Everyone's a little bit racist: a novel ML backdoor attack in black-box mode
A novel black-box backdoor attack against ML models operates without training-time poisoning, undermining a key assumption in most current defence frameworks.
Summary written by editorial AI · Source link below
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. In this paper, we introduce Backdoor-as-a-Service, a model-agnostic, fully black-box technique that, instead of installing a backdoor, activates it in the form of a latent
Editorial Analysis
Enterprises relying on supply-chain integrity checks at training time may miss backdoors implanted through inference-time manipulation—a blind spot in current AI governance.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the AI Security Desk
- OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication1d
- Exposed Infrastructure Reveals How Ransomware Affiliates Used AI Agents to Execute Intrusions3d
- You gave your AI agent access, but who is giving it orders?3d
- AI Agents as Insider Threats: Inside Microsoft's Bet on a Unified Security Stack3d
- Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances3d