HiddenLayer, Inc.
25Patents
25Active
25Granted
62Portfolio score
Filing activity: Feb 23, 2023 → Feb 4, 2025
Most-cited patents
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US11995180B1 | Generative artificial intelligence model protection using output blocklist | Physics | 10 | Active |
| US11797672B1 | Machine learning-based technique for model provenance | Physics | 6 | Active |
| US11921903B1 | Machine learning model fingerprinting | Physics | 4 | Active |
| US11954199B1 | Scanning and detecting threats in machine learning models | Electricity | 2 | Active |
| US12229265B1 | Generative AI model protection using sidecars | Physics | 2 | Active |
| US12026255B1 | Machine learning model adversarial attack monitoring | Physics | 2 | Active |
| US12107885B1 | Prompt injection classifier using intermediate results | Electricity | 2 | Active |
| US12137118B1 | Prompt injection classifier using intermediate results | Electricity | 1 | Active |
| US12105844B1 | Selective redaction of personally identifiable information in generative artificial intelligence model outputs | Physics | 1 | Active |
| US11930030B1 | Detecting and responding to malicious acts directed towards machine learning models | Electricity | 1 | Active |
| US12174954B1 | Generative AI model information leakage prevention | Physics | 1 | Active |
| US12248883B1 | Generative artificial intelligence model prompt injection classifier | Physics | 1 | Active |
| US12111926B1 | Generative artificial intelligence model output obfuscation | Physics | 1 | Active |
| US12130917B1 | GenAI prompt injection classifier training using prompt attack structures | Physics | 1 | Active |
| US12130943B1 | Generative artificial intelligence model personally identifiable information detection and protection | Physics | 1 | Active |
| US12254120B2 | Machine learning model fingerprinting | Physics | 0 | Active |
| US12314378B1 | Machine learning model parameter based encryption | Electricity | 0 | Active |
| US12254104B1 | Hidden compartments in data encrypted using machine learning | Physics | 0 | Active |
| US12242622B1 | Hidden compartments in data encrypted using machine learning | Physics | 0 | Active |
| US12278836B1 | Canonicalization of unicode prompt injections | Electricity | 0 | Active |
| US12293277B1 | Multimodal generative AI model protection using sequential sidecars | Physics | 0 | Active |
| US12328331B1 | Detection of privacy attacks on machine learning models | Electricity | 0 | Active |
| US12314380B2 | Scanning and detecting threats in machine learning models | Electricity | 0 | Active |
| US12271805B1 | Data obfuscation using encoder-multi-decoder architecture | Electricity | 0 | Active |
| US12273381B1 | Detection of machine learning model attacks obfuscated in unicode | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Counts and citation impact are objective bibliographic measures.