Re-thinking Data Availablity Attacks Against Deep Neural Networks

Understand

The unauthorized use of personal data for commercial purposes and the clandestine acquisition of private data for training machine learning models continue to raise concerns.

• In response to these issues, researchers have proposed availability attacks that aim to render data unexploitable.
• However, many current attack methods are rendered ineffective by adversarial training.
• In this paper, we re-examine the concept of unlearnable examples and discern that the existing robust error-minimizing noise presents an inaccurate optimization objective.