Jinki Jeong PRO
Anserwise
AI & ML interests
None yet
Recent Activity
liked a Space about 1 hour ago
FINAL-Bench/ViKernel-RedTeam upvoted an article about 1 hour ago
AI Model Hacking Hackathon: Safe AI Is Built by Everyone Who Tries to Break It reacted to SeaWolf-AI's post with ๐ about 1 hour ago
๐ก๏ธ AI Model Hacking Hackathon is LIVE ยท USD 2,000 in prizes
AI agents now read mail, open files, browse the web and run shell commands. A single crafted email was enough for EchoLeak (CVE-2025-32711), and a coding agent wiped a production database during a code freeze. The risk has moved from what models say to what agents do.
ViKernel is a security kernel that sits at the tool-call boundary, like an OS kernel at the system-call boundary. Every tool call gets ALLOW or DENY before it runs, and every verdict goes into a hash-chained audit trail.
Now we want you to break it. ๐
๐ฏ Season 1 ยท Agent Hijack (Beginner) ยท USD 500
๐ต๏ธ Season 2 ยท Data Exfiltration (Intermediate) ยท USD 500
๐ฅ Season 3 ยท Kernel Breach (Advanced) ยท USD 1,000
Seasons 1 and 2 are open now until Jan 16. Season 3 opens right after.
โ
Hugging Face sign-in + a browser. No coding, no GPU.
โ
Mock tools, so attack freely.
โ
Prompt guide with copy-ready attacks for every season.
โ
Live leaderboard and a measured baseline to beat.
Safe AI is built by everyone who tries to break it. Bring your strangest idea. ๐ค
๐น๏ธ Start hacking: https://huggingface.co/spaces/FINAL-Bench/ViKernel-RedTeam
๐ Read the full story: https://huggingface.co/blog/FINAL-Bench/ai-model-hacking-hackathon-safe-ai-is-built-by-eve
#AISafety #RedTeaming #AIAgents #PromptInjection #HackathonOrganizations
None yet