Pith. sign in

REVIEW 1 cited by

PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.03638 v3 pith:MBWS6G2U submitted 2021-03-05 cs.AI cs.LG

classification cs.AIcs.LG
keywords preciseprimaconvexnetworkneuralverificationactivationalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Formal verification of neural networks is critical for their safe adoption in real-world applications. However, designing a precise and scalable verifier which can handle different activation functions, realistic network architectures and relevant specifications remains an open and difficult challenge. In this paper, we take a major step forward in addressing this challenge and present a new verification framework, called PRIMA. PRIMA is both (i) general: it handles any non-linear activation function, and (ii) precise: it computes precise convex abstractions involving multiple neurons via novel convex hull approximation algorithms that leverage concepts from computational geometry. The algorithms have polynomial complexity, yield fewer constraints, and minimize precision loss. We evaluate the effectiveness of PRIMA on a variety of challenging tasks from prior work. Our results show that PRIMA is significantly more precise than the state-of-the-art, verifying robustness to input perturbations for up to 20%, 30%, and 34% more images than existing work on ReLU-, Sigmoid-, and Tanh-based networks, respectively. Further, PRIMA enables, for the first time, the precise verification of a realistic neural network for autonomous driving within a few minutes.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Efficient Neural Network Verification via Order Leading Exploration of Branch-and-Bound Trees

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Reordering branch-and-bound sub-problems by a counterexample-potentiality heuristic accelerates neural network verification, especially for falsified instances.

Pith tools