AI Paper Atlas

Research map / Large language models / Agents, code and math

DeepFuzz: Automatic Generation of Syntax Valid C Programs for Fuzz Testing

AAAI 2019 · Large language models › Agents, code and math · approach: Execution-based code verification · 94 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
DeepFuzz generated tests vs CsmithGCC test suite augmentation · GCC-5line coverage: +0.45% vs +7.14%Helped
DeepFuzz generated tests vs CsmithLLVM test suite augmentation · Clang-3branch coverage: +0.24% vs +7.57%Helped
sampling next char instead of greedy (NoSample) (ablation)DeepFuzz · GCC test suite seedspass rateHurt
sampling (Sample) instead of greedy (ablation)DeepFuzz G2 · GCC-5line coverage improvement: 5.41% -> 7.76%Helped
insert at multiple locations (G2) instead of one location (G1) (ablation)DeepFuzz SampleSpace · GCC-5function coverage improvement: 0.17% -> 2.44%Helped
replace lines (G3) instead of insert (G1) (ablation)DeepFuzz NoSample · GCC test suite seedspass rate: 82.63 -> 73.23Hurt
train beyond 30 epochs (ablation)DeepFuzz · GCC test suite seedspass rateHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy