Trustworthy medical imaging: Conformal prediction with adversarial guarantees

Summary

Researchers present a framework that combines conformal prediction methods with adversarial robustness for deep learning models in medical imaging. The approach is tested on the MedMNIST datasets (PathMNIST, OrganAMNIST and TissueMNIST) against various combinatorial attacks within a predefined threat model, and the authors report that it achieves valid coverage under this framework. The paper was published in Computer Vision and Image Understanding on 2026-10-06.

Related items

• InfoDoes Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive EncodersSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoBRANCH: Bypassing Multi-Scanner AI GuardrailsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoDetecting Adversarial Images through Response Profiles of Vision-Language ModelsSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoGraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural NetworksSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoVCR-Bench: A Modular Open-Source Benchmark for Video Classification RobustnessSimilar attack · Arxiv (cs.RO + cs.CV security)