Data Security in Artificial Intelligence Projects Training

Infoshare is the largest tech community in CEE and the organizer of the leading tech conference in Gdańsk. It connects startups, investors, corporations, and innovation enthusiasts. It promotes entrepreneurship, knowledge sharing, and networking. Through events, competitions, and programs, it supports the development of the tech ecosystem in Poland and the region.

An advanced, practical course dedicated to key aspects of data protection in AI projects. The training combines a solid theoretical foundation with intensive practical workshops that will allow participants to acquire the necessary skills to secure sensitive information in artificial intelligence environments. The emphasis is on practical solutions, case studies, and direct experience in identifying and mitigating data security threats.

• AI and data science engineers
• Customer service teams
• AI project managers
• Programmers working on projects utilizing artificial intelligence
• Data analysts interested in security aspects
• Students in computer science and mathematics fields

• A comprehensive approach to data protection in AI projects
• Identification and prevention of security vulnerabilities in AI systems
• Practical techniques for securing models and datasets
• Implementation of privacy standards and protection of sensitive information

DAY 1: FUNDAMENTALS OF DATA SECURITY IN AI

1. INTRODUCTION TO DATA SECURITY IN AI
    • analysis of key security threats in AI projects
    • overview of the most common attack vectors on artificial intelligence systems
    • discussion of legal and regulatory frameworks (GDPR)

2. DATASET PROTECTION
    • encryption methods in data storage and transfer processes
    • techniques for data anonymization and pseudonymization
    • differential privacy techniques
    • federated learning techniques for enhanced privacy
    • practical workshops – implementation of secure data preprocessing

3. PRACTICAL WORKSHOP – ANALYSIS OF AI MODEL VULNERABILITIES
    • identification of security gaps in machine learning models
    • tools for automatic attack detection
    • practical attempts to manipulate models (adversarial examples)
    • defense techniques against attacks on AI models

DAY 2: ADVANCED DATA PROTECTION TECHNIQUES

4. SECURITY OF MODELS AND ALGORITHMS
 • methods for protecting the intellectual property of AI models
 • techniques for securing algorithms against unauthorized access
 • case studies – real scenarios of security breaches
 • incident response procedures

5. PRIVACY AND ETHICS IN AI
    • principles of designing systems with privacy in mind (Privacy by Design)
    • ethical aspects of processing personal data
    • mechanisms for controlling consent and access to data

6. FINAL WORKSHOP – COMPREHENSIVE SECURITY PROJECT
    • building a comprehensive security strategy for an AI project
    • simulation of security breach scenarios
    • development of a risk mitigation plan

16 h/2 days