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

#llm-fingerprinting

1 stories this week · 2 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedagentic-attacks1 feed-forward-networks1 harness-fingerprinting1 honeypot1 model-ownership1 open-weights1 shibboleth1 spectral-analysis1

2 stories, newest first · one card per story

arXiv cs.CR2d ago

Shibboleth traps fingerprint LLMs and harnesses in agentic attacks

Combined inference reached 90% top-1 accuracy across 15 models and 92% across four harnesses.

agentic-attacks llm-fingerprinting

arXiv cs.CR20d ago

Training-free spectral fingerprints match related LLM checkpoints from weights

GATE singular-value features stay similar under instruction tuning, quantization, pruning, and distillation without prompts or forward passes.

llm-fingerprinting open-weights

2