Newest papers

Signature Knowledge Shielding: Protecting Antivirus Detection Knowledge through Robust Embedding Matching

Jieshuai Yang, Zhi Wang, Yan Jia, Zhenhua Wu, Jianfei Tang, Chenbin Su, Jingwei Ye, Jianwen Tian, Wanpeng Li · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26207 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

As assinaturas antivírus (AV) eficientes codificam valiosos conhecimentos de detecção acumulados através da análise de provas especializada, mas as consultas de caixa preta repetidas podem expor esse conhecimento para reutilização não autorizada e evasão direcionada. Proponemos o Escudo de Conhecimento de Assinatura (SKS), um paradigma de design que protege as regras AV existentes, chamadas de Assinaturas Protegidas (PS), através da análise auxiliar de assinaturas de escudo (SS). O SKS usa o feedback de detecção menos diretamente atribuível ao PS e aumenta a dificuldade de localizar blocos de byte associados à assinatura, filtros e os seleciona através da calibração de amostras negativas, e combina os jogos SS com os veredictos AV originais através da l

Machine translation (Meta M2M100); the English original follows.

Abstract

Antivirus (AV) signatures encode valuable detection knowledge accumulated through expert analysis, yet repeated black-box queries can expose this knowledge for unauthorized reuse and targeted evasion. We propose Signature Knowledge Shielding (SKS), a design paradigm that protects existing AV rules, termed Protected Signatures (PS), through auxiliary Shielding Signatures (SS). SKS uses AV-supervised importance ranking to discover candidate byte blocks, filters and selects them through negative-sample calibration, and combines SS matches with original AV verdicts through logical OR. SS matching introduces additional positive responses and verdict changes during probing, making detection feedback less directly attributable to PS and increasing the difficulty of localizing signature-related content, while preserving original positive verdicts. Within SKS, we integrate five individually tuned non-learning matching methods and further propose Robust Embedding Matching (REM), a lightweight learned matcher trained with random context and byte perturbations. REM provides stronger and more consistent protection against content modifications and scanning-alignment changes. We develop and open-source a ClamAV-based prototype and evaluate it against five probing methods. With an observed additional test false-positive rate below 0.1%, REM raises the mean query count of state-of-the-art probing to as much as 282.57 times the unprotected baseline, while introducing only 0.67% GPU scanning overhead. These results demonstrate that SKS can substantially increase signature-extraction costs with limited impact on detection utility and scanning efficiency.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Context (archaeology), Intrusion detection system, Byte, Embedding, Matching (statistics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange