{"data":{"id":"4ed57429-6406-4fa0-8657-e9eedef81fab","title":"CaDe: Adaptive Sparse Causal Decoupling for Adversarially Robust Object Detection via Hierarchical Stability Constraints","summary":"Object detectors used in safety-critical systems are vulnerable to physical adversarial patch attacks (images or objects designed to fool AI vision systems), which work by disrupting how information flows through layers of the neural network rather than simply corrupting visual features. The paper proposes CaDe, a defense method that uses hierarchical stability constraints and adaptive sparse causal decoupling to stop adversarial perturbations from propagating through the network layers, improving detection accuracy by 5-6% against these attacks while maintaining real-time performance.","solution":"The source proposes CaDe as the defense mechanism, which \"mitigates the hierarchical propagation of residual perturbations through hierarchical stability constraints and adaptive sparse causal decoupling strategies, fundamentally enhancing the model's robustness.\" Experimental results show CaDe achieves \"improvements of 6.19% and 5.53% in mean Average Precision (mAP) compared with the best baseline method\" against Hiding Attack and Appearing Attack, while maintaining \"minimal additional computational overhead\" and only a 0.14% mAP decrease on benign (normal, unattacked) samples.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11614563","publishedAt":"2026-07-20T13:17:07.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-07-20T13:17:07.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.85,"researchCategory":"peer_reviewed","atlasIds":null}}