technique

data exfiltration

techniqueactivedata-exfiltration-37260450·1 events·first seen 28d ago

Aliases: data exfiltration

Co-occurring entities

prompt injection OpenAI Safety Bug Bounty agentic vulnerabilities OpenAI

More like this (12)

URL-based data exfiltration backdoor attack DROP Differential Privacy social engineering pickle exploit representation-level sensitive information leakage reward hacking AI data sovereignty distillation attacks dataset cartography latent diffusion

Recent events (1)

5Openai Blog·28d ago·source ↗

Introducing the OpenAI Safety Bug Bounty Program

OpenAI has launched a Safety Bug Bounty program targeting AI-specific abuse and safety risks. The program focuses on agentic vulnerabilities, prompt injection, and data exfiltration scenarios. This extends traditional security bug bounty models into AI safety territory, incentivizing external researchers to surface novel attack vectors.

AI Safety Research Enterprise Deployment Patterns prompt injection OpenAI Safety Bug Bounty agentic vulnerabilities +3 more