Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners
Everyday objects, whether placed by an adversary or introduced by ordinary rearrangement of the environment, are thus sufficient to overturn a refusal, and susceptibility to safety bypass is called a property of the task, which it is shown that it can be predicted before the target is ever queried.
Leon Lin, Mikhail Kuznetsov, Muslum Ozgur Ozmen et al.
· 0 citations