Ethical and Secure AI Vulnerability Disclosure - Challenges and Best Practices
Explore the complexities of AI vulnerability disclosure, focusing on ethical challenges, bias management, and security implications while examining real-world cases and solutions for responsible reporting.
Ethical and Secure AI Vulnerability Disclosure - Challenges and Best Practices
Explore the complexities of AI vulnerability disclosure, examining ethical challenges, bias concerns, and security implications while learning practical approaches to responsible vulnerability management.
A Practical Guide to Securing Your AI Application
Explore practical strategies for securing AI applications, from responsible AI principles to vulnerability control and evaluation techniques. Learn to implement guardrails and observability in generative AI projects.
Getting AI to Do the Unexpected - Exploring LLM Vulnerabilities and Defenses
Explore LLM vulnerabilities, attacks, and defenses. Learn about prompt injections, output handling, and jailbreaking. Discover secure practices for AI implementation and see real-world examples.
AI Safety, Security, and Play - Episode 137
Explore AI safety and security with David Haber, covering prompt injections, data poisoning, LLM vulnerabilities, and approaches to handling sensitive data in AI models.
Evaluating LLM Applications - Insights from Shahul Es
Explore LLM application evaluation with Shahul Es. Learn about debugging, benchmarks, custom data distributions, and fine-tuning to enhance model performance in this insightful discussion.
Navigating the AI Frontier: The Power of Synthetic Data and Agent Evaluations in LLM Development
Explore synthetic data and agent evaluations in LLM development. Learn strategies for enhancing model behavior, prototyping, testing, and fine-tuning to build robust AI applications.
Unveiling Tomorrow: Exploring the Frontiers of Generative AI
Explore the frontiers of generative AI, from emerging models and use cases to challenges, trends, and regulatory implications. Gain insights into implementation, security, and future developments.
Harnessing AI APIs for Safer, Accurate, and Reliable Applications
Explore strategies for integrating AI APIs to build safer, more accurate applications. Learn to mitigate risks, enhance performance, and improve quality in production settings for RAG and AI-assisted knowledge work.
Secure and Govern Custom AI Built on Azure AI and Copilot Studio
Discover essential strategies for securing and governing custom AI applications, focusing on data security, compliance controls, vulnerability management, and protection against emerging AI threats.
Leveraging AI for Better Security Outcomes - Managing Risks and Implementation
Discover strategies to combat AI-driven security threats, implement effective AI security measures, and ensure compliance while managing risks like shadow AI, prompt injection, and data loss in modern organizations.
Model-Based Input Validation - Preventing Prompt Injection Attacks
Discover effective strategies for preventing prompt injection attacks through model-based input validation techniques, with practical demonstrations and comprehensive testing approaches.
Testing LLM-Powered Applications - Best Practices and Evaluation Methods
Master essential strategies and methodologies for testing LLM applications, covering security concerns, evaluation metrics, adversarial testing, and practical tools for building robust AI systems.
Formalizing and Benchmarking Prompt Injection Attacks and Defenses
Explore a systematic framework for understanding and evaluating prompt injection attacks on LLM applications, including analysis of 5 attack types and 10 defense mechanisms across multiple models.
OWASP Top 10 Security Risks for LLMs - Code Examples and Mitigation Strategies
Explore real-world security risks and vulnerabilities in AI systems through entertaining code examples, focusing on OWASP Top 10 AI/ML threats and practical defense strategies.
Generative AI Security: Top Considerations and Risk Mitigation Strategies
Explore essential security considerations for generative AI applications, covering risk mitigation strategies, data protection, prompt injection defense, and responsible implementation practices.
Black Hat USA 2025
Black Hat USA 2025
Black Hat USA 2024
Black Hat USA 2024
Black Hat Europe 2023
Black Hat Europe 2023
Black Hat Asia 2025
Black Hat Asia 2025
Black Hat Europe 2024
Black Hat Europe 2024