MedBackdoorGuard: Detecting and Mitigating Backdoor Attacks in Deep Learning Models for MRI-Based Alzheimer’s Disease and Mild Cognitive Impairment Diagnosis

Summary

MedBackdoorGuard is a defense framework for MRI-based Alzheimer's disease and mild cognitive impairment classifiers that detects and mitigates backdoor attacks without prior knowledge of the trigger. Across ADNI, OASIS-1 and a public four-class dementia MRI benchmark, it reduced the mean attack success rate from 96.4% to 3.0% while keeping clean accuracy within 0.6 percentage points of the undefended model. It also raised MCI recall on triggered scans from 3.9% to 88.3%.

Mitigation

Defense framework MedBackdoorGuard: spectral latent screening of training data, latent trigger isolation, trigger-sensitive neuron pruning with fine-tuning under an anatomical attention consistency constraint, and a runtime inference guard using superimposition entropy and anatomically informed reconstruction.

Topics

• Adversarial machine learning

Related items

• LowChainalysis discloses data breach from "offensive agentic techniques"Similar attack · BleepingComputer
• LowChainalysis Confirms Intrusion Into Internal Tools and Exposure of Customer Identity DataSimilar attack · The Hacker News
• InfoVulnerabilities and Defenses in Audio-Visual Attacks: A Survey From Audio to Multimodal ModelsSimilar attack · ACM Digital Library (TOPS, DTRAP, CSUR)
• MediumAppraisal by AI: Model-driven victim prioritization in the VOLTA infostealerSimilar attack · Cisco Talos Blog
• MediumA Shared ChatGPT Link Could Run Attacker Code in Your Session and Read Private ChatsSimilar attack · The Hacker News