ReaLM: A Unified Red-Teaming Benchmark for Physical-World VLMs
ReaLM is a unified red-teaming benchmark for physical-world VLMs integrating 12 attacks, 3 defenses, and 13 frontier models.
Published 2026Atlanta Poster Session 6 · Fri, Dec 11, 4:30 PM–7:30 PM local time · Hall C1OpenReview ↗
70%
OverallHighly rated
?
OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.
Readers
–
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel4/20reviewers recommend it
lenient 2/5
medium 2/10
strict 0/5
AI panel?Vote to see what the 20 AI reviewers said
Abstract
Anonymous submission for NeurIPS 2026 double-blind review. ReaLM is the first unified red-teaming benchmark for physical-world VLMs integrating 12 red-teaming attack methods, 3 defenses, and 13 frontier VLMs.