arXiv:2606. 23858v1 Announce Type: cross Abstract: A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify.
arXiv:2607. 08773v1 Announce Type: new Abstract: In this work we present a rigorous theoretical framework to a foundational problem of AI safety, namely adversarial robustness.
The paper introduces MACCHIATO, a training algorithm that builds a ReLU‑MLP from partial truth‑table data while simultaneously constructing an explicit Boolean circuit over AND, OR, and XOR gates that certifies the network’s computation. The method iteratively projects residuals onto low‑dimensional Boolean classes, compiles the resulting circuit into a ReLU‑MLP, and uses logic minimization and influence‑based variable selection to achieve a six‑layer network with provable truth‑table error bounds. Experiments on synthetic random‑junta tasks show that these certified networks outperform Adam‑trained MLPs in data‑sparse or projection‑aligned regimes and complete faster than flat ESPRESSO in certain settings.
arXiv:2603. 13334v4 Announce Type: replace Abstract: Lipschitz-based robustness certification bounds a network's sensitivity through concrete numerical computation rather than symbolic reasoning, and so scales efficiently.
PANDA is a scalable system that uses zero‑knowledge proofs to certify the robustness and fairness of neural networks without revealing their private parameters. Built on the CROWN robustness framework, PANDA introduces a novel algorithm for proving linear relaxation bounds on non‑linear activation layers, producing lightweight proofs. The system can generate proofs for networks with over 2.9 million parameters in just five minutes and verify them in ten seconds, scaling polynomially with network size and enabling verification of models four orders of magnitude larger than prior ZKP‑based approaches.
arXiv:2607. 14375v1 Announce Type: cross Abstract: We study exact verification of ReLU networks in an adversarial smoothed model.
The paper presents a complete characterization of when two deep ReLU networks realize the same function, showing that this occurs iff one can be transformed into the other using a set of axioms from many‑valued logic. It introduces a symbolic calculus that maps networks to substitution graphs, proves a completeness theorem linking equivalent formulas, and provides an algorithm to reconstruct networks from these graphs. The framework yields a new compositional normal form for MV logic that preserves the algebraic structure of deep ReLU networks.
arXiv:2608. 13118v1 Announce Type: new Abstract: Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS), given their increasing adoption of AI components.
arXiv:2603. 00408v2 Announce Type: replace-cross Abstract: We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations.
Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS), given their increasing adoption of AI components. Compared to simple trace properties (e.
arXiv:2606. 18918v1 Announce Type: new Abstract: This paper studies the computational complexity of verification problems for Binarized Neural Networks (BNNs), where activations (and sometimes weights) are binary.
The paper proves that training a binary quantized neural network (2-QNNT) is W[1]-hard when parameterized solely by the sum of input and output dimensions, α+ω. This hardness result holds even for zero training error on a specially constructed dataset where each input equals its target and the examples form a coordinate‑wise prefix chain. The proof reduces from DAG edge‑disjoint paths, employing a one‑flip routing equivalence that links activation transitions to vertex‑disjoint paths in the network.