Security News > 2023 > October > Google expands bug bounty program to cover AI-related threats
Google has expanded its bug bounty program, aka Vulnerability Rewards Program, to cover threats that could arise from Google's generative AI systems.
Following the voluntary commitment to the Biden-Harris Administration to develop responsible AI and manage its risks, Google has added AI-related risks to its bug bounty program, which gives recognition and compensation to ethical hackers who successfully find and disclose vulnerabilities in Google's systems.
Training data extraction - An attacker gains unauthorized access to and extracts the training data used to develop ML models, potentially compromising the integrity and reliability of those model.
Manipulating models - Changing the behavior of the model to trigger pre-defined adversarial behaviors.
Model theft / exfiltration - Unauthorized access and exfiltration of details about Google's models, such as its architecture or weights.
Microsoft has recently announced its own AI bug bounty program, rewarding bug hunters with up to $15,000 to find vulnerabilities in the company's AI-powered Bing experience.
News URL
https://www.helpnetsecurity.com/2023/10/30/google-ai-bug-bounty/
Related news
- Arc browser launches bug bounty program after fixing RCE bug (source)
- Eliminating AI Deepfake Threats: Is Your Identity Security AI-Proof? (source)
- How agentic AI handles the speed and volume of modern threats (source)
- Google’s AI Tool Big Sleep Finds Zero-Day Vulnerability in SQLite Database Engine (source)
- Google claims Big Sleep 'first' AI to spot freshly committed security bug that fuzzing missed (source)
- AI-Assisted Attacks Top Cyber Threat For Third Consecutive Quarter, Gartner Finds (source)
- How AI will shape the next generation of cyber threats (source)
- Why AI-enhanced threats and legal uncertainty are top of mind for risk executives (source)
- Google says “Enhanced protection” feature in Chrome now uses AI (source)
- New Google Pixel AI feature analyzes phone conversations for scams (source)