Safety and alignment

Google expands vulnerability rewards to generative AI attacks

Google expanded its Vulnerability Reward Program to pay researchers for qualifying generative-AI attack scenarios and added open-source security support for AI supply chains.

0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

CURRENT ASSESSMENT · REVISION 1
AWAY FROM DOOM40confidence 96/100

Why it moved the index

A mature paid disclosure program began incentivizing external discovery of model manipulation and AI supply-chain vulnerabilities, strengthening practical monitoring and remediation.

AUDIT TRAIL

Assessment history

  1. R1
    Away 40 · confidence 96

    New October 2023 operational generative-AI security incentive.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Google expands vulnerability rewards to generative AI attacks.
  1. DoomBench assesses “Google expands vulnerability rewards to generative AI attacks” as evidence moving away from doom, with magnitude 40 and confidence 96 out of 100 in the safety and alignment category.

  2. The DoomBench assessment of “Google expands vulnerability rewards to generative AI attacks” is based on reporting from Google and records the editorial rationale, source quality, attribution, and revision history.

  3. DoomBench summarizes “Google expands vulnerability rewards to generative AI attacks” as follows: Google expanded its Vulnerability Reward Program to pay researchers for qualifying generative-AI attack scenarios and added open-source...

    https://www.doombench.com/news/google-expands-vulnerability-rewards-to-generative-ai-attacks-2023-10-26