Pith. sign in

REVIEW 4 cited by

TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

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 1807.10875 v1 pith:TFKEL47A submitted 2018-07-28 stat.ML cs.LG

classification stat.MLcs.LG
keywords networksneuralcoveragecoverage-guidederrorsfuzzinginputsmetric
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Machine learning models are notoriously difficult to interpret and debug. This is particularly true of neural networks. In this work, we introduce automated software testing techniques for neural networks that are well-suited to discovering errors which occur only for rare inputs. Specifically, we develop coverage-guided fuzzing (CGF) methods for neural networks. In CGF, random mutations of inputs to a neural network are guided by a coverage metric toward the goal of satisfying user-specified constraints. We describe how fast approximate nearest neighbor algorithms can provide this coverage metric. We then discuss the application of CGF to the following goals: finding numerical errors in trained neural networks, generating disagreements between neural networks and quantized versions of those networks, and surfacing undesirable behavior in character level language models. Finally, we release an open source library called TensorFuzz that implements the described techniques.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Toward Reproducible Cross-Backend Compatibility for Deep Learning: A Configuration-First Framework with Three-Tier Verification

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A configuration-first, three-tier verification framework quantifies cross-backend drift in deep learning, reporting a 72% pass rate across 672 checks and offering deterministic adapters as mitigations.

  2. DeepEvolution: A Search-Based Testing Approach for Deep Neural Networks

    cs.LG 2019-09 conditional novelty 5.0 of 10

    DeepEvolution uses population-based metaheuristics to evolve image transformations guided by neuron coverage, increasing coverage and detecting more DNN defects than TensorFuzz in small experiments.

  3. Detecting Deep Neural Network Defects with Data Flow Analysis

    cs.LG 2019-09 reject novelty 5.0 of 10

    DeepMorph claims to locate the root cause of poor deep network performance by comparing internal layer outputs, called data flow footprints, against patterns learned from training data.

  4. Data Sanity Check for Deep Learning Systems via Learnt Assertions

    cs.LG 2019-09 conditional novelty 3.0 of 10

    SaneDL detects invalid inputs by using autoencoder reconstruction losses of intermediate activations as assertions, reporting high detection rates on two image dataset pairs.

Pith tools