{"slug": "are-safety-guarantees-in-neural-networks-safe-how-to-compute-trustworthy", "title": "Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications", "summary": "Researchers introduced the apothem measure for computing robustness certifications in neural networks, achieving optimal certifications with linear oracle calls. They proved volume-optimal oracle-based algorithms are intractable and presented the ParallelepipedoNN system, which showed at least two-fold improvement on MNIST benchmarks.", "body_md": "arXiv:2606.23858v1 Announce Type: new\nAbstract: A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify. To mitigate this problem, recent research focuses on the computation of robustness certifications, which, for a given input, determine the largest distortion the input may receive without breaking the network's prediction. Robustness certifications can be interpreted as an axis-aligned hyper-rectangle (multi-dimensional intervals). Most existing approaches focus on maximizing the certification's volume, but recent intractability results prohibit the computation of volume-optimal certifications in reasonable time. We introduce the apothem measure and show how to compute apothem-optimal certifications in a linear number of calls to a NN verifier (oracle) w.r.t. the input domain's diameter. Moreover, we prove that we cannot have a volume-optimal, oracle-based algorithm, even if we discard the oracle costs. Also, we introduce dual certifications -- an interval including all instances of a class -- thus providing apothem-minimum upper bounds to a robustness certification. Further, we present the ParallelepipedoNN system, which we evaluate on the standard MNIST and Fashion MNIST benchmarks. A preliminary comparison with existing work on the same datasets reveals at least two-fold improvement w.r.t. the minimum edge length.", "url": "https://wpnews.pro/news/are-safety-guarantees-in-neural-networks-safe-how-to-compute-trustworthy", "canonical_source": "https://arxiv.org/abs/2606.23858", "published_at": "2026-06-24 04:00:00+00:00", "updated_at": "2026-06-24 04:29:11.494242+00:00", "lang": "en", "topics": ["ai-safety", "neural-networks", "machine-learning", "ai-research"], "entities": ["ParallelepipedoNN", "MNIST", "Fashion MNIST"], "alternates": {"html": "https://wpnews.pro/news/are-safety-guarantees-in-neural-networks-safe-how-to-compute-trustworthy", "markdown": "https://wpnews.pro/news/are-safety-guarantees-in-neural-networks-safe-how-to-compute-trustworthy.md", "text": "https://wpnews.pro/news/are-safety-guarantees-in-neural-networks-safe-how-to-compute-trustworthy.txt", "jsonld": "https://wpnews.pro/news/are-safety-guarantees-in-neural-networks-safe-how-to-compute-trustworthy.jsonld"}}