{"slug": "hitting-a-nerve-with-attacks-on-ai-powered-brain-computer-interfaces", "title": "Hitting a NERVE with attacks on AI-powered brain-computer interfaces", "summary": "A preprint titled \"NERVE Attacks: Breaking AI-Powered Brain-Computer Interfaces\" from researchers Zahra Tarkhani, Georgios Akkogiounoglou, Isabel Tscherniak, Lorena Qendro of Nokia Bell Labs, and Anil Madhavapeddy categorizes the attack surface of AI-powered brain-computer interfaces and documents 17 novel neuro-specific attacks found using the EEGle security-analysis framework. The paper's end-to-end demonstration hijacked all three tasks of the CYBATHLON 2024 BCI game — cursor control, wheelchair navigation, and robotic-arm ice-machine operation — in about 8 seconds, with some chained attacks executing in under 10ms. The authors report no published defense against attacks such as evasion and desynchronisation signal attacks, and note their 2022 information flow control proposal covers only the systems half of the problem.", "body_md": "Human brain interfaces are advancing at a startling pace; Ray Kurzweil has just\njoined a startup that dispenses with skull surgery\nin favour of you [snorting charged nanoparticles](https://www.ibtimes.com.au/ray-kurzweil-joins-subsense-brain-computer-interfaces-1875104) that are then driven by\nmagnetic coils in a cap.\n\nThis all sounds very scifi, but the [software stack on these BCI](https://anil.recoil.org/papers/2022-enhancing-brain-security) devices\nhave an enormous and unguarded attack surface. [Zahra Tarkhani](https://zatkh.github.io/) has just uploaded a preprnt [NERVE Attacks: Breaking AI-Powered Brain-Computer Interfaces](https://anil.recoil.org/papers/2026-nerve-attacks) that we worked on with\ntwo brilliant interns who visited last summer, [Georgios Akkogiounoglou](https://github.com/sdi1400258) (KTH) and [Isabel Tscherniak](https://www.linkedin.com/in/isabel-tscherniak) (TUM),\nand [Lorena Qendro](https://lorenaqendro.github.io) at Nokia Bell Labs.\n\nBack in 2022, our [first pass at this](https://anil.recoil.org/ideas/brain-interface-security) found over\n[300 vulnerabilities](https://anil.recoil.org/papers/2022-enhancing-brain-security) across the stacks of commodity BCI headsets.\nThe new paper categorises this surface into what we dub the **NERVE attacks**, which\nbetween them cover the entire Brain-Computer stack from the radio interface to the underlying trained model:\n\nIn order to help find these vulnerability points, we built 'EEGle' (no relation to my [Energy and Environment Group](https://anil.recoil.org/notes/eeg-interns-2025)!). EEGle's an extensible framework for BCI security analysis that exposed 17 novel neuro-specific attacks.\nAnd like [other areas recently](https://anil.recoil.org/notes/rumour-is-the-exploit) LLMs remove the need for any expertise in neuroscience and\nmake it super easy to supply the physiological parameters for a forged motor-imagery signal.\nThe same models are just as happy [scanning for the flaws](https://anil.recoil.org/notes/scrutineer-local-llm) as finding ways through them.\n\nThe end-to-end demonstration in the paper against the [CYBATHLON 2024](https://cybathlon.com/en/event/disciplines/bci) BCI game\nis pretty cool. This game has three tasks: cursor control, wheelchair navigation, and operating an ice machine with a robotic arm.\nAll three were hijacked via raw replay, synthesised epochs and augmented replay in about 8 seconds.\n\nThe defences aren't in good shape unfortunately. There's no (published) protection against some of these such as the evasion/desynchronisation signal attacks,\nand the [information flow control](https://anil.recoil.org/projects/difc-tee) approach we proposed back in 2022 only covers the systems half of the problem.\nThe reason it's all so worrying is that [chained attacks](https://anil.recoil.org/notes/internet-immune-system) are really\neasy to execute these days, several of which are shown in the paper and often take <10ms.\nIn the ice machine task, a misclassification tips the robotic arm over, showing the physical stakes involved given\nthe same mechanisms are intended to be used for [wheelchairs](https://upnride.com/) and [prosthetics](https://uk.hypershell.tech).\n\nSo there's certainly some brainy work to be done here! The [preprint is on arXiv](https://arxiv.org/abs/2609.08971) and comments are very welcome.", "url": "https://wpnews.pro/news/hitting-a-nerve-with-attacks-on-ai-powered-brain-computer-interfaces", "canonical_source": "https://anil.recoil.org/notes/nerve-attacks", "published_at": "2026-09-11 00:00:00+00:00", "updated_at": "2026-09-11 19:22:22.111696+00:00", "lang": "en", "topics": ["ai-safety", "ai-research", "artificial-intelligence", "ai-ethics"], "entities": ["Zahra Tarkhani", "Georgios Akkogiounoglou", "Isabel Tscherniak", "Lorena Qendro", "Nokia Bell Labs", "Anil Madhavapeddy", "EEGle", "CYBATHLON 2024"], "alternates": {"html": "https://wpnews.pro/news/hitting-a-nerve-with-attacks-on-ai-powered-brain-computer-interfaces", "markdown": "https://wpnews.pro/news/hitting-a-nerve-with-attacks-on-ai-powered-brain-computer-interfaces.md", "text": "https://wpnews.pro/news/hitting-a-nerve-with-attacks-on-ai-powered-brain-computer-interfaces.txt", "jsonld": "https://wpnews.pro/news/hitting-a-nerve-with-attacks-on-ai-powered-brain-computer-interfaces.jsonld"}}