Interval Certifications for Multilayered Perceptrons via Lattice Traversal

• URL: http://arxiv.org/abs/2607.08773v1
• Date: Thu, 09 Apr 2026 11:25:43 GMT
• Title: Interval Certifications for Multilayered Perceptrons via Lattice Traversal
• Abstract summary: We show that the adversarial robustness problem can be reduced to a lattice problem.<n>We develop formal verifiers, sound maximality and complete minimality are guaranteed.<n>We present an empirical evaluation, using the novel ParallelepipedoNN system.
• Score: 10.268619734362547
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• PureSuperQMA(exp) = BellPureSymQMA(poly) = QMA via Dimension-Free Bosonic Argmax [36.23068106699028]
  Pure-state consistency problems naturally lead to quantum proof systems in which a single witness must satisfy many acceptance constraints.<n>$mathsfBellPureSymQMA(textpoly)$ is a related model that requires the prover to give the verifierly many copies of a pure state.<n>We show that exact $k$-local pure-state consistency is $mathsfQMA$-complete for every fixed $kge2$, and so are the corresponding exact bosonic and fermionic pure $N$-representability problems.
  arXiv  Detail & Related papers  (2026-09-10T17:37:22Z)
• Multi-Prover Interactive Proof Systems with Leakage [1.0960289997471082]
  We introduce two techniques to approach the setting where communication between provers is allowed but bounded.<n>We show that for any $p$, we can construct two-prover one-round $mathsfMIP$ and $mathsfMIPast$ protocols for $mathsfNEXP$ and $mathsfRE$.
  arXiv  Detail & Related papers  (2026-05-11T01:58:44Z)
• SoS Certificates for Sparse Singular Values and Their Applications: Robust Statistics, Subspace Distortion, and More [37.208622097149714]
  We give a new family of upper-time algorithms which can certify bounds on the maximum of $|M u|$.<n>Our certification algorithm makes essential use of the Sum-of-Squares hierarchy.
  arXiv  Detail & Related papers  (2024-12-30T18:59:46Z)
• Learning Networks from Wide-Sense Stationary Stochastic Processes [7.59499154221528]
  A key inference problem here is to learn edge connectivity from node outputs (potentials)<n>We use a Whittle's maximum likelihood estimator (MLE) to learn the support of $Last$ from temporally correlated samples.<n>We show that the MLE problem is strictly convex, admitting a unique solution.
  arXiv  Detail & Related papers  (2024-12-04T23:14:00Z)
• Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP [58.13930707612128]
  This work considers the sample complexity of obtaining an $varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP) We prove an upper bound of $widetilde O(H varepsilon-3 ln frac1delta)$ samples per state-action pair, where $H := sp(h*)$ is the span of bias of any optimal policy, $varepsilon$ is the accuracy and $delta$ is the failure probability.
  arXiv  Detail & Related papers  (2022-12-01T15:57:58Z)
• Multimeasurement Generative Models [7.502947376736449]
  We map the problem of sampling from an unknown distribution with density $p_X$ in $mathbbRd$ to the problem of learning and sampling $p_mathbfY$ in $mathbbRMd$ obtained by convolving $p_X$ with a fixed factorial kernel.
  arXiv  Detail & Related papers  (2021-12-18T02:11:36Z)
• Under-bagging Nearest Neighbors for Imbalanced Classification [63.026765294759876]
  We propose an ensemble learning algorithm called textitunder-bagging $k$-NN (textitunder-bagging $k$-NN) for imbalanced classification problems.
  arXiv  Detail & Related papers  (2021-09-01T14:10:38Z)
• Provable Robustness of Adversarial Training for Learning Halfspaces with Noise [95.84614821570283]
  We analyze the properties of adversarial learning adversarially robust halfspaces in the presence of label noise. To the best of our knowledge, this is the first work to show that adversarial training prov yields classifiers in noise.
  arXiv  Detail & Related papers  (2021-04-19T16:35:38Z)
• Hardness of Learning Halfspaces with Massart Noise [56.98280399449707]
  We study the complexity of PAC learning halfspaces in the presence of Massart (bounded) noise. We show that there an exponential gap between the information-theoretically optimal error and the best error that can be achieved by a SQ algorithm.
  arXiv  Detail & Related papers  (2020-12-17T16:43:11Z)
• Learning Halfspaces with Tsybakov Noise [50.659479930171585]
  We study the learnability of halfspaces in the presence of Tsybakov noise. We give an algorithm that achieves misclassification error $epsilon$ with respect to the true halfspace.
  arXiv  Detail & Related papers  (2020-06-11T14:25:02Z)
• Robustly Learning any Clusterable Mixture of Gaussians [55.41573600814391]
  We study the efficient learnability of high-dimensional Gaussian mixtures in the adversarial-robust setting. We provide an algorithm that learns the components of an $epsilon$-corrupted $k$-mixture within information theoretically near-optimal error proofs of $tildeO(epsilon)$. Our main technical contribution is a new robust identifiability proof clusters from a Gaussian mixture, which can be captured by the constant-degree Sum of Squares proof system.
  arXiv  Detail & Related papers  (2020-05-13T16:44:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.