arXiv (All)
open access
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certification on such inputs within a patch bound can verify their label benignity and should retain high prediction accuracy. However, existing smoothing-based and masking-based recover
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning#986014
- Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures#1217129
- Adversarial Robustness by Combining Prototype Models with Lipschitz Training#965638
- Evaluating the adversarial robustness of detection transformers#130595
- Towards One-for-All Robustness Across a Continuum of Threat Levels#924322
Record · ID 1247544
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive