Low Cost High Power Membership Inference Attacks
Explore robust, efficient membership inference attacks for machine learning privacy risk assessment. Learn to differentiate population and training data with minimal computational overhead.
The Data Minimization Principle in Machine Learning
Explore data minimization in machine learning, its challenges, and practical implementations. Examine optimization-based formalization and applications in high-stakes domains, revealing insights on privacy and efficiency.
Private Stochastic Optimization with Large Worst-Case Lipschitz Parameter
Explore differentially private stochastic optimization techniques for loss functions with large worst-case Lipschitz parameters, addressing outliers and heavy-tailed data for improved excess risk bounds.
Home Automation Crash Course - 2024
Explore Home Assistant's architecture, ecosystem, and capabilities for building secure, privacy-focused local home automation systems.
A Guide to Responsible Data Collection in Open Source
Explore best practices for ethical and effective usage data collection in open source projects, covering community, security, privacy, compliance, and governance aspects.
Installing and Using Local AI for n8n
Learn to integrate locally-run LLMs with n8n for cost-effective and privacy-focused operations. Explore three setup methods with n8n engineer Oleg in this informative tutorial.
Blind Signatures - Crypto 2024
Explore advanced cryptographic concepts and applications of blind signatures in this cutting-edge session from Crypto 2024, chaired by Masayuki Abe.
Practical Cryptographic Solutions for Secure Inference and Private Benchmarking
Explore practical cryptographic solutions for secure inference and private benchmarking in machine learning, presented by Nishanth Chandran at PPML 2024.
Samplable Anonymous Aggregation for Private Federated Data Analysis
Kunal Talwar explores samplable anonymous aggregation for private federated data analysis, discussing innovative approaches to privacy-preserving machine learning in distributed settings.
Algorithmic Injustice and the Algorithmic Accountability Act
Explore algorithmic bias in criminal justice and everyday settings, examining the Algorithmic Accountability Act's impact on shopping and social media platforms.
The Ethical Dilemma of AI - Save the World or Forsake It?
Exploring AI's ethical challenges: balancing life-saving potential with privacy concerns, fairness issues, and corporate interests. A critical look at AI's impact on society and regulation needs.
AI for Inclusive Society - Responsible AI
Explore responsible AI principles for inclusive, trustworthy solutions. Learn about AI fluency, shared accountability, and intentional inclusivity to avoid unintentional exclusion in AI development and deployment.
Vacuum Robot Security and Privacy
Explore security vulnerabilities in smart vacuum robots, learn root access techniques, and discover ways to protect your privacy while using these AI-powered devices.
Tracking the Pandemic: Data Science and AI in Tackling Covid-19
Explore data science's role in tackling Covid-19, including smartphone tracking and AI research for crisis solutions, with Jon Crowcroft from the Alan Turing Institute.
Attribute-based Encryption
Explore cutting-edge developments in attribute-based encryption at this Crypto 2024 session, featuring expert insights and the latest research in cryptographic access control.
How I Met Your Data - Navigating Data Breaches and Cybersecurity
Explore data breaches with Troy Hunt: from initial chaos to dealings with cybercriminals and law enforcement. Gain insights, anecdotes, and practical wisdom for navigating digital security challenges.
Building Open-Source AI-Enabled Smart Glasses with AR
Explore the creation of open-source AI-enabled smart glasses with AR, focusing on innovation, user experience, and the challenges of hardware development in the tech industry.
Privacy Backdoors: Stealing Data with Corrupted Pretrained Models - Explained
Explore how tampering with pretrained models can compromise privacy, enabling attackers to reconstruct finetuning data. Learn about privacy backdoors in transformers and their implications for machine learning security.
Differentially Private Release of Spatio-Temporal Data Statistics
Explore strategies for releasing spatio-temporal data statistics with differential privacy, focusing on sample mean and variance calculations while minimizing reconstruction errors in urban data management.
Personalized and Context-Aware Digital Nudging for Behavioral Change
Explore the science of digital nudging and how personalized, context-aware suggestions can effectively influence behavioral change while respecting ethical boundaries and user privacy.
Flipped Huber - A New Additive Noise Mechanism for Differential Privacy
Discover a novel additive noise mechanism for differential privacy that combines Laplace and Gaussian distributions, offering enhanced privacy protection while maintaining data accuracy in query responses.