Tagged:

3 posts

• Model Inversion Attacks: Reconstructing Private Training Data from Model Confidence Scores

  A model's output probability scores are not neutral summaries — they encode information about the training data that produced them. Model inversion attacks exploit this to reconstruct representative training examples from API-level confidence values. This post covers the foundational Fredrikson et al. work, black-box and GAN-based variants, conditions for vulnerability, and how to distinguish this class from membership inference and training data extraction.

  Jul 13, 2026 privacy adversarial-ml model-inversion differential-privacy attack-defense training-data

• Differential Privacy in Practice: What the Math Guarantees (and What It Doesn't) for AI Training Data

  Differential privacy is the strongest mathematical privacy guarantee for ML training data — but the gap between formal ε-DP and deployed reality means many 'private' AI systems aren't nearly as private as advertised. This post bridges the math and the practice.

  Jul 6, 2026 privacy differential-privacy dp-sgd membership-inference training-data epsilon attack-defense llm-security

• Gradient Inversion Attacks: Reconstructing Private Training Data from Model Updates

  Gradients are not safe summaries of training data. In federated learning and fine-tuning pipelines where model updates are shared, a malicious aggregator can run gradient inversion to recover original training samples with alarming fidelity — and the defenses have hard limits.

  Jul 4, 2026 federated-learning privacy gradient-inversion differential-privacy training-data attack-defense