Google Launches AI Bug Bounty Program with Rewards Up to $30,000
By
Elissa Welle
Toasted to a respectable shade. No regrets, no crumbs left.
Summary
Google has launched a new bug bounty program specifically targeting AI-related vulnerabilities in its products. The program offers rewards up to $30,000 for finding security flaws in AI systems, including examples like prompt injection attacks that could cause Google Home to unlock doors or data exfiltration attacks that summarize and steal email content. The program clarifies what constitutes an AI bug, focusing on issues where large language models or generative AI systems are exploited to cause harm or security breaches.
Key quotes
· 5 pulledGoogle launched a new reward program dedicated specifically to finding bugs in AI products
Google's list of qualifying bugs includes examples of the kind of rogue actions it's looking for
indirectly injecting an AI prompt that causes Google Home to unlock a door
data exfiltration prompt injection that summarizes all of someone's email and sends the summary to the attacker's own account
The new program clarifies what constitutes an AI bug, breaking them down as issues that use a large language model or a generative AI system to cause harm
You might also wanna read
OpenAI launches GPT-5.5 Bio Bug Bounty program for red-teaming AI biosecurity safeguards
OpenAI is launching a Bio Bug Bounty program for GPT-5.5, inviting researchers with expertise in AI red teaming, security, or biosecurity to
openai.com·1mo ago
Google Confirms First Known Case of Hackers Using AI to Discover Software Vulnerability
Google's security researchers have identified the first known instance of criminal hackers using artificial intelligence to discover a previ
nytimes.com·20d ago
Security Vulnerability: Google's Antigravity AI Susceptible to Indirect Prompt Injection Attacks
The article describes a security vulnerability where Google's Antigravity AI system (likely referring to Gemini) can be manipulated through
promptarmor.com·6mo ago
Google reports first evidence of hackers using AI to develop zero-day security exploit
Google has reported evidence of hackers using AI to develop a zero-day security vulnerability, marking the first time the company has observ
politico.com·14h ago
HackMyClaw: $1000 Bounty Challenge for AI Prompt Injection Testing
The article announces a $1000 bounty challenge called 'HackMyClaw' where participants attempt to hack an AI assistant named Fiu (an OpenClaw
hackmyclaw.com·3mo ago
AI-Generated Vulnerability Reports Overwhelm Bug Bounty Platforms and Security Teams
A cybersecurity expert with nearly a decade of experience in bug bounty programs analyzes the growing problem of AI-generated vulnerability
devansh.bearblog.dev·6mo ago