AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures

Suqing Wang, Ziyang Ma, Li Xinyi, Zuchao Li

AAAI 2026 · Large language models › Instruction and fine-tuning · approach: Safety alignment after fine-tuning · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
build fingerprint from invariant products (QK^T and VO) instead of raw Wq/Wk/Wv/Wo matrices (ablation)GhostSpec · permutation and scaling attackssimilarity scoreImproved
use GhostSpec-mse versus data-free baseline PCS on permuted Llama-2-7bGhostSpec · Llama-2-7b-permutedsimilarity score: 0.3863 -> 0.9761Improved
use GhostSpec-mse vs GhostSpec-corr on Llemma 7b fine-tuneGhostSpec · Llama-2-7b vs Llemma 7bsimilarity score: 0.7595 -> 0.9532Improved
use POSA alignment to compare models of different depthGhostSpec-mse · pruned and expanded modelssimilarity score: 0.8886 on Sheared-Llama 1.3B vs PCS 0.0000Improved
fine-tune adversarially with spectral divergence loss to evade GhostSpecLlama-3.2-1B-instruct · evasion attackspectral distance vs task performanceHurt
use MLP up/down projection spectra instead of attention products (ablation)GhostSpec-mse · Llama-2-7b fine-tuned variantssimilarity score: fine-tuned above 0.96 vs unrelated near zeroNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy