Bounding the Invertibility of Privacy-Preserving Instance Encoding Using Fisher Information
–Neural Information Processing Systems
In this paper, we propose a theoretically-principled measure for the invertibility of instance encoding based on Fisher information that is broadly applicable to a wide range of popular encoders.
Neural Information Processing Systems
Oct-9-2025, 03:26:27 GMT
- Country:
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Asia > Middle East
- Israel (0.04)
- Republic of Türkiye > Istanbul Province
- Istanbul (0.04)
- Europe
- Austria > Vienna (0.14)
- France > Île-de-France
- Italy > Sicily
- Palermo (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Netherlands > North Brabant
- Eindhoven (0.04)
- North America
- Canada > Quebec
- Montreal (0.04)
- Puerto Rico > San Juan
- San Juan (0.04)
- United States
- California
- Los Angeles County > Long Beach (0.04)
- San Francisco County > San Francisco (0.14)
- Santa Barbara County > Santa Barbara (0.04)
- Santa Clara County > Palo Alto (0.04)
- Indiana > Monroe County
- Bloomington (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Maryland > Baltimore (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- California
- Canada > Quebec
- Oceania > Australia
- Western Australia > Perth (0.04)
- Africa > Ethiopia
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.46)
- Natural Language (1.00)
- Representation & Reasoning (1.00)
- Vision (0.68)
- Machine Learning > Neural Networks
- Data Science > Data Mining (0.82)
- Security & Privacy (1.00)
- Artificial Intelligence
- Information Technology