Answers are grounded in this paper and cite their sources.
The latest machine learning models are sensitive to adversarial inputs, i.e., the neural network can give incorrect results even with small changes in the learning case. To avoid this, techniques are used during learning, or verification is also possible. In many cases, these methods use interval arithmetic, whose usefulness is severely limited by overestimation. In this paper, we present and compare such methods that can handle this problem.
No takes yet. Share an insight, caveat, or question.
Szász et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: