What is the relationship between model size (e.g., 7B vs 70B parameters) and the transferability of token-leve

Abstract

Abstract: Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract sensitive relationships between nodes (entities), potentially leading to academic misconduct, fraudulent transactions, or other malicious activities. Previous studies have primarily focused on single datasets and did not explore cross-dataset attacks, let alone attacks that leverage the combined knowledge of multiple attackers. However, we find that an attacker

Research Question

What is the relationship between model size (e.g., 7B vs 70B parameters) and the transferability of token-level adversarial attacks across SOTA legal reasoning models on the Abductive Logic Reasoning (ALR) benchmark, evaluated via accuracy degradation?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance