AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain

Quanrui Rao, Lin Wang, Wuying Liu

ICLR 2024 · 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 how CNNs memorize and generalize backdoor-poisoned samples through the frequency domain, examining the role of frequency-domain trigger features in backdoor attacks.

Problem

CNNs are vulnerable to backdoor injection, behaving normally on clean inputs but producing attacker-specified outputs on poisoned ones; prior work focused on spatial-domain trigger changes and their effect on generalization.

Approach

Shifts the analysis to the frequency domain, examining how CNNs memorize poisoned samples and generalize to backdoor triggers in frequency space rather than spatial space.

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