2 papers
cs.CL2026
Seeing Through the Forgery Is Not Enough: Regressive Sycophancy under Fabricated Evidence in Medical Vision-Language Models
Sadif Ahmed, Soumya Swagata Biswas, Rifat Shahriyar +1
A medical vision-language model may analyze a given CT scan and correctly detect both kidneys in view. Continuing this conversation, if a user provides a prescription with an oppos…
cs.CR2026
Embedding Asymmetry as Attack Signal: Detecting and Defending Active Label Inference in Vertical Federated Learning
Soumya Swagata Biswas, Muhammad Abdullah Adnan
Vertical federated learning lets organizations train a shared model over features they hold separately, while one party keeps the labels private. The active label inference attack…