Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Detecting poisoning attacks on neural networks by activation clustering

Detecting poisoning attacks on neural networks by activation clustering

US Patent 11188789 · Granted Nov 30, 2021

Estimated economic value: $2,996,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Dynamically applied processes for mitigating adversarial jamming attack events2025
Secure reordering using tensor of indicators2025
Graph exploration framework for adversarial example generation2025
Graph exploration framework for adversarial example generation2025
Equalizer for removing inter symbol interference of data signal by increasing pu2025
Adaptive robustness certification against adversarial examples2025
Adaptive robustness certification against adversarial examples2025
Methods of fabricating semiconductor devices2025
Privacy-preserving federated learning2024
Federated learning with dataset sketch commitment based malicious participant id2024
Building a federated learning framework2024
Dynamic gradient deception against adversarial examples in machine learning mode2024