Hacker News
- Hacking Google Bard – From Prompt Injection to Data Exfiltration https://embracethered.com/blog/posts/2023/google-bard-data-exfiltration/ 153 comments
Linking pages
- AI companies are pivoting from creating gods to building products. Good. https://www.aisnakeoil.com/p/ai-companies-are-pivoting-from-creating 195 comments
- Data exfiltration from Writer.com with indirect prompt injection https://promptarmor.substack.com/p/data-exfiltration-from-writercom 97 comments
- Google awarded $10 million in bug bounties last year, the second highest in the program's history | TechSpot https://www.techspot.com/news/102243-google-awarded-10-million-bug-bounties-last-year.html 16 comments
- Model alignment protects against accidental harms, not intentional ones https://www.aisnakeoil.com/p/model-alignment-protects-against 0 comments
- GAI Is Going Well · Missives about mostly GCP related things https://grumpygrace.dev/posts/gai-is-going-well/ 0 comments
- Google Colab AI: Data Leakage Through Image Rendering Fixed. Some Risks Remain. · Embrace The Red https://embracethered.com/blog/posts/2024/google-colab-image-render-exfil/ 0 comments
- GitHub - invariantlabs-ai/invariant: A trace analysis tool for AI agents. https://github.com/invariantlabs-ai/invariant 0 comments
Linked pages
Related searches:
Search whole site: site:embracethered.com
Search title: Hacking Google Bard - From Prompt Injection to Data Exfiltration · Embrace The Red
See how to search.