Discover a novel computer vision-based attack that automatically discloses touch screen inputs, including passcodes, from a distance of three meters using spying cameras like Google Glass. Learn how the attack tracks fingertip movements, analyzes shadow formations, and applies advanced computer vision techniques to recognize over 90% of tapped passcodes, even when the screen is not visible to the naked eye. Explore the methodology behind this stealthy attack, including optical flow, deformable part-based model object detection, k-means clustering, and planar homography. Understand the potential impact of this security threat in public spaces and conferences. Examine the proposed countermeasure: a context-aware Privacy Enhancing Keyboard (PEK) for Android systems that randomizes the keyboard layout for sensitive information input.