Pith. sign in

REVIEW 1 cited by

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

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 2002.12920 v3 pith:NHCJ5R3C submitted 2020-02-28 cs.LG stat.ML

classification cs.LGstat.ML
keywords lirpacertifieddefenseperturbationanalysisframeworknetworknetworks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes provable linear bounds of output neurons given a certain amount of input perturbation, has become a core component in robustness verification and certified defense. The majority of LiRPA-based methods focus on simple feed-forward networks and need particular manual derivations and implementations when extended to other architectures. In this paper, we develop an automatic framework to enable perturbation analysis on any neural network structures, by generalizing existing LiRPA algorithms such as CROWN to operate on general computational graphs. The flexibility, differentiability and ease of use of our framework allow us to obtain state-of-the-art results on LiRPA based certified defense on fairly complicated networks like DenseNet, ResNeXt and Transformer that are not supported by prior works. Our framework also enables loss fusion, a technique that significantly reduces the computational complexity of LiRPA for certified defense. For the first time, we demonstrate LiRPA based certified defense on Tiny ImageNet and Downscaled ImageNet where previous approaches cannot scale to due to the relatively large number of classes. Our work also yields an open-source library for the community to apply LiRPA to areas beyond certified defense without much LiRPA expertise, e.g., we create a neural network with a probably flat optimization landscape by applying LiRPA to network parameters. Our opensource library is available at https://github.com/KaidiXu/auto_LiRPA.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 92 citations worldwide. Full citation record

  1. A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verification

    cs.AI 2025-02 conditional novelty 6.0 of 10

    Probabilistic NeSy robustness can be verified approximately by compiling neural and symbolic parts into one arithmetic graph and running interval bound propagation, with an NPPP-completeness result for the exact version.

Pith tools