Privacy-Preserving Smart Surveillance with Cross-Dataset Violence Detection and Decentralized Evidence Governance
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910278507036672 |
|---|---|
| author | Coşkun, Hasan Çolhak, Furkan Kulakov, Andrea Dimitrova, Vesna |
| author_facet | Coşkun, Hasan Çolhak, Furkan Kulakov, Andrea Dimitrova, Vesna |
| contents | AI-enabled surveillance can accelerate public-safety response, yet most systems still leave recorded evidence under centralized administrative control. This paper proposes a privacy-preserving smart surveillance framework that separates incident detection from evidence disclosure. A lightweight MobileNetV2-based video classifier detects violent clips, while each recorded incident segment is immediately encrypted and made accessible only through threshold-based approval. The decryption key is split with Shamir's Secret Sharing, member shares are protected with public-key cryptography, and voting is supported by time-limited tokens, two-factor authentication, signatures, and audit logs. This study evaluates MobileNetV2+LSTM, MobileNetV2+BiLSTM, and MobileNetV2+temporal CNN heads on SCVD, RWF-2000, and Real-Life Violence Situations under seven in-domain and cross-dataset scenarios. The best all-source model, MobileNetV2+BiLSTM, reaches 93.5% test accuracy and ROC-AUC 0.980% on the merged held-out set, while lower RWF-2000 slice performance confirms persistent dataset shift. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01225 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Privacy-Preserving Smart Surveillance with Cross-Dataset Violence Detection and Decentralized Evidence Governance Coşkun, Hasan Çolhak, Furkan Kulakov, Andrea Dimitrova, Vesna Cryptography and Security AI-enabled surveillance can accelerate public-safety response, yet most systems still leave recorded evidence under centralized administrative control. This paper proposes a privacy-preserving smart surveillance framework that separates incident detection from evidence disclosure. A lightweight MobileNetV2-based video classifier detects violent clips, while each recorded incident segment is immediately encrypted and made accessible only through threshold-based approval. The decryption key is split with Shamir's Secret Sharing, member shares are protected with public-key cryptography, and voting is supported by time-limited tokens, two-factor authentication, signatures, and audit logs. This study evaluates MobileNetV2+LSTM, MobileNetV2+BiLSTM, and MobileNetV2+temporal CNN heads on SCVD, RWF-2000, and Real-Life Violence Situations under seven in-domain and cross-dataset scenarios. The best all-source model, MobileNetV2+BiLSTM, reaches 93.5% test accuracy and ROC-AUC 0.980% on the merged held-out set, while lower RWF-2000 slice performance confirms persistent dataset shift. |
| title | Privacy-Preserving Smart Surveillance with Cross-Dataset Violence Detection and Decentralized Evidence Governance |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2606.01225 |