AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors

Jingxiao Yang, Ping He, Tianyu Du, Sun Bing, Xuhong Zhang

AAAI 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 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
combine lexical and syntax perturbations in HogVul versus ALERT (lexical only)HogVul · Devign, DiverseVul, BigVul (3 victim models)ASR: +26.37 ASR on averageImproved
combine lexical and syntax perturbations in HogVul versus DIP (dead code only)HogVul · Devign, DiverseVul, BigVul (3 victim models)ASR: +25.72 ASR on averageImproved
HogVul versus ALERT on confidence dropHogVul · Devign, DiverseVul, BigVulconfidence drop: 0.18 larger than ALERTImproved
HogVul versus DIP on CodeBLEU similarity to the original codeHogVul · Devign, DiverseVul, BigVulCodeBLEU: Devign CodeT5: 0.86 (DIP) vs 0.84 (HogVul)Hurt
add lexical perturbation (PSO) to structure-only attack (ablation)HogVul · Devign (CodeT5)ASRImproved
add structure-aware transformation to lexical-only attack (ablation)HogVul · Devign (CodeT5)ASR and confidence dropImproved
combine any two modules (C4-C6) (ablation)HogVul · Devign (CodeT5)ASRImproved
full model with semantic-aware initialization, PSO lexical and structural transformation (ablation)HogVul · Devign (CodeT5)ASR: best ASR 97.28%Improved
use PSO instead of MHM, greedy search or GA as optimizer (ablation)HogVul · code search trajectoriesconvergence and population diversityImproved
HogVul query efficiency versus baselinesHogVul · 9 victim model and dataset scenariosASR per Query: highest APQ in six out of nine scenariosImproved

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