Research topic
AI systems
AI risk begins before the model endpoint.
26 publications
Threat modeling for data paths, orchestration identities, model services, and the cloud systems around AI workloads.
View every topicFrom the desk
26 publicationsQwen3.8-Flash-Next and GLM-5.3-Flash share a 3:1 long-context pattern
Both models replace most conventional attention layers with recurrent state and reserve sparse attention for periodic retrieval. Their differences lie in where they place capacity, how much neural computation they activate, and what their serving stacks must keep trustworthy.
Threat-model the system around the model
The model endpoint is one component. The consequential paths often run through retrieval stores, orchestration identities, evaluation data, and operator tools.