Home▸Cybersecurity▸Generative AI Model Extraction & Data Leakage

Generative AI Model Extraction & Data Leakage

Interactive 3D simulator of two real attacks on generative AI APIs: model extraction (cloning a model via input-output query pairs) and membership inference (detecting whether a record was in the training set). Toggle rate limiting, query obfuscation and differential privacy to see how each defense blunts the attack.

Cybersecurity3DAdvanced60 FPS

Two real attack classes against generative AI systems, separate from prompt injection: model extraction, where an attacker floods the API with queries to train a local clone from input-output pairs, and membership inference, where an attacker probes model confidence to determine whether a specific record was in the training set. Toggle rate limiting, query obfuscation and differential privacy to see how each defense narrows the attacker's advantage.

⚙ Under the hood

3D simulator of two real attacks on generative AI APIs, distinct from prompt injection: model extraction, where thousands of query-response pairs are used to train a cloned model, and membership inference, where confidence gaps expose whether a record was in the training set. Toggle rate limiting, query obfuscation and differential privacy to see each defense blunt the attack.

cybersecurityai-securitymodel-extractionmembership-inferencedifferential-privacyThree.js

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install