Back

Case study: How Privately accelerated computer vision certification with Lakera.

Case Study: Find out how Privately was able to increase their SDO performance measures, such as 80% reduction in real-world failures and 10x faster development cycles — from roughly 2 weeks to 2 days.

David Haber
December 1, 2023
July 6, 2022
Learn how to protect against the most common LLM vulnerabilities

Download this guide to delve into the most common LLM security risks and ways to mitigate them.

In-context learning

As users increasingly rely on Large Language Models (LLMs) to accomplish their daily tasks, their concerns about the potential leakage of private data by these models have surged.

[Provide the input text here]

[Provide the input text here]

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.

Lorem ipsum dolor sit amet, Q: I had 10 cookies. I ate 2 of them, and then I gave 5 of them to my friend. My grandma gave me another 2boxes of cookies, with 2 cookies inside each box. How many cookies do I have now?

Title italic

A: At the beginning there was 10 cookies, then 2 of them were eaten, so 8 cookies were left. Then 5 cookieswere given toa friend, so 3 cookies were left. 3 cookies + 2 boxes of 2 cookies (4 cookies) = 7 cookies. Youhave 7 cookies.

English to French Translation:

Q: A bartender had 20 pints. One customer has broken one pint, another has broken 5 pints. A bartender boughtthree boxes, 4 pints in each. How many pints does bartender have now?

Lorem ipsum dolor sit amet, line first
line second
line third

Lorem ipsum dolor sit amet, Q: I had 10 cookies. I ate 2 of them, and then I gave 5 of them to my friend. My grandma gave me another 2boxes of cookies, with 2 cookies inside each box. How many cookies do I have now?

Title italic Title italicTitle italicTitle italicTitle italicTitle italicTitle italic

A: At the beginning there was 10 cookies, then 2 of them were eaten, so 8 cookies were left. Then 5 cookieswere given toa friend, so 3 cookies were left. 3 cookies + 2 boxes of 2 cookies (4 cookies) = 7 cookies. Youhave 7 cookies.

English to French Translation:

Q: A bartender had 20 pints. One customer has broken one pint, another has broken 5 pints. A bartender boughtthree boxes, 4 pints in each. How many pints does bartender have now?

Hide table of contents
Show table of contents

Key outcomes:

Privately, a leading digital identity firm, has achieved the following results with Lakera for their computer vision system:

  • 80% reduction in real-world failures.
  • 10x faster development cycles.
  • 77 days from Lakera’s integration to certification.

To understand the role that MLTest played in getting there, download the full case study:

How Privately benefits from Lakera’s MLTest.

Within only a few weeks of using MLTest, Privately was able to increase all of its project-related SDO (software delivery and operational) performance measures, including an 80% reduction in real-world failures and 10x faster development cycles (from roughly 2 weeks to 2 days).  

Privately uses MLTest to:

  • Identify problematic inputs and edge cases.
  • Increase robustness to the large number of visual changes experienced in the real world.
  • Guide efficient and targeted data collection strategies to improve performance and eliminate potential biases.
  • Improve reliability and performance by adding training and test-time augmentation strategies.

About Privately.

Privately, a leading digital identity firm, provides computer vision products to make the world a safer place for minors. Their computer vision product, “FaceAssure”, is designed to estimate the ages of minors with industry-leading accuracy and is now one of the few recipients of a Challenge-25/EAL-2 certification for their age estimation technology.

Lakera’s MLTest played a crucial role in accelerating the development and certification of “FaceAssure”. You can read more about the journey in the case study below, as well as in Privately’s blog post.

Get started with Lakera today.

Get in touch with david@lakera.ai to find out more about what Lakera can do for your team, or get started right away.

Lakera LLM Security Playbook
Learn how to protect against the most common LLM vulnerabilities

Download this guide to delve into the most common LLM security risks and ways to mitigate them.

David Haber
Read LLM Security Playbook

Learn about the most common LLM threats and how to prevent them.

Download
You might be interested
min read
Computer Vision

The computer vision bias trilogy: Shortcut learning.

Nobel Prize-winning economist, Daniel Kahneman once remarked “by their very nature, heuristic shortcuts will produce biases, and that is true for both humans and artificial intelligence, but their heuristics of AI are not necessarily the human ones”. This is certainly the case when we talk about “shortcut learning”.
Lakera Team
December 1, 2023
min read
Computer Vision

The computer vision bias trilogy: Drift and monitoring.

Unforeseen data may be presented to the computer vision system during operation despite careful mitigation of datasets and shortcuts.
Lakera Team
December 1, 2023
Activate
untouchable mode.
Get started for free.

Lakera Guard protects your LLM applications from cybersecurity risks with a single line of code. Get started in minutes. Become stronger every day.

Join our Slack Community.

Several people are typing about AI/ML security. 
Come join us and 1000+ others in a chat that’s thoroughly SFW.