Even when AI systems aren't explicitly trained on your personal data, they can predict private facts about you by finding statistical patterns in what they've learned. An AI trained on aggregate salary data might infer your income from your job title and location, demonstrating that omission isn't the same as protection.
Inference attacks occur when an AI model uses publicly available or indirectly obtained data points to accurately predict information you never explicitly shared, such as your income, health status, or political views.
These attacks expose a critical gap between what you choose to disclose and what AI can deduce, and learning how they work empowers you to audit your public digital presence and reduce the signals that make you predictable.
Peri can explain this concept, give practical examples, help you decide whether it applies to your situation, or recommend a journey if appropriate.
Explore related journeys or tell Peri what you're working through.