Evaluation of CAPTCHA to Ensure Accessibility in the Digital Age

CSEF · 2023 Behavioral & Social Sciences Honorable_mention Award

Overview

Users with visual impairments should be able to access the internet without getting blocked by CAPTCHA. CAPTCHA is a technology that helps differentiate humans from SPAM Bots. For users with disabilities, it adds another layer of complexity since they navigate the digital world with screen readers. Screen Readers cannot solve image captchas and audio captchas are also pretty difficult to solve. There are already products in the market(Google ReCaptcha) that have solved this problem. But they inspect users’ internet browser history to identify humanness. I wanted to find a solution that is accessible but also won’t invade users’ privacy. Procedures Instead of making the user take the test and prove themselves as humans, I built a system, that will determine the humanness of the user by looking at how they interact with the site. I built a five-layer protection that can differentiate, deviate and detect a bot from a human. It will fall back to CAPTCHA only when the humanness confidence score is low. Once the user solves the CAPTCHA, it will store a session cookie which will eliminate further bot checks for that site. Data and a brief analysis: I tested my solution with 5 trials. Each trial includes 600 runs. 100 runs from users & users with disabilities, and 100 runs from each bot type. I tested for 5 different bot types. Conclusion I was able to identify the bots with a 95% accuracy rate. The success rate had a direct relationship with the sophistication of the bot. While the rudimentary bots had the best identification rate, modern sophisticated bots had the lowest identification rate 92%. 97% of the users with screen readers got identified as humans and doesn’t have to fill in CAPTCHA. Only 3% of users with screen readers ended up with Audio CAPTCHA. My solution met both the accessibility requirements and privacy constraints.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (1)

  • Category Award: HM

Competition history

  • CSEF 2023 Behavioral & Social Sciences · Entry S0410

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google