NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#kgw

0 stories this week · 3 this month · 3 in 6 months · mostly AI

Stories per day · 30 days

Relatedwatermarking2 agent-skills1 black-box1 constitution1 detection-evasion1 leakage-tracing1 llm1 llm-watermark1 open-source1 ownership1 provenance1 synthid1 text-detection1

3 stories, newest first · one card per story

arXiv cs.CR10d ago

Black-box attack defeats statistical LLM watermarks including SynthID

The attack drops detection to at most 0.05 on seven schemes and three models without keys or weights.

llm-watermark synthid

1

Hugging Face daily papers20d ago

SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification

SkillMarker watermarks agent skills with KGW so owners can verify copies without breaking procedural accuracy.

watermarking kgw

2

arXiv cs.CR23d ago

Constitution-Guided Watermarking

Constitution-Guided Watermarking selects per-request watermark trade-offs from natural-language provider rules.

watermarking kgw

1