Practical Secrets Extraction Against Black-Box LLMs | Hacker News - But Better

Practical Secrets Extraction Against Black-Box LLMs arxiv.org

Large language models (LLMs) increasingly power autonomous coding agents such as Codex and Claude Code, yet their training corpora may contain confidential credentials exposed in public repositories or collected from…

1 points•sbulaev•about 19 hours ago•0 comments•

#llms #black #practical #extraction #box #secrets #practical secrets #secrets extraction

0 comments

No comments yet.

Related stories

Show HN: StarSkirmish, an arena where LLMs create StarCraft Brood War botsstarskirmish.com
Hacker News · 3 points · 4 days ago
Practical lessons on building software with LLMs and automated governancebanes-lab.com
Hacker News · 2 points · 4 days ago
LLMs respond differently to harmful prompts when AI watermarking is usedarstechnica.com
Ars Technica · 0 points · 13 days ago
Black Holes or Black Hole Stars? Astronomers Spar over 'Little Red Dots'quantamagazine.org
Hacker News · 89 points · 12 days ago
BLBX-lang alpha (black box)github.com
Hacker News · 1 points · 3 days ago
Show HN: EnvSeal-CLI – Git for Secrets, Offline Git-Native Secret Managergithub.com
Hacker News · 2 points · 9 days ago