Answers are grounded in this paper and cite their sources.
Recent machine learning models are sensitive to adversarial input perturbation. That is, an attacker may easily mislead an otherwise wellperforming image classification system by altering some pixels. It is quite challenging to prove that a network will have correct output when changing slightly some regions of the images. This is why only a few works targeted this problem. Although there are an increasing number of studies on this field, really reliable robustness evaluation is still an open issue. We will present some theoretical results on the dependency problem of interval arithmetic what is critical in interval based verification.
No takes yet. Share an insight, caveat, or question.
Tibor Csendes (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: