Towards Safe World Models: Risks, Defenses, and Evaluation

World models support planning, control, learning from imagined experience, and model-mediated evaluation by predicting action-conditioned consequences. Their safety cannot be inferred from predictive accuracy alone: errors in observations, state and memory, dynamics, evaluation, execution, or...

How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection

Provenance-based intrusion detection systems PIDS frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets tha...

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors, prompts, or feedbac...

From SFT to RL: Demystifying the Post-Training Pipeline for LLM-Based Vulnerability Detection

The integration of LLMs into vulnerability detection VD has shifted the field toward interpretable and context-aware analysis. While post-training methods have shown promise in general coding tasks, their systematic application to VD remains underexplored. In this paper, we present the first...