Fuzzers vs. AI: Comparing Fuzzilli and BigSleep on JavaScript Engines

Summary

Google Project Zero compared Fuzzilli, a generative JavaScript engine fuzzer, and BigSleep, an LLM-based bug finding system, on Chrome's V8 engine. Over six months BigSleep reported more vulnerabilities than Fuzzilli (45 versus 37), with a 25% overlap in specific bugs, and dedicated experiments estimated overlap near 60%. The authors conclude that fuzzing and LLM-based analysis are complementary and recommend vendors use both.

Related items

• InfoGoogle’s next Genie AI model generates more realistic experiencesSame vendor · The Verge (AI)
• HighCVE-2026-117560: ATXP Gemini CLI extension OS command injection in runAtxp() via MCP parametersSame vendor · NVD/CVE Database
• InfoFrom Wall Street to Silicon Valley, Anthropic IPO poised to have massive 'trickle-down effect'Same vendor · CNBC Technology
• InfoKevin Roose is AGI-pilled. Why aren’t you?Same vendor · The Verge (AI)
• InfoThe focus on AI safety disasters ignores everyday harmsSame vendor · MIT Technology Review