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
Resources
Related projects
JSHS · 2022
Breaking ‘Click the Crosswalks’ reCAPTCHA: A Technological and Economic Analysis
ISEF · 2020
Solving Image-Based CAPTCHAs Using Optical Character Recognition and Machine Learning
ISEF · 2022
An Enhanced Adversarial Attack Method for Defending Against CAPTCHA Solvers
ISEF · 2025
A Novel Approach To Using Artificial Intelligence to Aid the Hearing and Vision Impaired
ISEF · 2018
The Creation of a Wearable Device Using Artificial Intelligence Technologies to Aid the Visually Impaired
CSEF · 2018
Eye Track: An Indoor Navigation System for the Visually Impaired
CSEF · 2011
Development of a Mashup That Transforms a Smartphone into an Assisted Vision Aid
AJAS · 2022
This device helps the visually impaired by alerting them of objects nearby and providing directions.
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects