# Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy

arXiv: https://arxiv.org/abs/2505.19951 · HTML: https://mlsanity.com/paper/2505.19951/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking](https://mlsanity.com/paper/2303.00332/) (2023)
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022)
- [GeoDA: a geometric framework for black-box adversarial attacks](https://mlsanity.com/paper/2003.06468/) (2020)
- [Universal Adversarial Perturbations for Speech Recognition Systems](https://mlsanity.com/paper/1905.03828/) (2019)
- [RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification](https://mlsanity.com/paper/1904.08104/) (2019)
- [Enabling Fast and Universal Audio Adversarial Attack Using Generative Model](https://mlsanity.com/paper/2004.12261/) (2020)
- [Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Model](https://mlsanity.com/paper/2111.10759/) (2021)
- [Speaker anonymization using orthogonal Householder neural network](https://mlsanity.com/paper/2305.18823/) (2023)
- [VSMask: Defending Against Voice Synthesis Attack via Real-Time Predictive Perturbation](https://mlsanity.com/paper/2305.05736/) (2023)
- [Universal Adversarial Perturbations Generative Network for Speaker Recognition](https://mlsanity.com/paper/2004.03428/) (2020)
- [AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge](https://mlsanity.com/paper/2408.17352/) (2024)
- [Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditions](https://mlsanity.com/paper/2203.14834/) (2022)
- [Certification of Speaker Recognition Models to Additive Perturbations](https://mlsanity.com/paper/2404.18791/) (2024)
- [Traversing the Subspace of Adversarial Patches](https://mlsanity.com/paper/2412.01527/) (2024)

## Abstract (arXiv)

Deep learning voice models are commonly used nowadays, but the safety processing of personal data, such as human identity and speech content, remains suspicious. To prevent malicious user identification, speaker anonymization methods were proposed. Current methods, particularly based on universal adversarial patch (UAP) applications, have drawbacks such as significant degradation of audio quality, decreased speech recognition quality, low transferability across different voice biometrics models, and performance dependence on the input audio length. To mitigate these drawbacks, in this work, we introduce and leverage the novel Exponential Total Variance (TV) loss function and provide experimental evidence that it positively affects UAP strength and imperceptibility. Moreover, we present a novel scalable UAP insertion procedure and demonstrate its uniformly high performance for various audio lengths.