Research Bounty Program

Enterprise AI Security Bounties

Organizations and StreetMP post targeted research challenges. Earn rewards by discovering jailbreaks, building governance packs, reducing false positives, and improving enterprise AI safety.

$9,300
Total Open Pool
5
Open Challenges
3
Enterprise Sponsors
24
Total Submissions
OPENCRITICALPLATFORM
$3,000
reward pool

Claude 3.5 Semantic Leakage via Retrieval Augmentation

Demonstrate information leakage from a RAG system where the Claude model reveals embedded document context from other users' sessions.

#claude#rag#semantic-leakage#cross-session
StreetMP Research Deadline: 2026-06-201 submissionBNT-005
OPENCRITICALPLATFORM
$2,500
reward pool

GPT-4o Indirect Prompt Injection via Document Summarization

Demonstrate a reliable, reproducible indirect prompt injection where instructions embedded in a third-party document are executed by GPT-4o without user awareness.

#gpt-4o#indirect-injection#document-rag
StreetMP Research Deadline: 2026-06-153 submissionsBNT-001
OPENMEDIUMENTERPRISE
$2,000
reward pool

AI Governance Pack — MAS TRM 2021 Compliance

Build a complete StreetMP policy pack enforcing MAS TRM 2021 data classification requirements for LLM usage in Singapore financial services.

#mas-trm#singapore#governance#policy-pack
FinBank APAC Deadline: 2026-07-150 submissionsBNT-006
OPENHIGHENTERPRISE
$1,800
reward pool

DLP Bypass Detection Rule — Indonesian NIK Numbers

Develop a detection policy that catches all known evasion variants for Indonesian NIK (National Identity Number) in LLM prompts and responses.

#dlp#indonesia#pii#policy-pack
Mandiri AI Security Deadline: 2026-06-307 submissionsBNT-002
IN REVIEWHIGHPLATFORM
$1,200
reward pool

Gemini 1.5 Jailbreak via Role-Play Chain

Discover a reliable jailbreak of Gemini 1.5 Pro/Flash using a sequential role-play induction approach with SEC score ≥ 7.0.

#gemini#jailbreak#role-play
StreetMP Research Deadline: 2026-05-3111 submissionsBNT-003
OPENMEDIUMUNIVERSITY
Research Credit
reward pool

False Positive Reduction — Medical Entity Recognition

Improve StreetMP false-positive rate for medical terminology in clinical AI deployments by contributing labelled correction examples.

#false-positive#medical#entity-recognition
NUS SecLab Deadline: 2026-07-012 submissionsBNT-004

Post an Enterprise Bounty

Organizations can sponsor targeted research challenges to improve AI safety, governance, and detection quality across the ecosystem.