AI makes brain computer interfaces vulnerable to new attack types
NERVE Attacks: Breaking AI-Powered Brain-Computer Interfaces
Cryptography and Security
Summary
Brain-Computer Interfaces (BCIs) connect human brains directly to computers, but as AI is used more in these systems, new security risks appear. The authors describe five main ways attackers can exploit BCIs to steal brain data or control connected devices. They created a tool called EEGle to find and study these vulnerabilities, discovering 17 new attack examples. Their work shows how AI can help even non-experts launch these attacks and highlights the need to protect this technology carefully.
Brain-Computer InterfaceArtificial IntelligenceNeural signalsCybersecurityNeuro-mimetic forgeryDesynchronizationReplay attackBackdoorGenerative AI
Authors
Zahra Tarkhani, Georgios Akkogiounoglou, Lorena Qendro, Isabel Tscherniak, Anil Madhavapeddy
Abstract
The rapid integration of AI into human-centred systems such as Brain-Computer Interfaces (BCIs) has created a poorly understood attack surface linking neural signals to physical systems. Exploits in this domain threaten cognitive autonomy, mental privacy, and physical safety, from neural data exfiltration to malicious control of BCI-tethered devices. We introduce the NERVE Attacks class, a systematic characterisation of five orthogonal attack dimensions that together span the complete BCI stack: Neuro-mimetic Forgery (N), Evasion via Desynchronization (E), Replay-based Hijacking (R), Vein Tapping (V), and Embedded Backdoors (E). To evaluate this class, we present EEGle, an AI-assisted extensible framework for systematic BCI security analysis. Our evaluation uncovers 17 novel neuro-specific attack instances and reveals a stealth-effectiveness spectrum unique to BCI backdoor design. We also show that generative AI lowers the barrier to entry for non-expert attackers and provide EEGle to the community for building and verifying the security of these deeply personal devices.