Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors

Reported by arXiv cs.CR (Arnab Dey, Mohammad Mahfuzul Islam)

Summary by Cyber Security News12 Oct 2026, 06:00 CEST

About this summary. This is a short, independently written summary of an article first published by arXiv cs.CR. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.13051

arXiv:2610.13051v1 Announce Type: new Abstract: Some backdoor attacks never touch an image. FLIP only changes labels: on CIFAR-10, flipping 3% of them makes a ResNet-32 send 99.7% of triggered source-class images to the attacker's class. The usual defenses look for the poison inside a model trained on those same labels.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

When Does Trust Help? A Leakage-Free Evaluation of Representation- and Aggregation-Based Defenses Against Backdoors in Federated Intrusion Detection

Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection

Quiet Triggers, Loud Footprints: A Tri-Space Measurement Study of Backdoor Stealthiness

Hackers Backdoor Nextcloud Servers Through Critical Flaw in Collabora’s Built-in CODE App

Microsoft Disrupts 3 Phishing Kits Linked to Over 1 Billion Scam Messages

Volexity Uncovers Stealthy Ivanti VPN Attack Using Three Zero-Day Vulnerabilities