Author name: Manoj Parmar

Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attacks

Manoj Parmar / April 21, 2026

arXiv:2604.16424v1 Announce Type: cross
Abstract: State-Space Models (SSMs) — structured SSMs (S4, S4D, DSS, S5), selective SSMs (Mamba, Mamba-2), and hybrid architectures (Jamba) — are deployed in safety-critical long-context applications: genomic …

cs.AI, cs.CR, cs.LG, cs.RO

Safety, Security, and Cognitive Risks in World Models

Manoj Parmar / April 8, 2026

arXiv:2604.01346v2 Announce Type: replace-cross
Abstract: World models – learned internal simulators of environment dynamics – are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic AI. By predict…

cs.AI, cs.CR, cs.LG, cs.RO

Safety, Security, and Cognitive Risks in World Models

Manoj Parmar / April 3, 2026

arXiv:2604.01346v1 Announce Type: cross
Abstract: World models — learned internal simulators of environment dynamics — are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic AI. Yet this predict…