# Breaking Speaker Recognition with PaddingBack

arXiv: https://arxiv.org/abs/2308.04179 · HTML: https://mlsanity.com/paper/2308.04179/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Audio jailbreaks and speech backdoors, one of 12 directions in LLM safety and security.
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Placed in

- LLM safety and security / [Audio jailbreaks and speech backdoors](https://mlsanity.com/safety/audio-jailbreaks-and-speech-backdoors/)

## Builds on (most cited first, 13 of 13)

- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses](https://mlsanity.com/paper/2012.10544/) (2020)
- [Backdoor Attack against Speaker Verification](https://mlsanity.com/paper/2010.11607/) (2020)
- [Pushing the limits of raw waveform speaker recognition](https://mlsanity.com/paper/2203.08488/) (2022)
- [Can You Hear It? Backdoor Attacks via Ultrasonic Triggers](https://mlsanity.com/paper/2107.14569/) (2021)
- [Going In Style: Audio Backdoors Through Stylistic Transformations](https://mlsanity.com/paper/2211.03117/) (2022)
- [Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation](https://mlsanity.com/paper/2207.10825/) (2022)
- [BATT: Backdoor Attack with Transformation-based Triggers](https://mlsanity.com/paper/2211.01806/) (2022)
- [Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion](https://mlsanity.com/paper/2306.15875/) (2023)

## Built on by (most cited first, 3 of 3)

- [Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models](https://mlsanity.com/paper/2506.11521/) (2025)
- [Multi-Target Backdoor Attacks Against Speaker Recognition](https://mlsanity.com/paper/2508.08559/) (2025)
- [STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling](https://mlsanity.com/paper/2603.18103/) (2026)

## Abstract (arXiv)

Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent research has shown that speech backdoors can utilize transformations as triggers, similar to image backdoors. However, human ears can easily be aware of these transformations, leading to suspicion. In this paper, we propose PaddingBack, an inaudible backdoor attack that utilizes malicious operations to generate poisoned samples, rendering them indistinguishable from clean ones. Instead of using external perturbations as triggers, we exploit the widely-used speech signal operation, padding, to break speaker recognition systems. Experimental results demonstrate the effectiveness of our method, achieving a significant attack success rate while retaining benign accuracy. Furthermore, PaddingBack demonstrates the ability to resist defense methods and maintain its stealthiness against human perception.