AI security
13 moments from 12 videos · 33:14 min total
Explore safety practices for building applications on top of large language models. These expert talks guide security specialists and developers in preventing injection and leaks.
Current state of security in AI applications
Why the security domain is playing catch-up with rapidly evolving AI protocols and agent interactions.
Defining the core dimensions of generative AI security
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
Traditional security mechanisms cannot guarantee trusting generative AI behavior in the face of evolving prompts and external content.
Evaluating supply chain risk with AI security assistants
Interacting directly with AI assistants on the web accelerates security assessments of open source dependencies like Bootstrap.
Increasing security stack investments to mitigate novel AI vectors
The surge in new AI attack vectors requires proactive frameworks and robust investment in security tooling.
Navigating new cybersecurity challenges in artificial intelligence applications
Treating external intelligence as a black box introduces significant security vulnerabilities that require dedicated exploratory testing strategies.
Treating AI responses as untrusted user data inputs
Protecting core infrastructure by isolating execution environments and enforcing classical application security checks on intelligent agents.
Securing AI agents against internal and external threat vectors
Operating AI at scale necessitates strict devsecops guardrails to prevent accidental secret exposure and defend against outside aggressors.
Distinguishing AI-assisted users from experienced security professionals
Why relying on AI-generated security answers still requires critical skepticism, strict accountability, and deep domain expertise.
Core AI security risks and data poisoning
Why trusting language model outputs equates to trusting potentially poisoned training data.
Scaling AI-native security capabilities across the system
Matching engineering velocity requires continuous learning and embedding validation seamlessly into code generation workflows.
Utilizing industry threat models for AI security
Navigating frameworks from OWASP, NIST, and MITRE to understand and mitigate machine learning vulnerabilities.
Securing AI agents against malicious MCP servers
Enforcing scoped APIs and modern authorization standards mitigates supply chain attacks and unauthorized data exfiltration.
Your mix. Instantly.
More mixes
AI & Machine Learning
AI coding agents
AI & Machine Learning
MCP (Model Context Protocol)
AI & Machine Learning
RAG
Languages & Frameworks
TypeScript
Languages & Frameworks
React
Languages & Frameworks
Java
Cloud, Platform & Data
Platform engineering
Cloud, Platform & Data
Observability
Cloud, Platform & Data
Infrastructure as code
Architecture, Quality & Security
System architecture
Architecture, Quality & Security
Code review
Architecture, Quality & Security
Software supply chain security
Leadership, Career & Community
Engineering strategy
Leadership, Career & Community
Developer experience
Leadership, Career & Community