Signature filtering learns unreliable tokens with MILP and removes them at detection time, raising true positive rates from 8-31% to 78-99% across Kgw, Sweet, Unigram, and Exp watermarks on multiple corpora and LLMs while controlling false positives.
The Automotive BlackBox: Towards a standardization of automotive digital forensics,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
AliMark introduces a two-stage detection strategy with multi-candidate bit sequence alignment to improve robustness of sentence-level text watermarks against paraphrasing attacks.
A literature synthesis that defines digital vehicle forensics, formalizes its evidence triage problem, derives eight characteristics, and proposes a characteristic-driven procedure as a conceptual framework.
citing papers explorer
-
Signature filtering: a lightweight enhancement for statistical watermark detection in large language models
Signature filtering learns unreliable tokens with MILP and removes them at detection time, raising true positive rates from 8-31% to 78-99% across Kgw, Sweet, Unigram, and Exp watermarks on multiple corpora and LLMs while controlling false positives.