paper-with-me

홈 › Papers

SlothSpeech: Denial-of-service Attack Against Speech Recognition Models

2023-06-01 · Mirazul Haque, Rutvij Shah, Simin Chen, Berrak Şişman, Cong Liu, Wei Yang

Deep Learning (DL) models have been popular nowadays to execute different speech-related tasks, including automatic speech recognition (ASR). As ASR is being used in different real-time scenarios, it is important that the ASR model remains efficient against minor perturbations to the input. Hence, evaluating efficiency robustness of the ASR model is the need of the hour. We show that popular ASR models like Speech2Text model and Whisper model have dynamic computation based on different inputs, causing dynamic efficiency. In this work, we propose SlothSpeech, a denial-of-service attack against ASR models, which exploits the dynamic behaviour of the model. SlothSpeech uses the probability distribution of the output text tokens to generate perturbations to the audio such that efficiency of the ASR model is decreased. We find that SlothSpeech generated inputs can increase the latency up to 40X times the latency induced by benign input.

📄 PDF Abstract BibTeX arXiv:2306.00794

Code (1)

0xrutvij/slothspeech 공식 구현 pytorch

Tasks

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

Similar Papers 제목 키워드 기반

Denial-of-Service Poisoning Attacks against Large Language Models

2024-10-14 · Kuofeng Gao, Tianyu Pang, Chao Du, Yong Yang 외

Recent studies have shown that LLMs are vulnerable to denial-of-service (DoS) attacks, where adversarial inputs like spelling errors or non-semantic prompts trigger endless outputs without generating an [EOS] token. Thes…

16kSpeech-to-Text

CoAP-DoS: An IoT Network Intrusion Dataset

2022-06-29 · Jared Mathews, Prosenjit Chatterjee, Shankar Banik

The need for secure Internet of Things (IoT) devices is growing as IoT devices are becoming more integrated into vital networks. Many systems rely on these devices to remain available and provide reliable service. Denial…

BIG-bench Machine LearningIntrusion DetectionNetwork Intrusion Detection

AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition

2023-09-20 · Mohamad Fakih, Rouwaida Kanj, Fadi Kurdahi, Mohammed E. Fouda

Automatic Speech Recognition systems have been shown to be vulnerable to adversarial attacks that manipulate the command executed on the device. Recent research has focused on exploring methods to create such attacks, ho…

Automatic Speech Recognitionspeech-recognitionSpeech Recognition

Defending Against Adversarial Denial-of-Service Data Poisoning Attacks

2021-04-14 · Nicolas M. Müller, Simon Roschmann, Konstantin Böttinger

Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples a…

Anomaly DetectionBIG-bench Machine LearningClusteringData Poisoning

Adversarial Attacks and Defenses for Speech Recognition Systems

2021-03-31 · Piotr Żelasko, Sonal Joshi, Yiwen Shao, Jesus Villalba 외

The ubiquitous presence of machine learning systems in our lives necessitates research into their vulnerabilities and appropriate countermeasures. In particular, we investigate the effectiveness of adversarial attacks an…

Adversarial RobustnessAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoder+2