Panda to Gibbon Is the Least of Your Worries - Why Securing AI Is Not What You Think

Overview

Explore AI security best practices, attack history, and organizational strategies. Learn to secure AI implementations across platforms, debunking misconceptions and focusing on practical approaches.

Syllabus

• **Introduction to AI Security**
Overview of AI security landscape
Common misconceptions in AI security
• **History of AI Attacks**
Evolution of AI threat vectors
Case studies of notable AI attacks
Lessons learned from past breaches
• **AI Security Best Practices**
Fundamental principles of AI security
Secure coding for AI and ML models
Protecting data integrity and privacy
• **Vulnerability Assessment in AI Implementations**
Identifying potential vulnerabilities
Risk assessment methodologies for AI systems
• **Securing AI Across Platforms**
Cloud-based AI security strategies
On-premises AI system protections
Hybrid system security considerations
• **Debunking AI Security Myths**
Common fallacies in securing AI models
Realistic expectations in AI risk management
• **AI Governance and Organizational Strategy**
Establishing AI security policies
Role of AI ethics in security
Building a culture of security within AI teams
• **Practical Approaches to AI Security**
Implementing AI security frameworks
Incident response planning for AI environments
Continuous monitoring and updating of AI systems
• **Future of AI Security**
Emerging threats and trends
Preparing for the next generation of AI risks
• **Conclusion**
Summarizing key takeaways
Resources for further learning in AI security

Subjects

Conference Talks