{"data":{"id":"ca5f46f9-769e-4be1-9ca9-727d45590b10","title":"Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks","summary":"Deep neural networks deployed across cloud storage, CI/CD pipelines (automated software deployment systems), and edge devices face parameter attacks, where attackers directly modify the model's internal weights and settings rather than just manipulating input data. Unlike previous defenses that require retraining or reduce accuracy significantly, this research presents ParDef, a defense system that protects model parameters by obscuring sensitive directions, adding error-correction capabilities through QC-LDPC quantization (a compression technique with built-in redundancy), and stabilizing predictions when attacks occur.","solution":"The source presents ParDef as the solution, which \"integrates keyed channel reparameterization, which obscures sensitive parameter directions, QC-LDPC quantization, which embeds redundancy and supports error correction, and adaptive robust inference, which stabilizes predictions under uncertainty.\" The paper demonstrates this defense \"consistently reduces attack success rates across different parameter attacks while maintaining high model performance and incurring only moderate deployment overhead.\"","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11609840","publishedAt":"2026-07-16T13:16:47.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_poisoning"],"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":"2026-07-16T13:16:47.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","availability"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.92,"researchCategory":"peer_reviewed","atlasIds":null}}