Cert-SSBD: Certified Backdoor Defense With Sample-Specific Smoothing Noises

Summary

Cert-SSBD is a certified backdoor defense for deep neural networks that replaces fixed randomized smoothing noise with sample-specific noise magnitudes, optimized per sample via stochastic gradient ascent. The method retrains several smoothed models on multiple poisoned training sets and aggregates their predictions, and it introduces a storage-update-based certification method to handle the varying noise. The authors report effectiveness on multiple benchmark datasets and provide code at https://github.com/NcepuQiaoTing/Cert-SSBD.

Related items

• MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
• MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
• HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
• InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
• MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online