AI Security Deep Dive (TTAI2800)

About This Course:

AI and machine learning systems introduce unprecedented security challenges that traditional cybersecurity practices cannot adequately address. AI Security Deep Dive delivers the specialized knowledge and hands-on experience needed to secure AI/ML systems against sophisticated attacks, protect sensitive training data, and implement robust defenses for AI-integrated applications. This intensive course is designed for programmers building AI-enabled applications, security analysts responsible for protecting AI systems, cybersecurity professionals expanding into AI security, and technical managers overseeing AI implementation projects. 

Throughout three intensive days, you will master the fundamentals of machine learning from a security perspective, identify and exploit vulnerabilities in AI systems through hands-on exercises, and implement practical defenses against data poisoning, adversarial attacks, and privacy breaches. You will gain critical experience securing traditional applications that integrate AI models, including LLM-powered features, and learn to validate inputs and outputs to prevent prompt injection and other AI-specific attacks. The course combines essential AI/ML concepts with real-world security scenarios, ensuring you understand both the technical foundations and practical implementation challenges. 

Course Objectives:

• Master AI/ML security fundamentals from the ground up. Understand how machine learning works, identify attack vectors unique to AI systems, and assess security

• implications of different ML model types and deployment patterns. 

• Identify and exploit AI-specific vulnerabilities through hands-on exercises. Conduct data poisoning attacks, implement adversarial examples, perform model inversion and membership inference attacks, and understand the mechanics of AI system compromise. 

• Implement comprehensive defenses against AI security threats. Design and deploy robust input validation, output filtering, differential privacy mechanisms, and secure training pipelines to protect against known attack vectors. 

• Secure traditional applications integrating AI models and APIs. Build secure interfaces to LLM APIs, implement prompt injection defenses, validate AI-generated content, and establish secure authentication and authorization patterns. 

• Protect sensitive information in AI training and inference. Apply privacy-preserving techniques, detect and prevent data leakage through model behavior, and implement secure data handling practices for AI systems. 

• Establish enterprise-grade AI security governance and incident response. Develop AI security policies, create monitoring and detection capabilities, design incident response procedures for AI breaches, and build security-first AI development workflows. 

Audience:

• This intermediate-level course is designed for programmers and developers building AI-enabled applications, security analysts and cybersecurity professionals expanding into AI security, and technical leads responsible for securing AI implementations. Software engineers integrating machine learning models, security architects designing AI system defenses, and incident response teams preparing for AI-related threats will gain essential skills to identify vulnerabilities, implement robust security measures, and respond to sophisticated AI attacks. 

• Technical managers, DevSecOps professionals, and compliance officers overseeing AI security initiatives will also benefit from this course by gaining insights into AI-specific risk management, security governance frameworks, and regulatory compliance considerations. Whether you are directly developing AI systems, securing existing AI implementations, or establishing organizational AI security practices, this course provides the technical depth and practical experience needed to protect against emerging AI threats and build resilient AI-powered solutions

Prerequisites:

• Read code and understand basic programming concepts. The course provides hands-on opportunities using interactive Python and optionally other platforms.

• Successful students will need to setup a basic development environment, read and follow program logic and make minor modifications to code. 

• Awareness of traditional cybersecurity issues.  The successful student will have some prior knowledge of security issues in an IT environment. 

• Basic understanding of web applications.  Students should have some experience and exposure to basic HTTP based web technology. 

• Familiarity with data handling and basic statistical concepts. Understanding of data formats, databases, and basic data analysis principles. 

• Experience with software development lifecycle and security practices. Knowledge of testing, deployment, and security integration in development processes.