{
 "license": "CC-BY-4.0",
 "attribution": "Fide AI, Agentic Cyber Explorer",
 "url": "https://agentic-cyber-explorer.pages.dev/events/project-zero-bigsleep-fuzzilli-comparison-2026/",
 "asOf": "2026-10-30",
 "id": "project-zero-bigsleep-fuzzilli-comparison-2026",
 "date": "2026-10-27",
 "datePrecision": "day",
 "title": "Project Zero compares BigSleep and Fuzzilli on V8 and finds complementary vulnerability discovery",
 "lane": "defense",
 "kind": "eval-report",
 "summary": "Google Project Zero compares BigSleep and Fuzzilli on V8 over April–September 2026, reporting 45 versus 37 actionable vulnerabilities and about 25% observed overlap. A separate historical rediscovery experiment finds higher overlap; the report does not establish a controlled cost-efficiency ranking.",
 "whyItMatters": "It shows why observed production overlap and controlled rediscovery measure different aspects of AI-assisted vulnerability discovery.",
 "actors": [
  "google-project-zero",
  "google-deepmind"
 ],
 "topics": [
  "vulnerability-discovery",
  "autonomous-defense",
  "eval-validity",
  "capability-evaluation"
 ],
 "atlas": [
  "model",
  "eval-environment"
 ],
 "artifacts": [
  "big-sleep",
  "fuzzilli",
  "gemini"
 ],
 "sources": [
  {
   "url": "https://projectzero.google/2026/10/fuzzing-v-AI.html",
   "publisher": "Google Project Zero",
   "title": "Fuzzers vs. AI: Comparing Fuzzilli and BigSleep on JavaScript Engines",
   "date": "2026-10-27",
   "type": "primary",
   "accessed": "2026-10-30"
  }
 ],
 "keyFacts": [
  {
   "fact": "Production counts filter out duplicates and unactionable reports and require fixes. The 25% overlap is 20 of 81 actionable vulnerability reports after the article’s deduplication process.",
   "locator": "Part 1: Production Statistics; Bugtracker Overlap"
  },
  {
   "fact": "BigSleep rediscovered about 62% of 112 selected historical bugs across 25 attempts per introducing commit, using Gemini 3.6 Flash. Selection excluded bugs incompatible with the evaluation build or allowed flags.",
   "locator": "Overlap Experiment"
  },
  {
   "fact": "Both systems run in production on newly added code with different scheduling. Cost optimization, scheduling and target selection limit generalization beyond this V8 comparison.",
   "locator": "Introduction; Part 1; Conclusion"
  }
 ],
 "significance": 4,
 "fideQuestions": [
  "FID-075",
  "FID-076"
 ],
 "methods": [
  "ai-vulnerability-discovery"
 ],
 "review": "assistant-drafted",
 "addedOn": "2026-10-30",
 "revisions": []
}