[
    {
        "id": "osp-25028",
        "type": "article-journal",
        "title": "AERIAL: Adversarial Evaluation of Robustness in Accuracy-Preserving Low-Precision EEG Decoders",
        "author": [
            {
                "family": "Rehman",
                "given": "Saim"
            },
            {
                "family": "Shafique",
                "given": "Muhammad"
            }
        ],
        "URL": "https://omanscience.com/en/articles/aerial-adversarial-evaluation-of-robustness-in-accuracy-preserving-low-precision-eeg-decoders",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Deployment-oriented compression is attractive for resource-constrained brain--computer interfaces (BCIs), but whether it changes adversarial vulnerability remains unclear. On BCI Competition IV-2a, we compare 32-bit floating-point (FP32) EEGNet and ShallowConvNet models with global magnitude pruning and simulated INT8 post training quantization (PTQ) and quantization-aware training (QAT) across nine subjects and three seeds. Simulation provides differentiable quantize--dequantize models for white-box attacks and gradient analysis, while native TensorRT deployment is used for validation. Accuracy-preserving compression does not improve direct robustness: at $ε=0.005$, EEGNet PGD accuracy remains 22--24\\% across FP32, 50\\% pruning (P50), PTQ, and QAT. However, P50 reduces bidirectional transfer efficiency to 0.963/0.928 (FP32$\\rightarrow$P50/P50$\\rightarrow$FP32), versus 0.994/0.997 for PTQ; the same trend holds for ShallowConvNet. Gradient alignment shows a corresponding separation, while native PTQ agrees with simulated clean/adversarial predictions in 95--98\\% of cases. These results show that direct robustness, adversarial transfer, and deployment efficiency are distinct properties of compressed EEG decoders."
    }
]