> Markdown version of [/playlists/ai-security](https://www.wearedevelopers.com/playlists/ai-security). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Playlist: AI security 15 videos · 16 moments · 39.0 minutes ## Delay the AI Overlords: How OAuth and OpenFGA Can Keep Your AI Agents from Going Rogue - **Current state of security in AI applications** (00:04, 1min) — Why the security domain is playing catch-up with rapidly evolving AI protocols and agent interactions. [Learn more](https://www.wearedevelopers.com/videos/1637-delay-the-ai-overlords-how-oauth-and-openfga-can-keep-your-ai-agents-from-going-rogue) ## Building Trustworthy AI in Industry: Beyond Traditional Cybersecurity - **Defining the core dimensions of generative AI security** (13:59, 1min) — Comprehensive system trustworthiness merges responsible AI, robust security controls, and strict privacy compliance to ensure safe user interaction. - **Moving from secure software behavior to trustworthy AI** (00:00, 2min) — Traditional security mechanisms cannot guarantee trusting generative AI behavior in the face of evolving prompts and external content. [Learn more](https://www.wearedevelopers.com/videos/1948-building-trustworthy-ai-in-industry-beyond-traditional-cybersecurity) ## How GitHub secures open source - **Evaluating supply chain risk with AI security assistants** (12:26, 1min) — Interacting directly with AI assistants on the web accelerates security assessments of open source dependencies like Bootstrap. [Learn more](https://www.wearedevelopers.com/videos/1450-how-github-secures-open-source) ## The New AI Security Stack: Observe, Detect, Protect - **Increasing security stack investments to mitigate novel AI vectors** (02:52, 1min) — The surge in new AI attack vectors requires proactive frameworks and robust investment in security tooling. [Learn more](https://www.wearedevelopers.com/videos/100302-the-new-ai-security-stack-observe-detect-protect) ## From Monolith Tinkering to Modern Software Development - **Navigating new cybersecurity challenges in artificial intelligence applications** (10:01, 4min) — Treating external intelligence as a black box introduces significant security vulnerabilities that require dedicated exploratory testing strategies. [Learn more](https://www.wearedevelopers.com/videos/822-from-monolith-tinkering-to-modern-software-development) ## Prompt Injection, Poisoning & More: The Dark Side of LLMs - **Treating AI responses as untrusted user data inputs** (16:30, 2min) — Protecting core infrastructure by isolating execution environments and enforcing classical application security checks on intelligent agents. [Learn more](https://www.wearedevelopers.com/videos/1563-prompt-injection-poisoning-more-the-dark-side-of-llms) ## AI Won't Fix Your Engineering Culture - **Securing AI agents against internal and external threat vectors** (09:42, 2min) — Operating AI at scale necessitates strict devsecops guardrails to prevent accidental secret exposure and defend against outside aggressors. [Learn more](https://www.wearedevelopers.com/videos/100266-ai-won-t-fix-your-engineering-culture) ## Fighting the Next Wave of Cybercrime - **Distinguishing AI-assisted users from experienced security professionals** (25:59, 3min) — Why relying on AI-generated security answers still requires critical skepticism, strict accountability, and deep domain expertise. [Learn more](https://www.wearedevelopers.com/videos/100331-fighting-the-next-wave-of-cybercrime) ## WeAreDevelopers LIVE - SpeculAItions - **Security integration and AI skepticism in developer tooling** (00:05, 4min) — Applying AI agents to large pull requests while maintaining security guardrails and acknowledging growing skepticism around AI investments. [Learn more](https://www.wearedevelopers.com/videos/1830-wearedevelopers-live-speculaitions) ## Can Machines Dream of Secure Code? Emerging AI Security Risks in LLM-driven Developer Tools - **Core AI security risks and data poisoning** (09:08, 3min) — Why trusting language model outputs equates to trusting potentially poisoned training data. [Learn more](https://www.wearedevelopers.com/videos/1217-can-machines-dream-of-secure-code-emerging-ai-security-risks-in-llm-driven-developer-tools) ## A hundred ways to wreck your AI - the (in)security of machine learning systems - **Utilizing industry threat models for AI security** (08:59, 1min) — Navigating frameworks from OWASP, NIST, and MITRE to understand and mitigate machine learning vulnerabilities. [Learn more](https://www.wearedevelopers.com/videos/715-a-hundred-ways-to-wreck-your-ai-the-in-security-of-machine-learning-systems) ## Automated Security for the Entire SDLC - **Scaling AI-native security capabilities across the system** (17:56, 1min) — Matching engineering velocity requires continuous learning and embedding validation seamlessly into code generation workflows. [Learn more](https://www.wearedevelopers.com/videos/100323-automated-security-for-the-entire-sdlc) ## WWC24 - Chris Wysopal, Helmut Reisinger and Johannes Steger - Fighting Digital Threats in the Age of AI - **Consolidating fragmented security tools with precision AI methodologies** (08:27, 1min) — Replacing disconnected security toolchains with integrated posture management future-proofs the enterprise vulnerability lifecycle. [Learn more](https://www.wearedevelopers.com/videos/926-wwc24-chris-wysopal-helmut-reisinger-and-johannes-steger-fighting-digital-threats-in-the-age-of-ai) ## Spot, Squash, Secure: Fighting Security Bugs with GitHub Copilot - **Building a vulnerable application for security testing** (00:03, 2min) — Demonstrating the security risks of generating code with artificial intelligence tools. [Learn more](https://www.wearedevelopers.com/videos/100052-spot-squash-secure-fighting-security-bugs-with-github-copilot) ## Bringing AI Everywhere - **Hardware security features necessary for compliance and responsible AI** (24:38, 1min) — Meeting strict regional regulatory mandates requires establishing foundational hardware trust services that continuously protect sensitive data thr... [Learn more](https://www.wearedevelopers.com/videos/1132-bringing-ai-everywhere)