# When Certificates Fail: A Unified Safety Framework for Embedded Neural Interface Models

arXiv: https://arxiv.org/abs/2607.06630 · HTML: https://mlsanity.com/paper/2607.06630/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 7 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Parseval Networks: Improving Robustness to Adversarial Examples](https://mlsanity.com/paper/1704.08847/) (2017)
- [Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks](https://mlsanity.com/paper/1906.04893/) (2019)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation](https://mlsanity.com/paper/1705.08475/) (2017)
- [Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach](https://mlsanity.com/paper/1801.10578/) (2018)
- [Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming](https://mlsanity.com/paper/1903.01287/) (2019)
- [MOABB: Trustworthy algorithm benchmarking for BCIs](https://mlsanity.com/paper/1805.06427/) (2018)
- [Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs](https://mlsanity.com/paper/1912.01171/) (2019)
- [Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces](https://mlsanity.com/paper/2212.00727/) (2022)
- [Regulating Next-Generation Implantable Brain-Computer Interfaces: Recommendations for Ethical Development and Implementation](https://mlsanity.com/paper/2506.12540/) (2025)

## Abstract (arXiv)

Formal robustness certificates for embedded neural-interface models can pass while task accuracy collapses: at perturbation budget e=0.25, EEGNet classification accuracy drops by 25.7% under projected-gradient attack while the Lipschitz-style certificate remains valid for all 9 tested subjects. We argue that this gap between mathematical certification and operational safety is one instance of a broader alignment failure in neural interfaces, where training objectives diverge from user welfare. We propose a unified empirical audit framework organized around three such failures: verification insufficiency, in which certificates pass while task behavior degrades; proxy-fidelity divergence, in which task-optimized representations damage neural signal structure (a time-domain auxiliary objective reduces reconstruction MSE by 0.1132 while worsening spectral log-MSE); and latent information exfiltration, in which public-task embeddings retain private attributes (subject identity recoverable at 48.1% versus 6.7% chance). We instantiate the framework on BCI Competition IV 2a and SEED-IV using multiple deep and classical EEG decoders, official session-level validation, null controls, and paired statistical tests. The verification gap persists across EEGNet, CSP+LDA, and FBCSP+LDA, and is therefore architecture-independent. Our results establish that operational safety auditing, not certificate verification alone, is necessary for responsible neural-interface deployment.