Automatic speech recognition (ASR) systems are vulnerable to audio adversarial examples that attempt to deceive ASR systems by adding perturbations to benign speech signals. Although an adversarial example and the original benign wave are indistinguishable to humans, the former is transcribed as a malicious target sentence by ASR systems. Several methods have been proposed to generate audio adversarial examples and feed them directly into the ASR system (over-line). Furthermore, many researchers have demonstrated the feasibility of robust physical audio adversarial examples(over-air). To defend against the attacks, several studies have been proposed. However, deploying them in a real-world situation is difficult because of accuracy drop or time overhead. In this paper, we propose a novel method to detect audio adversarial examples by adding noise to the logits before feeding them into the decoder of the ASR. We show that carefully selected noise can significantly impact the transcription results of the audio adversarial examples, whereas it has minimal impact on the transcription results of benign audio waves. Based on this characteristic, we detect audio adversarial examples by comparing the transcription altered by logit noising with its original transcription. The proposed method can be easily applied to ASR systems without any structural changes or additional training. The experimental results show that the proposed method is robust to over-line audio adversarial examples as well as over-air audio adversarial examples compared with state-of-the-art detection methods.
相關內容
Convolutional neural network (CNN) has surpassed traditional methods for medical image classification. However, CNN is vulnerable to adversarial attacks which may lead to disastrous consequences in medical applications. Although adversarial noises are usually generated by attack algorithms, white-noise-induced adversarial samples can exist, and therefore the threats are real. In this study, we propose a novel training method, named IMA, to improve the robust-ness of CNN against adversarial noises. During training, the IMA method increases the margins of training samples in the input space, i.e., moving CNN decision boundaries far away from the training samples to improve robustness. The IMA method is evaluated on publicly available datasets under strong 100-PGD white-box adversarial attacks, and the results show that the proposed method significantly improved CNN classification and segmentation accuracy on noisy data while keeping a high accuracy on clean data. We hope our approach may facilitate the development of robust applications in medical field.
Vulnerability of various machine learning methods to adversarial examples has been recently explored in the literature. Power systems which use these vulnerable methods face a huge threat against adversarial examples. To this end, we first propose a signal-specific method and a universal signal-agnostic method to attack power systems using generated adversarial examples. Black-box attacks based on transferable characteristics and the above two methods are also proposed and evaluated. We then adopt adversarial training to defend systems against adversarial attacks. Experimental analyses demonstrate that our signal-specific attack method provides less perturbation compared to the FGSM (Fast Gradient Sign Method), and our signal-agnostic attack method can generate perturbations fooling most natural signals with high probability. What's more, the attack method based on the universal signal-agnostic algorithm has a higher transfer rate of black-box attacks than the attack method based on the signal-specific algorithm. In addition, the results show that the proposed adversarial training improves robustness of power systems to adversarial examples.
Speaker verification systems have been widely used in smart phones and Internet of things devices to identify a legitimate user. In recent work, it has been shown that adversarial attacks, such as FAKEBOB, can work effectively against speaker verification systems. The goal of this paper is to design a detector that can distinguish an original audio from an audio contaminated by adversarial attacks. Specifically, our designed detector, called MEH-FEST, calculates the minimum energy in high frequencies from the short-time Fourier transform of an audio and uses it as a detection metric. Through both analysis and experiments, we show that our proposed detector is easy to implement, fast to process an input audio, and effective in determining whether an audio is corrupted by FAKEBOB attacks. The experimental results indicate that the detector is extremely effective: with near zero false positive and false negative rates for detecting FAKEBOB attacks in Gaussian mixture model (GMM) and i-vector speaker verification systems. Moreover, adaptive adversarial attacks against our proposed detector and their countermeasures are discussed and studied, showing the game between attackers and defenders.
Automatic Speech Recognition services (ASRs) inherit deep neural networks' vulnerabilities like crafted adversarial examples. Existing methods often suffer from low efficiency because the target phases are added to the entire audio sample, resulting in high demand for computational resources. This paper proposes a novel scheme named FAAG as an iterative optimization-based method to generate targeted adversarial examples quickly. By injecting the noise over the beginning part of the audio, FAAG generates adversarial audio in high quality with a high success rate timely. Specifically, we use audio's logits output to map each character in the transcription to an approximate position of the audio's frame. Thus, an adversarial example can be generated by FAAG in approximately two minutes using CPUs only and around ten seconds with one GPU while maintaining an average success rate over 85%. Specifically, the FAAG method can speed up around 60% compared with the baseline method during the adversarial example generation process. Furthermore, we found that appending benign audio to any suspicious examples can effectively defend against the targeted adversarial attack. We hope that this work paves the way for inventing new adversarial attacks against speech recognition with computational constraints.
It is estimated that around 70 million people worldwide are affected by a speech disorder called stuttering. With recent advances in Automatic Speech Recognition (ASR), voice assistants are increasingly useful in our everyday lives. Many technologies in education, retail, telecommunication and healthcare can now be operated through voice. Unfortunately, these benefits are not accessible for People Who Stutter (PWS). We propose a simple but effective method called 'Detect and Pass' to make modern ASR systems accessible for People Who Stutter in a limited data setting. The algorithm uses a context aware classifier trained on a limited amount of data, to detect acoustic frames that contain stutter. To improve robustness on stuttered speech, this extra information is passed on to the ASR model to be utilized during inference. Our experiments show a reduction of 12.18% to 71.24% in Word Error Rate (WER) across various state of the art ASR systems. Upon varying the threshold of the associated posterior probability of stutter for each stacked frame used in determining low frame rate (LFR) acoustic features, we were able to determine an optimal setting that reduced the WER by 23.93% to 71.67% across different ASR systems.
Outlier detection is an important topic in machine learning and has been used in a wide range of applications. In this paper, we approach outlier detection as a binary-classification issue by sampling potential outliers from a uniform reference distribution. However, due to the sparsity of data in high-dimensional space, a limited number of potential outliers may fail to provide sufficient information to assist the classifier in describing a boundary that can separate outliers from normal data effectively. To address this, we propose a novel Single-Objective Generative Adversarial Active Learning (SO-GAAL) method for outlier detection, which can directly generate informative potential outliers based on the mini-max game between a generator and a discriminator. Moreover, to prevent the generator from falling into the mode collapsing problem, the stop node of training should be determined when SO-GAAL is able to provide sufficient information. But without any prior information, it is extremely difficult for SO-GAAL. Therefore, we expand the network structure of SO-GAAL from a single generator to multiple generators with different objectives (MO-GAAL), which can generate a reasonable reference distribution for the whole dataset. We empirically compare the proposed approach with several state-of-the-art outlier detection methods on both synthetic and real-world datasets. The results show that MO-GAAL outperforms its competitors in the majority of cases, especially for datasets with various cluster types or high irrelevant variable ratio.
Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks. Motivated by this observation, we develop new network architectures that increase adversarial robustness by performing feature denoising. Specifically, our networks contain blocks that denoise the features using non-local means or other filters; the entire networks are trained end-to-end. When combined with adversarial training, our feature denoising networks substantially improve the state-of-the-art in adversarial robustness in both white-box and black-box attack settings. On ImageNet, under 10-iteration PGD white-box attacks where prior art has 27.9% accuracy, our method achieves 55.7%; even under extreme 2000-iteration PGD white-box attacks, our method secures 42.6% accuracy. A network based on our method was ranked first in Competition on Adversarial Attacks and Defenses (CAAD) 2018 --- it achieved 50.6% classification accuracy on a secret, ImageNet-like test dataset against 48 unknown attackers, surpassing the runner-up approach by ~10%. Code and models will be made publicly available.
We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing achieves 0.6% accuracy in the threat model in which the defense is considered. We provide a brief overview of the defense and the threat models/claims considered, as well as a discussion of the methodology and results of our attack, which may offer insights into the reasons underlying the vulnerability of ALP to adversarial attack.
In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been found to be vulnerable to adversarial examples. Adversarial examples are slightly modified inputs that are intentionally designed to cause a misclassification by the model. In the domains of images and speech, the modifications are so small that they are not seen or heard by humans, but nevertheless greatly affect the classification of the model. Deep learning models have been successfully applied to malware detection. In this domain, generating adversarial examples is not straightforward, as small modifications to the bytes of the file could lead to significant changes in its functionality and validity. We introduce a novel loss function for generating adversarial examples specifically tailored for discrete input sets, such as executable bytes. We modify malicious binaries so that they would be detected as benign, while preserving their original functionality, by injecting a small sequence of bytes (payload) in the binary file. We applied this approach to an end-to-end convolutional deep learning malware detection model and show a high rate of detection evasion. Moreover, we show that our generated payload is robust enough to be transferable within different locations of the same file and across different files, and that its entropy is low and similar to that of benign data sections.
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 (at a rate of up to 50 characters per second). We apply our iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end, and show it has a 100% success rate. The feasibility of this attack introduce a new domain to study adversarial examples.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191