FakeSec - AI Photo Detector
Detect AI-generated photos with 12 forensic analysis methods
What it does
Most AI detectors rely on a single model that's easy to fool. FakeSec runs 12 independent methods on every photo — 3 neural networks plus 9 forensic analyses (FFT, ELA, noise, pixels, EXIF, texture, color, Benford's Law, edge detection). Each method catches what others miss. Results are combined into one clear verdict. Available on web and as a Telegram bot. 3 free checks, no credit card needed.
Does a similar job
all alternatives →
- FOFake or real? Try our AI image detector2024 · trial.nuanced.dev · ▲22
Hey HN! We're Ayman and Dylan, co-founders of Nuanced (https://www.nuanced.dev/). We want to share a tool we’re working on to detect fake and real images: https://trial.nuanced.dev/demo/. The UI is bare-bones but you’ll get the idea. Drag or upload an image and our tool will display the probabilities with which it thinks that the image might be AI-generated or not. If you want, you can click “No, it’s AI” to confirm that the image was AI-generated, or “No, it’s real” to confirm that the image was not AI-generated. Why we’re working on this: as AI-generated…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
