Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

新闻报道新闻报道
0

FaceObfuscator: A New Solution for Facial Privacy Protection from Zhejiang University andAlibaba

This article reports on a new facial privacy protection solution called FaceObfuscator, developed by Zhejiang University and Alibaba Security. It addresses the growing concern of facial data security and the vulnerability of facial recognition systems to reconstruction attacks.

KeyPoints:

  • The Problem: Existing facial recognition systems store facial features in databases, which are susceptible to leakage. Malicious actors can use these features toreconstruct original faces through powerful AI techniques, compromising privacy.
  • FaceObfuscator’s Solution: The solution involves two key steps:
    • Redundant Information Removal: It removes redundant visual information from facial images,preserving only the essential features for recognition.
    • Facial Feature Obfuscation: It introduces randomness to the facial features, making it impossible for attackers to reconstruct the original face.
  • Advantages:
    • Strong PrivacyProtection: Effectively prevents reconstruction attacks.
    • High Recognition Accuracy: Maintains high recognition accuracy comparable to mainstream models.
    • High Efficiency: Requires minimal storage space and computational resources.
  • Applications: FaceObfuscator can be widely applied in various scenarios, including surveillance, facial payment,and access control, benefiting industries like security, finance, and education.

Technical Details:

  • Frequency Domain Transformation: The solution utilizes Discrete Cosine Transform (DCT) to convert images into frequency domain features, allowing for the identification and removal of redundant information.
  • Randomness Introduction: Randomnessis introduced to the facial features through both direction and scale transformations, hindering the reconstruction process.
  • Server-Side Reversal: The server-side reverses the scale transformation to maintain recognition accuracy.

Experimental Results:

  • Robustness: FaceObfuscator effectively prevents reconstruction attacks, significantly reducing thecosine similarity between reconstructed and original images and minimizing the success rate of replay attacks.
  • Performance: The solution maintains high recognition accuracy, low storage overhead, and efficient computational speed.

Conclusion:

FaceObfuscator offers a promising solution for facial privacy protection, effectively addressing the vulnerabilities of existing facial recognition systems. Its combination of strong privacy protection, high recognition accuracy, and efficient performance makes it a valuable tool for ensuring secure and reliable facial recognition applications.

【source】https://www.ithome.com/0/791/494.htm

Views: 0

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注