OVERVIEW

This course provides advanced knowledge on data protection and privacy-preserving technologies, with a particular focus on data anonymization, privacy-enhancing technologies, and privacy-aware machine learning. Students will study both the theoretical foundations and practical implementation of modern privacy-preserving techniques for different types of data, including multidimensional datasets, graphs, time series, transactional data, mobile applications, and machine learning systems.
The course also addresses emerging challenges in privacy protection, including differential privacy, federated unlearning, privacy-preserving data mining, privacy risks in mobile platforms, blockchain de-anonymization, and privacy issues related to Large Language Models (LLMs). Practical laboratory activities and project work enable students to apply acquired knowledge to real-world privacy engineering scenarios.

AIMS AND CONTENT

LEARNING OUTCOMES

The purpose of the teaching unit is to introduce the theoretical and practical bases of the anonymization of personal data, with particular reference to state-of-the-art techniques for the anonymization of multidimensional data, graphs, time series, longitudinal and transactional data, as well as the legal foundations related to the protection of personal data.

AIMS AND LEARNING OUTCOMES

Knowledge and Understanding

At the end of the course, students will be able to:

• Understand the fundamental concepts of data protection and privacy.
• Explain privacy risks associated with the collection, processing, sharing, and analysis of personal data.
• Describe state-of-the-art anonymization and privacy-preserving techniques for different data types.
• Understand the principles, assumptions, and limitations of Differential Privacy.
• Understand privacy challenges arising in modern AI systems, federated learning environments, mobile ecosystems, and Large Language Models.

Applying Knowledge and Understanding

Students will be able to:

• Apply anonymization techniques to different classes of datasets.
• Implement and evaluate privacy-preserving mechanisms using software tools and programming environments.
• Analyze privacy risks in real-world datasets and software systems.
• Select appropriate privacy-enhancing technologies according to application requirements and threat models.
• Develop privacy-aware solutions through practical assignments and project activities.

Making Judgments

Students will be able to:

• Critically assess the effectiveness and limitations of privacy-preserving approaches.
• Evaluate trade-offs between privacy, utility, accuracy, and system performance.
• Compare alternative privacy models and anonymization strategies for specific application domains.
• Assess emerging privacy threats in AI, blockchain, and mobile systems.

Communication Skills

Students will be able to:

• Present privacy-related technical problems and solutions using appropriate terminology.
• Discuss scientific literature in the field of data privacy and privacy-enhancing technologies.
• Effectively communicate the results of privacy analyses and project activities.

Learning Skills

Students will be able to:

• Independently study recent scientific literature on privacy and data protection.
• Keep track of emerging privacy technologies and research trends.
• Develop autonomous problem-solving skills in privacy engineering and data protection.

PREREQUISITES

Students are expected to have:

• Programming skills.
• Foundations of algorithms and data structures.
• Basic knowledge of probability and statistics.
• Fundamental concepts in data management and machine learning are beneficial but not mandatory.

TEACHING METHODS

Lectures will combine theoretical instruction with practical implementation activities. 

SYLLABUS/CONTENT

Foundations of Data Protection and Privacy

• Introduction to privacy-preserving data publishing.
• Privacy models and threat scenarios.
• Multidimensional data anonymization.

Classical Data Anonymization Techniques

• k-anonymity.
• l-diversity.
• t-closeness.
• Anonymization of graph data (k-degree anonymity).
• Anonymization of time-series data ((k,p)-anonymity).
• Transactional data anonymization (CAHD).

Threats and Limitations

• Re-identification attacks.
• Privacy Skyline.
• De-anonymization techniques.
• Bitcoin de-anonymization.

Privacy-Preserving Data Analysis

• Privacy-preserving data mining.
• MASK algorithm.
• Test data anonymization ((K,b)-anonymity).

Modern Privacy-Enhancing Technologies

• Differential Privacy.
• Federated Unlearning.
• Privacy-preserving machine learning.

Privacy in Emerging Systems

• Anonymization in mobile applications.
• Privacy policies in Android ecosystems.
• Privacy challenges in Large Language Models and AI systems.

Project Work: Design, implementation, and evaluation of a privacy-preserving solution addressing a realistic use case.

RECOMMENDED READING/BIBLIOGRAPHY

The course primarily relies on:

• Scientific papers selected from the international literature.
• Lecture slides and teaching material provided during the course.
• Additional research articles discussed throughout the lectures.

TEACHERS AND EXAM BOARD

Exam Board

ALESSIO MERLO (President)

GIACOMO LONGO (President Substitute)

LESSONS

LESSONS START

Sept. 24, 2026

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

The exam will consist of a presentation and discussion of a project on implementing and evaluating an anonymization algorithm from the scientific literature, as well as an oral examination on the course topics.

ASSESSMENT METHODS

The final grade is based on:

• A practical project involving the analysis, implementation, or evaluation of privacy-preserving techniques.
• An oral examination focused on the theoretical foundations, practical methodologies, and critical discussion of privacy-preserving technologies.

The assessment verifies the achievement of the learning outcomes described above, with particular attention to the student's ability to apply privacy techniques, critically evaluate their effectiveness, and discuss current research challenges.

FURTHER INFORMATION

Students with valid certifications for Specific Learning Disorders (SLD) may request accommodations for exams at least 7 days prior to the exam date by filling out the “accommodation request form” (available via online services at https://modulionline.unige.it/richiesta-adattamenti# no-back), which will be automatically forwarded by the system to the instructor in charge of the course and to the faculty liaison for students with disabilities and SLDs in their School/Department. 

The student will receive a copy of their request.