Everyone's a little bit racist: a novel ML backdoor attack in black-box mode

Reported by arXiv cs.CR (Michele Cerrta, Gabriele Costa)

Summary by Cyber Security News19 Oct 2026, 06:00 CET

About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.22459

arXiv:2610.22459v1 Announce Type: new Abstract: Backdoors are among the most impactful attacks against Machine Learning (ML), yet most existing methods assume some form of training-time poisoning or direct model manipulation. This is often considered sufficient to assume that existing systems are not exposed to actual risks.

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

Hiding Capabilities in AI Models

Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering

I underestimated how fast security teams would trust AI to act in the SOC

ControlUp’s Pulse AI Resolve diagnoses and fixes IT issues within admin-defined controls

Attacker Relentlessly Scans for Credentials by Impersonating AI Bots

VikingCloud gives businesses a scorecard for AI governance readiness