A reliable deepfake detector or spoofing countermeasure (CM) should be robust in the face of unpredictable spoofing attacks. To encourage the learning of more generaliseable artefacts, rather than those specific only to known attacks, CMs are usually exposed to a broad variety of different attacks during training. Even so, the performance of deep-learning-based CM solutions are known to vary, sometimes substantially, when they are retrained with different initialisations, hyper-parameters or training data partitions. We show in this paper that the potency of spoofing attacks, also deep-learning-based, can similarly vary according to training conditions, sometimes resulting in substantial degradations to detection performance. Nevertheless, while a RawNet2 CM model is vulnerable when only modest adjustments are made to the attack algorithm, those based upon graph attention networks and self-supervised learning are reassuringly robust. The focus upon training data generated with different attack algorithms might not be sufficient on its own to ensure generaliability; some form of spoofing attack augmentation at the algorithm level can be complementary.

翻译：可靠的深度伪造检测器或欺诈应对措施（CM）应能稳健应对不可预见的欺诈攻击。为鼓励学习更具泛化能力的伪造特征（而非仅针对已知攻击的特异性特征），CM通常在训练中暴露于多种多样欺诈攻击。即便如此，基于深度学习的CM解决方案的性能在采用不同初始化参数、超参数或训练数据划分进行重新训练时，仍会表现出显著差异——有时甚至相当大。本文研究表明，同样基于深度学习的欺诈攻击效能也会随训练条件变化而变化，有时会导致检测性能显著下降。然而，尽管RawNet2 CM模型在攻击算法仅作微小调整时表现脆弱，基于图注意力网络和自监督学习的模型却展现出令人安心的稳健性。仅关注不同攻击算法生成的训练数据可能不足以确保泛化能力；在算法层面实施某种形式的欺诈攻击增强可形成互补。