paper-with-me

홈 › Papers

SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech

2025-01-10 · Yuqi Li, Yuanzhong Zheng, Zhongtian Guo, Yaoxuan Wang, Jianjun Yin, Haojun Fei

This paper presents SpecWav-Attack, an adversarial model for detecting speakers in anonymized speech. It leverages Wav2Vec2 for feature extraction and incorporates spectrogram resizing and incremental training for improved performance. Evaluated on librispeech-dev and librispeech-test, SpecWav-Attack outperforms conventional attacks, revealing vulnerabilities in anonymized speech systems and emphasizing the need for stronger defenses, benchmarked against the ICASSP 2025 Attacker Challenge.

📄 PDF Abstract BibTeX arXiv:2505.09616

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Universal Perturbation Attack Against Image Retrieval

2018-12-03 · ICCV 2019 10 · Jie Li, Rongrong Ji, Hong Liu, Xiaopeng Hong 외

Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly foc…

image-classificationImage ClassificationImage RetrievalRetrieval

AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks

2018-05-30 · Chun-Chen Tu, Pai-Shun Ting, Pin-Yu Chen, Sijia Liu 외

Recent studies have shown that adversarial examples in state-of-the-art image classifiers trained by deep neural networks (DNN) can be easily generated when the target model is transparent to an attacker, known as the wh…

Adversarial Robustness

Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition

2023-03-22 · CVPR 2023 1 · Zexin Li, Bangjie Yin, Taiping Yao, Juefeng Guo 외

A hard challenge in developing practical face recognition (FR) attacks is due to the black-box nature of the target FR model, i.e., inaccessible gradient and parameter information to attackers. While recent research took…

Adversarial AttackAttributeFace Recognition

Standard detectors aren't (currently) fooled by physical adversarial stop signs

2017-10-09 · Jiajun Lu, Hussein Sibai, Evan Fabry, David Forsyth

An adversarial example is an example that has been adjusted to produce the wrong label when presented to a system at test time. If adversarial examples existed that could fool a detector, they could be used to (for examp…

Adversarial Attack

From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks

2022-04-14 · Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich

This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural netwo…

Adversarial AttackAdversarial RobustnessBenchmarking