BadWAM: When World-Action Models Dream Right but Act Wrong
Ranking
Overall
77
Content
80
Popularity
70
Observed public metrics from 1 member.
Merged summary
TL;DR - BadWAM introduces a class of adversarial attacks against world-action models (WAMs) for embodied robot control, showing that the assumed safety benefit of coupling action generation with future-world prediction is fragile: tiny visual perturbations can desynchronize what a robot imagines from what it actually does.
- Defines "World-Action Drift Attacks" along two axes—attack strength and stealthiness—unifying overt and covert failure modes.
- An action-only attack maximizes disruption, cutting task success from 96.5% to 43.1% under closed-loop execution.
- An imagination-preserving attack stays stealthy: it induces harmful action shifts while keeping the predicted future close to the clean imagination, so the model "dreams right but acts wrong."
- Shows moderate future-preserving regularization retains strong attack performance while minimizing imagination drift, exposing a WAM-specific vulnerability that undermines "check action against imagined future" safety claims.
Sources (1)
BadWAM: When World-Action Models Dream Right but Act Wrong
Public signals
Hugging Face upvotes 54
TL;DR - BadWAM introduces a class of adversarial attacks against world-action models (WAMs) for embodied robot control, showing that the assumed safety benefit of coupling action generation with future-world prediction is fragile: tiny visual perturbations can desynchronize what a robot imagines from what it actually does.
- Defines "World-Action Drift Attacks" along two axes—attack strength and stealthiness—unifying overt and covert failure modes.
- An action-only attack maximizes disruption, cutting task success from 96.5% to 43.1% under closed-loop execution.
- An imagination-preserving attack stays stealthy: it induces harmful action shifts while keeping the predicted future close to the clean imagination, so the model "dreams right but acts wrong."
- Shows moderate future-preserving regularization retains strong attack performance while minimizing imagination drift, exposing a WAM-specific vulnerability that undermines "check action against imagined future" safety claims.