WebAlly: Making Visual Task-based CAPTCHAs Transferable for People with Visual
summary
WebAlly is a prototype that lets people with visual impairments transfer task-based visual CAPTCHAs to a remote helper via an interactive screenshot limited remote control that crops and mirrors only the CAPTCHA area. The team runs a role-play study with 18 participants in 10 pairs across four conditions (friend vs stranger and paid vs volunteer), finds PVIs accept it as a last-resort option, it reduces some privacy/security risks, allies worry about open links, and the system proves feasible.
AI-written summary · about
chapters (6)
related talks
09mImageAlly: A Human-AI Hybrid Approach to Support Blind People in Detecting...
23mCooperative Privacy and Security: Learning from People with Visual Impairments
10mBlind and Human: Exploring More Usable Audio CAPTCHA Designs
50mAI as an A11y Ally
21mRethinking web accessibility: Using AR for people with disabilities
43mHow to Make a Web App Accessible to a Blind Person
10mDualCheck: Exploiting Human Verification Tasks for Opportunistic Online Safety...
43mHow to Start Testing Your Product With Visually Impaired People
