https://github.com/imcaspar/audio-adv-papers
A curated list of awesome audio adversarial examples papers(with code & demo if available).
https://github.com/imcaspar/audio-adv-papers
adversarial-attacks adversarial-examples
Last synced: 4 months ago
JSON representation
A curated list of awesome audio adversarial examples papers(with code & demo if available).
- Host: GitHub
- URL: https://github.com/imcaspar/audio-adv-papers
- Owner: imcaspar
- License: cc0-1.0
- Created: 2020-04-26T06:33:44.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2020-04-26T09:25:02.000Z (about 6 years ago)
- Last Synced: 2025-04-22T19:05:50.896Z (about 1 year ago)
- Topics: adversarial-attacks, adversarial-examples
- Homepage:
- Size: 4.88 KB
- Stars: 32
- Watchers: 1
- Forks: 5
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Audio Adversarial Examples Paper List
A curated list of awesome audio adversarial examples papers(with code & demo if available), inspired by [awesome-adversarial-machine-learning](https://github.com/yenchenlin/awesome-adversarial-machine-learning).
## Papers
| Title | Authors | Publication | Year | Code | Demo | Presentation |
| ------------------------------------------------------------ | ------------------- | --------------- | ---- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| [Inaudible Voice Commands](http://arxiv.org/abs/1708.07238) | L. Song et al. | CCS | 2017 | [☑️](https://github.com/lwsong/inaudible-voice-commands) | [☑️](https://www.youtube.com/watch?v=wF-DuVkQNQQ) | |
| [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](http://arxiv.org/abs/1801.01944) | N. Carlini et al. | DLS | 2018 | [☑️](https://github.com/carlini/audio_adversarial_examples) | [☑️](https://nicholas.carlini.com/code/audio_adversarial_examples/) | [☑️](https://www.youtube.com/watch?v=Ho5jLKfoKSA) |
| [ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio](http://arxiv.org/abs/1805.11852) | N. Das et al. | ECML-PKDD | 2018 | | [☑️](https://youtu.be/0W2BKMwSfVQ) | |
| [CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition](https://www.usenix.org/conference/usenixsecurity18/presentation/yuan-xuejing) | X. Yuan et al. | USENIX Security | 2018 | | | [☑️](https://www.usenix.org/conference/usenixsecurity18/presentation/yuan-xuejing) |
| [Adversarial Black-Box Attacks for Automatic Speech Recognition Systems Using Multi-Objective Genetic Optimization](http://arxiv.org/abs/1811.01312) | S. Khare et al. | Interspeech | 2019 | | | |
| [Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding](http://arxiv.org/abs/1808.05665) | L. Schönherr et al. | NDSS | 2019 | [☑️](https://github.com/rub-ksv/adversarialattacks) | [☑️](https://adversarial-attacks.net/) | |
| [Robust Audio Adversarial Example for a Physical Attack](http://arxiv.org/abs/1810.11793) | H. Yakura et al. | IJCAI | 2019 | [☑️](https://github.com/hiromu/robust_audio_ae) | [☑️](https://yumetaro.info/projects/audio-ae/) | |
| [Characterizing Audio Adversarial Examples Using Temporal Dependency](http://arxiv.org/abs/1809.10875) | Z. Yang et al. | ICLR | 2019 | [☑️](https://github.com/AI-secure/Characterizing-Audio-Adversarial-Examples-using-Temporal-Dependency) | [☑️](https://www.ibm.com/blogs/research/2019/05/audio-adversarial-attacks/) | |
| [Practical Hidden Voice Attacks against Speech and Speaker Recognition Systems](http://arxiv.org/abs/1904.05734) | H. Abdullah et al. | NDSS | 2019 | | [☑️](https://sites.google.com/view/transcript-evasion) | |
| [Hear ‘No Evil’, See ‘Kenansville’: Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systems](http://arxiv.org/abs/1910.05262) | H. Abdullah et al. | arXiv | 2019 | | [☑️](https://sites.google.com/view/transcript-evasion) | |
| [SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systems](http://arxiv.org/abs/1901.07846) | T. Du et al. | NDSS | 2019 | | | |
| [Towards Weighted-Sampling Audio Adversarial Example Attack](http://arxiv.org/abs/1901.10300) | X. Liu et al. | AAAI | 2019 | | [☑️](https://sites.google.com/view/audio-adversarial-examples) | |
| [Universal Adversarial Perturbations for Speech Recognition Systems](http://arxiv.org/abs/1905.03828) | P. Neekharaet al. | Interspeech | 2019 | | [☑️](https://universal-audio-perturbation.herokuapp.com/index.html) | |
| [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](http://arxiv.org/abs/1903.10346) | Y. Qin et al. | ICML | 2019 | [☑️](https://github.com/tensorflow/cleverhans/tree/master/examples/adversarial_asr) | [☑️](http://cseweb.ucsd.edu/~yaq007/imperceptible-robust-adv.html) | |
| [Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems](http://arxiv.org/abs/1908.01551) | L. Schönherr et al. | arXiv | 2019 | | [☑️](http://ota-adversarial-examples.selfip.org/) | |
| [Devil’s Whisper: A General Approach for Physical Adversarial Attacks against Commercial Black-box Speech Recognition Devices](https://www.usenix.org/system/files/sec20summer_chen-yuxuan_prepub.pdf) | Y. Chen et al. | USENIX Security | 2020 | [☑️](https://github.com/RiskySignal/Devil-Whisper-Attack) | [☑️](https://sites.google.com/view/devil-whisper) | |