Tootfinder

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
Yukun Chen, Boheng Li, Yu Yuan, Leyi Qi, Yiming Li, Tianwei Zhang, Zhan Qin, Kui Ren
https://arxiv.org/abs/2509.23871

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
Knowledge distillation (KD) is a vital technique for deploying deep neural networks (DNNs) on resource-constrained devices by transferring knowledge from large teacher models to lightweight student models. While teacher models from third-party platforms may undergo security verification (\eg, backdoor detection), we uncover a novel and critical threat: distillation-conditional backdoor attacks (DCBAs). DCBA injects dormant and undetectable backdoors into teacher models, which become activated i…

Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs
Domenico De Cristofaro, Vincenzo Norman Vitale, Alessandro Vietti
https://arxiv.org/abs/2508.17914

Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs
Automatic Speech Recognition has advanced with self-supervised learning, enabling feature extraction directly from raw audio. In Wav2Vec, a CNN first transforms audio into feature vectors before the transformer processes them. This study examines CNN-extracted information for monophthong vowels using the TIMIT corpus. We compare MFCCs, MFCCs with formants, and CNN activations by training SVM classifiers for front-back vowel identification, assessing their classification accuracy to evaluate pho…