Post

Bionic Vision Lab
@bionicvisionlab.org

🚨Fuzzing the brain - automated stress testing for ML-driven neurostimulation🚨 As #MachineLearning begins to control electrical stimulation in neural interfaces, how do we know these models are safe? Paper in Journal of Neural Engineering: bionicvisionlab.org/publications... #BCI #neuroskyence

bionicvisionlab.orgFuzzing the brain: Automated stress testing for the safety of ML-driven neurostimulation | Bionic Vision LabWe propose a systematic, quantitative approach to detect and characterize unsafe stimulation patterns in ML-driven neurostimulation systems.
Bionic Vision Lab
@bionicvisionlab.org

Most prior work treats safety narrowly, often by minimizing charge. But unsafe stimulation can take many forms: • physically impossible pulses • unsafe instantaneous currents • activating too many electrodes These are model outputs, so they need to be tested like software systems. #AISafety

Bionic Vision Lab
@bionicvisionlab.org

Our approach borrows an idea from software verification: coverage-guided fuzzing. We systematically mutate inputs and search for stimulation patterns that violate biophysical constraints - uncovering diverse safety violations that conventional testing misses. #Neurotech #MLResearch #AIVerification

Bionic Vision Lab
@bionicvisionlab.org

This work was a collaboration with Mara Downing, Matthew Peng, and Tevfik Bultan from the UCSB Verification Lab, together with @jacobgranley.bsky.social from the Bionic Vision Lab. Read the full paper here: iopscience.iop.org/article/10.1... @ucsb-cs.bsky.social

iopscience.iop.orgFuzzing the brain: automated stress testing for the safety of ML-driven neurostimulationFuzzing the brain: automated stress testing for the safety of ML-driven neurostimulation, Downing, Mara, Peng, Matthew, Granley, Jacob, Beyeler, Michael, Bultan, Tevfik

0 reposts1 like

No replies yet.