Interval Certifications for Multilayered Perceptrons via Lattice Traversal
Quick Answer
This paper introduces a theoretical framework linking adversarial robustness in multilayered perceptrons (MLPs) to lattice traversal problems.
Quick Take
This paper introduces a theoretical framework linking adversarial robustness in multilayered perceptrons (MLPs) to lattice traversal problems. It defines sound and complete certifications for MLPs, demonstrating that while sound certifications are intractable, complete certifications can be efficiently solved with polynomial oracle calls. The study also presents empirical evaluations using the ParallelepipedoNN system.
Key Points
- Introduces lattice traversal as a method for MLP adversarial robustness certification.
- Defines sound and complete certifications for MLPs with distinct computational complexities.
- Demonstrates polynomial oracle calls for complete certifications, unlike sound certifications.
- Presents logarithmic algorithms for optimization in symmetric intervals.
- Empirical evaluations conducted using the ParallelepipedoNN system.
Paper Resources
📖 Reader Mode
~2 min readAbstract:In this work we present a rigorous theoretical framework to a foundational problem of AI safety, namely adversarial robustness. In particular, we show that the adversarial robustness problem can be reduced to a lattice traversal problem. Each element of this lattice corresponds to an interval, i.e., an axis-aligned hyper-rectangle, containing an input point $\mathbf{x}$. Consider a multilayered perceptron classifier (MLP). An interval $I$ constitutes a sound certification if $\mathbf{x} \in I$ and $\mathbf{x}$ can be freely perturbed in $I$ without changing the MLP's prediction. Complementarily, an interval $I$ constitutes a complete certification if $\mathbf{x} \in I$ and when $\mathbf{x}$ moves outside of $I$ the MLP's prediction is guaranteed to change. While the sound certification problem corresponds to the well-studied adversarial robustness, complete certifications have not been examined in the literature. We develop lattice traversal operators, which we apply in a refine & verify iterative scheme. Using formal MLP verifiers, sound maximality and complete minimality are guaranteed. Moreover, we examine objective optimization problems. There we discover some interesting asymmetries. For complete certifications, the minimum solution is obtained in polynomial oracle calls. This does not hold for sound certifications, where we prove strong intractability results. Additionally, we examine optimization problems in symmetric intervals (i.e., $\ell_\infty$-spheres), where we provide logarithmic algorithms. Finally, we present an empirical evaluation, using the novel ParallelepipedoNN system.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.08773 [cs.AI] |
| (or arXiv:2607.08773v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.08773 arXiv-issued DOI via DataCite |
Submission history
From: Merkouris Papamichail Mr. [view email]
[v1]
Thu, 9 Apr 2026 11:25:43 UTC (790 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Adversarial Social Epistemology for Assemblies of Humans and Large Language Models
The paper introduces Adversarial Social Epistemology (ASE) to analyze how agents manipulate trust in public communications, highlighting mechanisms that undermine the reliability of testimony and inference. It critiques existing frameworks like epistemic bubbles and misinformation diffusion, proposing a new language for understanding trust breaches and auditing inferential chains in densely interactive environments involving humans and large language models.