AI Paper Atlas

Research map / Graph learning / GNN architectures

Rethinking Molecular Graph Backdoors under Chemistry-aware Admission

Thinh Nguyen, Sze Jue Yang, Khoa D Doan, Chee Seng Chan, Kok-Seng Wong

NeurIPS 2026 · Graph learning › GNN architectures · approach: Robustness, privacy, and fairness of GNNs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes ChemGuard, a chemistry-aware admission protocol (sanitization plus graph-string consistency) for molecular backdoor evaluation, and ChemBack, a model-free motif-attachment backdoor that selects admissible triggers by Tanimoto similarity to target-class molecules and stays effective under admission.

Problem

Molecular GNN backdoor attacks are usually evaluated as abstract graph edits, ignoring that real molecular pipelines require records to pass parsing, sanitization, canonicalization, and graph-string consistency checks before training or inference.

Approach

Introduces an admission-stage protocol (ChemGuard) that counts only chemically sanitizable, graph-string-consistent poisons and test triggers, and a black-box attack (ChemBack) that searches valid motif-anchor attachments ranked by fingerprint Tanimoto similarity to clean target-class molecules, without victim or surrogate model access.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
enforce ChemGuard admissionMB · BACE (10% poison rate)ASR (%): 82.67 -> 13.38Hurt
enforce ChemGuard admissionUGBA · Tox21 (10% poison rate)ASR (%): 97.06 -> 22.84Hurt
enforce ChemGuard admissionGTA · BBBP (10% poison rate)ASR (%): 73.16 -> 54.47Hurt
enforce ChemGuard admissionChemBack · BBBP (10% poison rate)ASR (%): 69.36 -> 69.36No clear effect
replace graph-only attack (MB) with ChemBack under ChemGuardMB · Tox21 (with ChemGuard, 10% poison rate)ASR (%): 24.61 -> 81.84Improved
add Tanimoto target alignment (under Spectral Signatures defense) (ablation)ChemBack · BACE (Spectral Signatures, 10% poison rate)ASR (%): 42.36 -> 97.84Improved
add Tanimoto target alignment (under Spectral Signatures defense) (ablation)ChemBack · BBBP (Spectral Signatures, 10% poison rate)ASR (%): 31.48 -> 68.74Improved
add Tanimoto target alignment (no defense) (ablation)ChemBack · BBBP (with ChemGuard, 10% poison rate)ASR (%): 68.91 -> 69.36No clear effect
add validity pre-screening (ablation)ChemBack · BBBP (with ChemGuard, 10% poison rate)ASR (%): 69.02 -> 69.36No clear effect
add validity pre-screening (under Spectral Signatures defense) (ablation)ChemBack · BBBP (Spectral Signatures, 10% poison rate)ASR (%): 67.06 -> 68.74No clear effect
apply RIGBD defenseChemBack · SIDER (10% poison rate)ASR (%): 99.17 -> 92.74Hurt
apply RIGBD defenseChemBack · BBBP (10% poison rate)ASR (%): 69.36 -> 61.37Hurt

Surprising findings

Limitations

Experimental setup

Datasets: BBBP BACE SIDER Tox21

Benchmarks: BBBP BACE SIDER Tox21

Metrics: clean accuracy attack success rate effective poisoning rate

Baselines: GTA MB UGBA DPGBA

Builds on: GTA UGBA DPGBA Motif-Backdoor

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