Papers › A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks

A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks

23 Feb 2019NeurIPS 2019 12arXiv:1902.08722archive 2025-07-28

Hadi Salman, Greg Yang, huan zhang, Cho-Jui Hsieh, Pengchuan Zhang

Verification of neural networks enables us to gauge their robustness against adversarial attacks. Verification algorithms fall into two categories: exact verifiers that run in exponential time and relaxed verifiers that are efficient but incomplete. In this paper, we unify all existing LP-relaxed verifiers, to the best of our knowledge, under a general convex relaxation framework. This framework works for neural networks with diverse architectures and nonlinearities and covers both primal and dual views of robustness verification. We further prove strong duality between the primal and dual problems under very mild conditions. Next, we perform large-scale experiments, amounting to more than 22 CPU-years, to obtain exact solution to the convex-relaxed problem that is optimal within our framework for ReLU networks. We find the exact solution does not significantly improve upon the gap between PGD and existing relaxed verifiers for various networks trained normally or robustly on MNIST and CIFAR datasets. Our results suggest there is an inherent barrier to tight verification for the large class of methods captured by our framework. We discuss possible causes of this barrier and potential future directions for bypassing it. Our code and trained models are available at http://github.com/Hadisalman/robust-verify-benchmark .

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Hadisalman/robust-verify-benchmark officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Provable defenses against adversarial examples via the convex outer adversarial polytope (arXiv:1711.00851; that paper's own run record: 21 ran (of which 15 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 1 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 23 unverified); nothing checks that they implement this paper's method. report
Verified-Intelligence/alpha-beta-CROWN_vnncomp2024 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fast and Complete: Enabling Complete Neural Network Verification with Rapid and... (arXiv:2011.13824; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified), Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete... (arXiv:2103.06624; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), General Cutting Planes for Bound-Propagation-Based Neural Network Verification (arXiv:2208.05740; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
avrahamraviv/formal-verification-of-object-detection mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to General Cutting Planes for Bound-Propagation-Based Neural Network Verification (arXiv:2208.05740; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
huanzhang12/alpha-beta-CROWN mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Network Verification with Branch-and-Bound for General Nonlinearities (arXiv:2405.21063; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
verified-intelligence/alpha-beta-crown mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ReLU

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections