Toll Cameras Are Now Police Cameras: NSW's Privacy Shift and What Drivers Can Do
New NSW laws will give police unredacted access to toll road camera images. Here's what that means for your privacy, how the surveillance network works, and practical countermeasures for drivers.
Defeating Surveillance Pricing with Digital Noise
How AI algorithms guess the absolute maximum you'll pay, and how you can fight back by poisoning their data with adversarial perturbation techniques.
Adversarial Clothing Is Going Mainstream: Fashion Meets Facial Recognition Defence
The Guardian reports on a new wave of clothing brands embedding adversarial patterns into garments to confuse facial recognition systems — and why this might be the next big fashion trend.
AdverTorch: BorealisAI's Practical Toolbox for Adversarial Attacks and Defences
A walkthrough of AdverTorch — a PyTorch toolbox from BorealisAI that gives researchers and tinkerers a ready-made kit of adversarial attacks, defences, and robust training methods.
Glaze: The Digital Cloak Protecting Artists from AI Style Mimicry
How University of Chicago's Glaze tool uses adversarial perturbations to cloak artists' personal styles from AI image generators — a technical explainer.
Nightshade: How Data Poisoning Became a Weapon for Artists Against AI
A deep dive into Nightshade — the data poisoning tool from University of Chicago that lets artists fight back against unauthorised AI training by corrupting the models themselves.
A Beginner's Guide to Adversarial Perturbation
An introduction to adversarial perturbation — the mathematical blind spots in AI systems, why they matter for security, and how individuals apply these principles in everyday environments.
Evading Facial Recognition in 2026: Modern Countermeasures
An evaluation of physical adversarial patches, makeup patterns, and glasses designed to disrupt modern facial detection pipelines.
Poisoning Datasets: A Theoretical Approach to Data Sovereignty
An analysis of techniques used to inject adversarial noise into public datasets to disrupt corporate scraping.