AI Paper Atlas

Research map / Detection and segmentation / CNN features

BDLF-Qwen3: Enhanced Cross-Architecture Binary Function Similarity Detection Through Binary Dynamic Layer Fusion

Yuanda Wang, Ji Zhou, Xinhui Han, Chao Zhang

AAAI 2026 · Detection and segmentation › CNN features · approach: Forgery detection · 1 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
add dynamic input-dependent layer weights (ablation)BDLF-Qwen3 · Cross-Bin poolsize 1,000Recall@10: 0.59 -> 0.67Improved
use dynamic weights instead of learned static weights (ablation)BDLF-Qwen3 · Cross-Bin poolsize 1,000Recall@10: 0.60 -> 0.67Improved
add XRef-enhanced information to Cross-Bin (ablation)BDLF-Qwen3 · Cross-Bin poolsize 10,000Recall@10: 0.335 -> 0.378Improved
add stage 1 partial fine-tuning before BDLF stage (ablation)Qwen3-Embedding BDLF · Cross-Bin poolsize 1,000NDCG@10: 0.50 -> 0.65Improved
add BDLF stage 2 after stage 1 fine-tuning (ablation)Qwen3-Embedding · Cross-Bin poolsize 1,000NDCG@10: 0.58 -> 0.65Improved
add BDLF stage 2 after stage 1 fine-tuning (ablation)UnixCoder · Cross-Bin poolsize 1,000NDCG@10: 0.44 -> 0.51Improved
add BDLF stage 2 after stage 1 fine-tuning (ablation)GraphCodeBERT · Cross-Bin poolsize 1,000NDCG@10: 0.31 -> 0.40Improved
BDLF-Qwen3 versus UnixCoder on unseen RISC-Vzero-shot cross-arch search · RISC-V (poolsize 1000)Recall@10: 0.38 -> 0.58Improved
BDLF-Qwen3 versus UnixCoder on vulnerability discoverycross-arch CWE search · 4 CWE typesRecall@10 (avg): 0.705 -> 0.945Improved
scale pool size from small to 10,000 (ablation)BDLF-Qwen3 · Cross-BinRecall@10: 0.905 -> 0.383Hurt

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