Could LLM Watermark Detection be Public?
Split-key LLM watermark exposes one key publicly while private scores still detect informed forgery.
Stories per day · 30 days
2 RSS
6 stories, newest first · one card per story
Stories tagged #forgery
Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents
Semantic Behavioral Watermarking marks LLM-agent actions so provenance survives paraphrasing and resists forged trajectories.
There's a new way to break RSA that's faster than anything we've seen before
A new sieve-based forgery attack lowers textbook RSA security to 2^65 for 1024-bit keys.
1
Agents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic Control
AI agents can forge financial documents with high success rates and low costs, though the threat is overestimated by a factor of two.
Forgery of C2PA on a Pixel 10
Researcher forged a Google Pixel 10 C2PA content credential with genuine signatures, showing root-level attackers can fake photo provenance.
4
Forging Tree-Ring: Reproducing and Instrumenting Black-Box Semantic Watermark Forgery
Reprompt watermark forgery reproduces on Stable Diffusion XL using free-tier T4 GPUs, with forged images accepted by the genuine detector 5 of 6 times.