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

Reported by arXiv cs.CR (Behrad Tajalli, Henk Berendsen, Xiaoyun Xu, Stjepan Picek)

Summary by Cyber Security News15 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/2610.19947

arXiv:2610.19947v1 Announce Type: new Abstract: Backdoor attacks on deep neural networks are commonly evaluated by attack success rate and benign accuracy, yet their stealthiness remains inconsistently defined and measured. Existing work often studies only one observable aspect of stealthiness, such as trigger imperceptibility, feature-space separability, parameter-space concentration, or evasion of particular defenses.

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

Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection

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

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

Towards Merging-conditional Backdoor Unalignment against Large Language Models

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

Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller