Elektrine lite

โ† Feed

@anyrun_app@infosec.exchange

2026-09-21 13:21 UTC

๐Ÿชฐ We taught a fly to analyze phishing in #ANYRUN Sandbox. No OCR, no LLM, no DOM hints, and no ability to read. Thanks to sandbox interactivity, the fly can move through the attack chain on its own and observe the full phishing flow: follow links, resolve CAPTCHAs, go through redirects, and fill forms with an email and password. See how the fly moves through an AiTM phishing flow: ๐Ÿชฐ https://app.any.run/tasks/92c4e053-5abf-428a-8587-bc8abd43c7fd/?utm_source=mastodon&utm_medium=post&utm_campaign=fly_analyzed_phishing&utm_term=210926&utm_content=linktoservice ๐Ÿชฐ https://app.any.run/tasks/f32ec968-3f2d-49f0-8654-6581370740f1/?utm_source=mastodon&utm_medium=post&utm_campaign=fly_analyzed_phishing&utm_term=210926&utm_content=linktoservice Device Code Flow: ๐Ÿชฐ https://app.any.run/tasks/3efc3564-7a8b-4475-8114-c86fde18ad48/?utm_source=mastodon&utm_medium=post&utm_campaign=fly_analyzed_phishing&utm_term=210926&utm_content=linktoservice ๐Ÿง  Whatโ€™s inside: 1. ๐—•๐—ฟ๐—ฎ๐—ถ๐—ป. Fruit fly hemibrain mapped to FlyWire for 3D visualization. 2. ๐—™๐—น๐—ถ๐—ด๐—ต๐˜. There is inertia, sharp saccades instead of a smooth path, and braking based on how fast the image moves. 3. ๐—ฉ๐—ถ๐˜€๐—ถ๐—ผ๐—ป, ๐˜€๐—บ๐—ฒ๐—น๐—น, ๐—ฎ๐—ป๐—ฑ ๐˜๐—ฎ๐˜€๐˜๐—ฒ. The fly cannot read. There is only contrast, movement, color, and shape. A button, link, and checkbox are different visual patterns converted into sensory signals. 4. ๐—Ÿ๐—ฒ๐—ด๐˜€. Landing on the right area counts as a click. If the fly finds an empty field, it โ€œsecretes acidโ€: select all โ†’ paste email. 5. ๐——๐—ผ๐—ฝ๐—ฎ๐—บ๐—ถ๐—ป๐—ฒ, ๐—บ๐—ผ๐˜๐—ถ๐˜ƒ๐—ฎ๐˜๐—ถ๐—ผ๐—ป, ๐—ฎ๐—ป๐—ฑ ๐—ฎ๐˜ƒ๐—ฒ๐—ฟ๐˜€๐—ถ๐—ผ๐—ป. When fed, it mostly flies around and looks at the page instead of clicking blindly. When hungry, it is more active and gets frustrated faster when it finds nothing. A successful click gives a reward signal and reduces frustration. A dead click increases avoidance of that area. When the search reaches a dead end, frustration makes the fly scroll down. 6. ๐— ๐—ฒ๐—บ๐—ผ๐—ฟ๐˜†. It remembers the screen map and does not return to places where nothing happenedโ€” inhibition of return. โ—๏ธ The fly is not smarter or more useful than an ML model trained for the task. This is not a phishing detection solution and not an attempt to replace one. Made for fun, research curiosity, and the community ๐Ÿค— #cybersecurity #infosec

Replies (1)