Lecture

Safe Machine Learning: Cryptographic Opportunities

Related lectures (31)

Socially-aware Artificial Intelligence for Last-mile Mobility

Explores socially-aware AI for last-mile mobility, focusing on understanding social etiquettes, anticipating behaviors, and forecasting crowd movements.

Homomorphic Encryption: Delegating Calculations Securely

Explores homomorphic encryption, enabling secure computations on encrypted data without data exposure, with applications in healthcare and finance.

Gradient-Based Algorithms in High-Dimensional Learning

Provides insights on gradient-based algorithms, deep learning mysteries, and the challenges of non-convex problems.

AI for Science

Explores fundamental principles in scientific research, the impact of computers, numerical algorithms, and deep learning in solving high-dimensional problems.

Homomorphic Encryption: Cloud and Aggregation

Explores homomorphic encryption for secure cloud computing and data aggregation.

Homomorphic Encryption

Introduces homomorphic encryption, enabling computation on encrypted data without decryption, covering security, applications, and practical aspects.

Contact Tracing and Cryptography

Explores contact tracing in public spaces and the role of cryptography in ensuring secure and private data transmission.

Veridical Data Science: Responsible, Reliable, Reproducible

By Prof. Bin Yu explores veridical data science, emphasizing responsible, reliable, and reproducible data analysis and decision-making.

Differentiable Ranking and Sorting

Explores differentiable ranking and sorting techniques for machine learning applications.

Technologies for Identity & Anonymity

Explores technologies for identity and anonymity, including e-ID, social media identities, and cryptographic signatures.

Introduction to Cryptography: One-Time Pad and Public-Key Systems

Introduces cryptography, focusing on the one-time pad and public-key systems, emphasizing privacy and authenticity in information security.

Homomorphic Encryption

Explores homomorphic encryption, enabling computations on encrypted data without decryption, with practical applications in secure medical clouds.

Anonymous Credentials: Binding Identity to Physical Authentication

Covers the binding of anonymous credentials to human identity through visual authentication and cryptographic protocols.

Machine Learning Security

Explores machine learning security, including model stealing, altering outputs, adversarial conditions, and privacy challenges, emphasizing the importance of addressing biases in machine learning models.

Non-Attributable Email: Forward-Forgeable Signatures

Explores non-attributable email using forward-forgeable signatures and the legal risks faced by security researchers.

E-Voting: Research and Challenges

Explores e-voting research, digital algorithms, privacy challenges, and cryptographic methods in ensuring legitimacy and participation.

Machine Learning and Privacy

Explores Federated Machine Learning and Differential Privacy in Machine Learning, discussing attacks, defenses, and challenges.

Introduction to Technology and Humanitarian Action

Introduces the MUK on technology, digital transformation, and humanitarian action, emphasizing responsible technology use in the humanitarian sector.

Internet Capsules: Opportunities and Dangers

Explores the opportunities and dangers of the internet, including encryption, surveillance, and censorship.

Data Privacy in eHealth Research

Explores data privacy challenges and perspectives in eHealth research, focusing on GDPR compliance, sensitive health data management, and decentralized agents.