Security when working with AI – how to avoid data leaks (AISEC)

AI - Artificial Intelligence, AI for End Users

THIS TRAINING COURSE WILL HELP YOU:

  • Understand security risks of using AI tools
  • Recognize situations that can cause sensitive data leaks
  • Know what data must never be shared with AI tools
  • Understand prompt injection and output manipulation
  • Verify AI answers and implement basic AI governance

WHO SHOULD ATTEND?

  • Employees using AI for documents, texts, analyses or data
  • Managers and team leads who set safe AI usage rules
  • Specialists in marketing, HR, analytics, IT, legal or support
  • Anyone who wants to use AI effectively and securely

COURSE LOCATION AND AVAILABLE DATES



Choose whether to attend in person in our classroom or join online. You can select your preferred format during registration. Learn more about hybrid training.

Public courses are usually delivered in Czech, but this course is also available in English. We can arrange private training for your team online, at your premises or in our classrooms, and tailor the content to your needs.

For groups of around 4 or more participants, private training can already be comparable in price to booking individual places on a public course. Send us your requirements and we’ll recommend the best format and provide an exact quote.

Request training in English

Course content:

Hide details
  • Introduction to AI security
    1. How generative AI systems (LLMs) work and how they handle context and inputs
    2. Typical ways companies use AI (ChatGPT, Copilot, internal AI assistants)
    3. Main security risks associated with AI tools
    4. Overview of real incidents and common user mistakes
  • Working with data when using AI
    1. How AI treats information placed in prompts or documents
    2. Types of data that should not be shared with AI tools (internal docs, personal data)
    3. Risks of sharing sensitive information with external AI services
    4. Practical anonymization techniques and safe data handling practices
  • Output manipulation (Prompt Injection)
    1. The concept of prompt injection and how outputs can be manipulated
    2. Hidden instructions in documents, emails or web content
    3. Attack scenarios when working with documents and external sources
    4. How to detect these attacks and how to defend against them
  • Trustworthiness of AI responses
    1. AI hallucinations and why inaccurate answers occur
    2. How AI uses information sources
    3. Quick methods to verify AI responses
    4. Situations when AI outputs must be checked or avoided
  • Safe AI use in an organization
    1. Setting basic rules for AI use in the company
    2. AI policy and recommended internal procedures
    3. Employee roles in secure AI usage
    4. A practical checklist for safe AI practices
  • Practical scenarios and recommendations
    1. Analysis of typical AI use cases in the workplace
    2. Identifying security risks in those scenarios
    3. Recommended procedures for safe AI tool use
    4. Discussion of concrete, real-world examples
Schedule:
2 days (9:00-17:00)
Price per person:
376.00 € ( 454.96 € incl. 21% VAT)

Training and learning environment