index hardening as foundational defenses. RAG combines language models with external document retrieval, which improves factual grounding but introduces risks.…
AI Attacks, Privacy, RAG and Agent Controls
This episode continues exploration of RAG security by examining context filtering and grounding as defenses for reliable outputs.…
AI Attacks, Privacy, RAG and Agent Controls
This episode introduces AI agents as a new and growing attack surface, highlighting how their autonomy and tool integration create unique risks.…
AI Attacks, Privacy, RAG and Agent Controls
This episode addresses secrets and credential hygiene, emphasizing their critical role in preventing leaks and privilege misuse in AI systems. Secrets include API keys, tokens, passwords, and configuration values embedded in prompts or environments.…
AI Attacks, Privacy, RAG and Agent Controls
This episode explores authentication (AuthN) and authorization (AuthZ) for large language model (LLM) applications, highlighting their importance in managing identities and permissions.…
AI Attacks, Privacy, RAG and Agent Controls
This episode examines output validation and policy enforcement as mechanisms for controlling what AI systems produce before results are delivered to users or downstream processes.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode introduces red teaming as a structured method for probing generative AI systems for vulnerabilities, emphasizing its importance for both exam preparation and real-world resilience.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode examines evaluations and test pipelines as essential processes for maintaining AI system security and reliability.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode explores telemetry and observability, emphasizing their importance in detecting anomalies, intrusions, and misuse in AI systems.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode addresses abuse and fraud detection in AI applications, focusing on how adversaries exploit systems for spam, phishing, or marketplace manipulation.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode examines cost and resource abuse, where adversaries or careless users exploit AI systems to drive up compute expenses or deny service to legitimate customers.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode introduces MLOps and serving security, focusing on practices that protect the deployment, operation, and continuous delivery of AI models. MLOps extends DevOps principles to AI, requiring controls for model registries, CI/CD pipelines, and serving infrastructure.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode examines supply chain and artifact security, focusing on how external dependencies and stored components create systemic risks in AI systems.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode introduces secure fine-tuning and adaptation, explaining how customization of pre-trained models introduces both benefits and new risks.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode focuses on API gateways and proxies, emphasizing their role as critical control points for AI applications. An API gateway manages traffic to model endpoints, providing authentication, authorization, rate limiting, and policy enforcement.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode examines the risks of code execution in AI systems and the security benefits of sandboxing. Many AI applications incorporate features allowing generated or user-provided code to run, enabling advanced analysis, automation, or integration with development environments.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode addresses connector and plugin security, focusing on how third-party integrations expand the attack surface of AI applications. Connectors link systems to external data or services, while plugins extend model functionality by calling APIs or executing tasks.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode explores cloud and infrastructure security in the context of AI, focusing on GPU clusters, multitenancy, storage, and network isolation.…
Testing, Monitoring, Infrastructure and Supply Chain
This episode examines keys, encryption, and attestation as core mechanisms for ensuring confidentiality, integrity, and trust in AI systems.…
Governance, Frameworks and Program Operations
This episode introduces governance and acceptable use policies as organizational frameworks that guide secure and ethical AI adoption.…
Governance, Frameworks and Program Operations
This episode examines risk frameworks for AI security, focusing on the NIST AI Risk Management Framework and ISO/IEC 42001. These frameworks provide structured approaches to identify, assess, mitigate, and monitor AI-specific risks across technical and organizational domains.…
Governance, Frameworks and Program Operations
This episode covers threat modeling as a structured method for identifying and prioritizing risks in AI systems.…
Governance, Frameworks and Program Operations
This episode introduces the OWASP GenAI/LLM Top 10, a structured list of the most critical risks associated with generative AI and large language models.…
Governance, Frameworks and Program Operations
This episode examines the secure software development lifecycle (SDLC) for AI, emphasizing integration of security at each stage of system creation.…
Governance, Frameworks and Program Operations
This episode addresses incident response for AI-specific security events, focusing on structured detection, containment, and remediation.…
Governance, Frameworks and Program Operations
This episode explores the risks of deepfakes and synthetic media, examining how generative AI enables the creation of realistic but deceptive audio, video, and images.…
Governance, Frameworks and Program Operations
This episode examines content provenance and watermarking as methods to authenticate AI-generated or human-created content, providing assurance of originality and integrity.…
Governance, Frameworks and Program Operations
This episode introduces the legal and compliance horizon for AI security, giving learners a high-level view of regulatory landscapes without overwhelming them with acronyms.…
Governance, Frameworks and Program Operations
This episode explores third-party and vendor risk management in AI security, focusing on the challenges of relying on external providers for models, datasets, APIs, and infrastructure.…
Governance, Frameworks and Program Operations
This episode examines enterprise architecture patterns for secure AI deployments, focusing on how organizations structure systems to balance scalability, performance, and resilience.…
Governance, Frameworks and Program Operations
This episode focuses on people and process as integral elements of AI security, highlighting how organizational culture and defined responsibilities reinforce technical defenses.…
Governance, Frameworks and Program Operations
This episode introduces program management patterns for phased AI security adoption, with emphasis on the 30/60/90-day framework.…
Emerging AI Security Engineering
This episode introduces multimodal and cross-modal security, focusing on AI systems that process images, audio, video, and text simultaneously.…
Emerging AI Security Engineering
This episode examines on-device and edge AI security, focusing on models deployed in mobile, IoT, or embedded systems where resources are constrained and connectivity may be intermittent.…
Emerging AI Security Engineering
This episode covers guardrails engineering, emphasizing the design of policy-driven controls that prevent unsafe or unauthorized AI outputs. Guardrails include policy domain-specific languages (DSLs), prompt filters, allow/deny lists, and rejection tuning mechanisms.…
Emerging AI Security Engineering
This episode introduces confidential computing as an advanced safeguard for AI workloads, focusing on hardware-based protections such as trusted execution environments (TEEs), secure enclaves, and encrypted inference.…
Emerging AI Security Engineering
This episode examines automated adversarial generation, where AI systems are used to create adversarial examples, fuzz prompts, and continuously probe defenses.…
Try another term or clear one of the filters.
A Practical Study Routine
Use the free audio course during a commute, walk, workout, or focused study session.
Follow the course with your own notes and use the related Cyber Wiki entries for additional context.
Return to difficult lessons and search the site for related concepts, examples, and explanations.
Related Magazine Features
Related Cyber Wiki
An AI acceptable use policy defines approved, restricted, and prohibited uses of AI services, models, data, accounts, and generated content.
Agentic AIAn AI agent selects actions and invokes tools, services, or workflows to pursue a goal across multiple steps.
AI assuranceAI audit scope defines the systems, life-cycle stages, data, decisions, vendors, locations, and stakeholders included in an engagement, while audit criteria define the requirements used to judge them.
Agentic AI securityAI connector and plugin security governs integrations that let models read data or act through external applications and services.
AI data securityAI data lifecycle security protects information during collection, labeling, storage, use, sharing, retention, and deletion.
AI privacy governanceAI data-rights and deletion processes handle access, correction, objection, restriction, portability, and erasure across datasets, models, embeddings, caches, logs, and derived outputs.
