Tag
#privacy
3 posts tagged privacy.
- attacks
Model Inversion Attacks: Reconstructing Training Data from Model Outputs
From Fredrikson's pharmacogenetics exploit to Geiping's gradient inversion, model inversion attacks recover private training data in ways most ML engineers don't expect.
- attacks
Training Data Extraction from LLMs: The Carlini et al. Results and What They Mean
Carlini et al. demonstrated verbatim extraction of training data from GPT-2. The results have been widely misread. Here's what the paper actually shows, what makes data extractable, and what production mitigations work.
- attacks
Membership Inference Attacks: What Actually Works Against Production ML APIs
Shokri et al.'s shadow-model attack is the canonical reference, but the gap between the paper's threat model and a real rate-limited API is wide. Here's what survives that gap.