AI Privacy
What models remember and what they leak. Training-data privacy, memorisation and extraction, inference attacks against individuals, and the privacy-enhancing technologies that are deployable today.
-
Federated Learning Privacy Depends on What the Server Is Allowed to Send
Federated learning keeps raw data on the device, and the security question that decides your actual risk is not whether…
Read More » -
Secure Multi-Party Computation Hides the Inputs, Not the Answer
Secure multi-party computation protects the inputs to a computation and reveals the output exactly as computed. In machine learning the…
Read More » -
Homomorphic Encryption for ML: What the Overhead Buys
Homomorphic encryption lets an untrusted server compute on data it cannot read. The overhead is severe enough that the set…
Read More » -
Differential Privacy Protects the Training Set, Not the System
What epsilon actually guarantees, why deployed values sit near 10, and what differential privacy leaves uncovered in a 2026 AI…
Read More » -
What Model Inversion Attacks Actually Recover
Model inversion recovers class representatives more often than individuals, its dominant evaluation framework counts adversarial examples as successful reconstructions, and…
Read More » -
The Future of Privacy in our Smart Living – Part 2
In a world where the population is increasing and resources are finite, we need to find smarter ways of living…
Read More » -
The Future of Privacy in our Smart Living
It is inevitable and important that human society moves towards a smarter way of living. We must use intelligent ways…
Read More »
