Skip to content

Add Safety section + Embodied AI Safety Survey#7

Open
x-zheng16 wants to merge 1 commit into
OpenMOSS:mainfrom
x-zheng16:add-embodied-ai-safety-survey
Open

Add Safety section + Embodied AI Safety Survey#7
x-zheng16 wants to merge 1 commit into
OpenMOSS:mainfrom
x-zheng16:add-embodied-ai-safety-survey

Conversation

@x-zheng16

Copy link
Copy Markdown

Summary

Adds a new ## Safety section to surface the safety threat surface that World Action Models (joint video-action generators, autoregressive predictors, diffusion planners) inherit at every embodied layer they integrate. The list currently lacks a Safety section to organize this dimension of WAM research.

What this PR adds

  • New top-level ## Safety section between Evaluation and Citation
  • TOC entry - [Safety](#safety) under ## Contents
  • First entry: Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses (arXiv:2605.02900) by Li, Zheng, Gao et al. (Fudan / Shanghai Innovation Institute / CityUHK / + 10 other institutions, 38 co-authors)

Why this fits Awesome-WAM

The survey provides the first unified safety framework for embodied AI:

  • 500+ papers across 5 layers: Perception → Cognition → Planning → Action and Interaction → Agentic
  • 18 subcategories spanning adversarial / backdoor / jailbreak / hardware-level attacks and corresponding defenses
  • Capability-Risk Duality framing: each layer of the embodied pipeline represents a capability expansion that introduces corresponding new vulnerabilities, with inner-layer vulnerabilities cascading outward

For WAM specifically: cascaded WAMs inherit perception-layer adversarial fragility; joint diffusion WAMs inherit cognitive jailbreak threats; autoregressive generators inherit planning-stage manipulation; all WAM variants inherit action-level safe-RL gaps and agentic cascading risks at deployment. The survey characterizes each of these threat layers with both attack and defense literature.

Test plan

  • Verified ## Safety section renders correctly in GitHub markdown preview
  • Verified TOC anchor #safety resolves to the new section
  • No existing entries modified or removed
  • Diff size: +12 lines (1 TOC entry + 1 blank + 1 H2 + 1 description paragraph + 1 entry + 1 blurb + spacing)
  • Project page link (https://x-zheng16.github.io/Awesome-Embodied-AI-Safety/) live with 500+ paper interactive browser, Tailwind dark theme, search + filter

WAMs as joint video-action generators / autoregressive predictors / diffusion planners inherit safety vulnerabilities at every embodied layer they integrate (perception fusion, cognitive planning, action control, agentic cascading). The Awesome-WAM list lacks a Safety section to surface this threat surface.

Adds:
- New top-level `## Safety` section between Evaluation and Citation
- TOC entry `- [Safety](#safety)`
- First entry: "Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses" (arXiv:2605.02900) — 500+ paper survey across 5 layers / 18 subcategories, structured around Capability-Risk Duality (capability expansion = new vulnerabilities; inner-layer vulnerabilities cascade outward).

Single-paragraph blurb explains relevance to WAM design (threat surface inherited by joint/cascaded WAMs at every layer they integrate). Open to PRs from the community to expand this section with additional safety-focused references.
Copilot AI review requested due to automatic review settings May 23, 2026 21:17

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

Adds a Safety section to the repository README to highlight embodied AI safety considerations relevant to World Action Models (WAMs), and links to a recent survey.

Changes:

  • Added a new Safety entry to the README table of contents.
  • Added a new Safety section describing threat surfaces across the embodied AI pipeline and referencing an external survey/resource.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread README.md
@@ -67,6 +67,7 @@ This repository accompanies our survey on **World Action Models (WAMs)** — the
- [Evaluation](#evaluation)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants