发表机构
İstinye University（伊斯坦耶大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过大规模逐预测审计，揭示脉冲语音分类器在相邻输入变化下存在集中于少数源的脆弱性，并证明源隔离与梯度前缀可恢复并解释此类脆弱性。
AI 中文摘要
聚合准确率无法揭示哪些话语在局部是脆弱的，也无法揭示当标签保持稳定时内部活动如何变化。我们保留了冻结的基于SpikeSCR的分类器在100个验证话语周围725,070个相邻区间、单计数变化上的每一次预测。规范的本地时间步长GPU单例路径达到86.0836%的验证准确率。在均匀选择的邻居下，等源期望准确率从84.00%上升到84.54%，尽管84个初始正确源中有13个允许不利邻居。五个源承载了93.21%的不利移动。基于边际和代理梯度的搜索在固定查询预算下遗漏了稀疏案例；事后梯度前缀在初始正确源的普查中找到了全部13个，覆盖率为73.45%。源匹配的轨迹和干净状态干预区分了内部变化与有害方向及可恢复性。两个计数读出副本具有相似的验证准确率，但在四个源中集中了5.21倍的类别变化差距。受控的查询/键源隔离消除了531个批次顺序标签变化，并在所有9,981个验证分数向量上恢复了逐位顺序不变性。隔离的批次预测在9,980个输入中的9,981个上重现了填充匹配的单例标签。对所有25,820个类别变化邻居的配对CPU/GPU重放给出了99.8993%的标签一致性，并保留了全部13个脆弱源及其固定见证者。完整的源条件映射区分了聚合准确率未解决的脆弱性发生率、集中度、内部变化和执行依赖性。
英文摘要
Aggregate accuracy cannot reveal which utterances are locally vulnerable or how internal activity changes when labels remain stable. We retain every prediction for 725,070 adjacent-bin, one-count changes around 100 validation utterances of a frozen SpikeSCR-based classifier. The canonical native-horizon GPU singleton path reaches 86.0836% validation accuracy. Equal-source expected accuracy under a uniformly chosen neighbor rises from 84.00% to 84.54%, although 13 of 84 initially correct sources admit adverse neighbors. Five sources carry 93.21% of adverse moves. Margin-guided and surrogate-gradient searches miss sparse cases at fixed query budgets; a post hoc gradient prefix finds all 13 at 73.45% of the census of initially correct sources. Source-matched traces and clean-state interventions distinguish internal change from harmful direction and recoverability. Two count-readout replicas have similar validation accuracies but a 5.21-fold class-change gap concentrated in four sources. Controlled query/key source isolation eliminates 531 batch-order label changes and restores bitwise order invariance across all 9,981 validation score vectors. Isolated batch predictions reproduce padding-matched singleton labels on 9,980 of 9,981 inputs. Paired CPU/GPU replay of all 25,820 class-changing neighbors gives 99.8993% label agreement and preserves all 13 vulnerable sources and their fixed witnesses. Complete source-conditioned maps distinguish vulnerability incidence, concentration, internal change, and execution dependence that aggregate accuracy leaves unresolved.
Comments4 figures, 12 tables. Submitted to Neural Networks. Code and data: https://doi.org/10.5281/zenodo.23089436
