paper-with-me

Papers

Audio Injection Adversarial Example Attack

2021-06-18 · ICML Workshop AML 2021 7 · Xiaolei Liu, Xingshu Chen, Mingyong Yin, Yulong Wang, Teng Hu, Kangyi Ding

We study the problem of audio adversarial example attacks with sparse perturbations. Compared with image adversarial example attacks, attacking audio is more challenging because the audio structure is more complex and the perturbation is difficult to conceal. To overcome this challenge, we propose an audio injection adversarial example attack, which provides a new sight light to increase the concealment of attack behavior. Experiments demonstrate that the proposed audio injection adversarial example attack can significantly reduce the perturbation proportion and achieve a better attack effect than traditional attack methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

2023-07-19 · Eugene Bagdasaryan, Tsung-Yin Hsieh, Ben Nassi, Vitaly Shmatikov

We demonstrate how images and sounds can be used for indirect prompt and instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding to the prompt and blends it into an imag…

PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection

2023-09-13 · Hanqing Guo, Guangjing Wang, Yuanda Wang, Bocheng Chen 외

In this paper, we propose PhantomSound, a query-efficient black-box attack toward voice assistants. Existing black-box adversarial attacks on voice assistants either apply substitution models or leverage the intermediate…

Adversarial AttackSpeech-to-Text

Weighted-Sampling Audio Adversarial Example Attack

2019-01-26 · Xiaolei Liu, Xiaosong Zhang, Kun Wan, Qingxin Zhu 외

Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essenti…

Adversarial AttackAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Denoising+2

Audio Adversarial Examples: Attacks Using Vocal Masks

2021-02-04 · Kai Yuan Tay, Lynnette Ng, Wei Han Chua, Lucerne Loke 외

We construct audio adversarial examples on automatic Speech-To-Text systems . Given any audio waveform, we produce an another by overlaying an audio vocal mask generated from the original audio. We apply our audio advers…

Adversarial AttackSpeech-to-Text

Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

2018-01-05 · Nicholas Carlini, David Wagner

We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1