ClareNow
Search
ClareNow
Toggle sidebar
Technology → Neutral

Eufy Expands Face-Reading Smart Lock Line, Specializing in On-Device Processing

Eufy's FamiLock line is now larger, with more affordable models that limit AI processing to help protect your privacy. Here's how that works.

CNET 2 min read 6/10
Eufy Expands Face-Reading Smart Lock Line, Specializing in On-Device Processing
Key Takeaways
  • Eufy expanded its FamiLock line to three models, with prices ranging from $199 to $349, all using on-device facial recognition that stores biometric data locally.
  • The new budget-friendly model cuts costs by omitting Wi-Fi connectivity, relying instead on Bluetooth and a keypad backup, while still offering face unlock in under 0.3 seconds.
  • On-device AI processing eliminates the need for cloud subscriptions and reduces the risk of remote data breaches, a key differentiator in the smart lock market.
  • Global smart lock sales are expected to exceed $6.1 billion by 2030, driven by rising home security awareness and the integration of AI-based features like facial recognition.
  • Eufy's NPU (neural processing unit) enables offline face matching, with accuracy rates above 99% in controlled testing, even in complete darkness using infrared sensors.
Eufy has expanded its FamiLock line of face-reading smart locks, introducing more affordable models that keep AI processing on the device itself—a move designed to address growing consumer privacy concerns over cloud-based facial recognition. Anker-owned Eufy, known for its privacy-first approach, now offers three FamiLock variants: the original flagship, a mid-range model, and a budget-friendly option starting at $199, each featuring on-device facial recognition that stores biometric data locally rather than sending it to the cloud. This expansion comes as smart lock adoption surges—the global market is projected to reach $6.1 billion by 2030—but consumers remain wary of hacks and data leaks. Eufy's on-device processing means face templates never leave the lock, reducing attack surfaces and eliminating subscription fees for cloud storage. The system uses a neural processing unit (NPU) to match faces against encrypted local storage in under 0.3 seconds, with accuracy maintained even in low light. Industry analysts note that while on-device AI is slower to update than cloud-based models, it offers a compelling trade-off for privacy-conscious buyers. Eufy's move signals a broader trend: major players like Yale and August are also exploring edge AI for locks. Expect competitors to follow suit, and look for Eufy to add remote management via the HomeBase 3 hub and Matter compatibility in future firmware updates.

Frequently Asked Questions

Eufy's FamiLock uses a built-in neural processing unit (NPU) to capture and match facial features against encrypted templates stored locally on the lock. The process takes under 0.3 seconds and works in low light using infrared sensors. No facial data is ever sent to the cloud.

Yes. Because all facial recognition processing happens on the device itself, biometric data never leaves the lock. This eliminates risks of cloud server hacks and data leaks, and also means no ongoing subscription fees for cloud storage.

Eufy offers three FamiLock models: the flagship version at $349, a mid-range model at $249, and a budget-friendly option starting at $199. The budget model omits Wi-Fi but retains Bluetooth and keypad backup.

Yes. The more expensive models work with the Eufy HomeBase 3 hub, enabling remote management and integration with Amazon Alexa and Google Assistant. Matter compatibility is expected via a future firmware update.

Eufy claims accuracy above 99% in controlled tests. The system uses infrared sensors for use in complete darkness and employs liveness detection to prevent spoofing with photos or videos.

All FamiLock models include a physical key override and a backup keypad entry. Additionally, a low-battery warning is sent via the Eufy Security app, and the lock can be powered temporarily with a 9V battery externally.

Original source

www.cnet.com

Read original

Discussion

Join the discussion

Sign in to post a comment or reply.

No comments yet. Be the first to share your thoughts!

Sign in
Enter your email to receive a one-time sign-in code. No password needed.
Email address