| Key features | - Multi-layer forensic analysis examining visual inconsistencies, facial behaviour, audio anomalies, metadata, and traces of AI generation
- Facial movement and expression analysis to identify signs of manipulation
- Suspicious region pinpointing with visual indicators in images, videos and audio
- Metadata and provenance inspection to identify inconsistencies
- Explainable results and forensic reports for decision-making and legal proceedings
- Flexible deployment options including cloud, on-premises, containerised and air-gapped setups
- API and SDK integration into existing systems
- Landmarking analysis detecting inconsistencies in facial features and face-to-background alignment
- Behavioral signal analysis tracking blinking, breathing and emotional cues to confirm liveness
- Cross-modality checks aligning and comparing audio and video streams to expose manipulation
| - Three separate scores: hateful, abusive, threat
- Ten target signals under the hate score: race, color, religion, descent, national or ethnic origin, sexual orientation, gender, disability, age, other
- Runs fully on device with no server calls
- Supports 23 European languages from one model file
- 80MB model size optimized for iOS, Android, and browser
- 0.847 macro F1 accuracy on Multilingual HateCheck
- Warn before message is sent
- Comment triage without infrastructure
|
|---|
| What makes it different | - Forensic evidence-backed results with explainable indicators instead of guesswork
- Research-grade technology backed by Rabobank and showcased at major tech events
- Supports investigation, intelligence, law enforcement and legal workflows with evidence-ready outputs
- Multimodal detection across video, audio, image and text with unmatched precision
| - Multilingual support across 23 European languages in a single 80MB model
- Complete privacy with no data leaving the device
- Free access up to 100k monthly active devices with unlimited inference
|
|---|
Cyberette
Toxic