The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along with this comes the rising concern about its safety risks.

First, we formalize the problem definition.Weintroducetheconceptof"Idon'tknow (idk) responses" and in this context, honesty necessitates that an aligned LLM provides idk responses for unknown questions and correct responses for known questions.

To remedy this, we introduce temporal certificate sets, a general notion for capturing the intrinsic temporal understanding length associated with a broad range of video understanding tasks & datasets.

Datasets of complex cyber-physical systems (CPS) are difficult to build and large CPS datasets are not publicly available.