AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Backdoor Attacks Rerouted: BatchNorm as a Sink for Adversarial Signals

Md Abdul Kadir, Tuan Tran Anh, Daniel Sonntag

NeurIPS 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks

Read the paperCheck your idea against 137,217 papers

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

Studies backdoor attacks on CNN classifiers and proposes that BatchNorm layers act as a sink for adversarial/trigger signals; full text unavailable, so details are limited to the abstract.

Problem

Backdoor attacks on CNN-based classifiers cause targeted misclassification via imperceptible triggers while preserving clean accuracy, and triggers may also distort model explanations.

Approach

Based on the title, the paper frames BatchNorm layers as a sink that absorbs adversarial/backdoor signals; the abstract does not state the mechanism or method in detail.

Limitations

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