TGViewer
CyberOps CyberOps @operations_cyber · 21 subscribers
Post #169 24
You know how Google's AI images carry an invisible watermark called SynthID? It's meant to prove "yes, this was made by AI." I found a trick that quietly wipes it out - using nothing more than Stable Diffusion 1.5.

The method, called MARKNULL, drops watermark detection to 53% accuracy - basically a coin flip - while keeping the image looking cleaner than any other attack. Curious how it fools even Gemini itself?

Full Article

@operations_cyber
More from @operations_cyber
  1. Aug 17, 2026Знаешь про водяные знаки на ИИ-картинках? Google вшивает в свои изображения невидимый сигн…
  2. Aug 12, 2026photo post
  3. Aug 12, 2026Пентест - это когда ты играешь за хакера с разрешения владельца, чтобы проверить, реально…
  4. Aug 12, 2026You know how AI agents used to just solve staged hacking puzzles (CTF challenges)? Summer…
  5. Aug 9, 2026Представь: у тебя в сумке лежит AirTag, чтобы найти её, если потеряешь. Логично же? А тепе…
  6. Aug 9, 2026You know those little AirTags people toss in bags to track their stuff? They rely on Apple…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →