arXiv subjects

Karla Markert

Publications and source records attributed to Karla Markert.

5 recordsLinked to original sources

arXiv2022

Language Dependencies in Adversarial Attacks on Speech Recognition Systems

Automatic speech recognition (ASR) systems are ubiquitously present in our daily devices. They are vulnerable to adversarial attacks, where manipulated input samples fool the ASR system's recognition. While adversarial examples for various English ASR systems have already been analyzed, there exists no inter-language comparative vulnerability analysis. We compare the attackability of a German and an English ASR system, taking Deepspeech as an example. We investigate if one of the language models is more susceptible to manipulations than the other. The results of our experiments suggest statistically significant differences between English and German in terms of computational effort necessary for the successful generation of adversarial examples. This result encourages further research in language-dependent characteristics in the robustness analysis of ASR.

cs.CL↗

arXiv2022

Visualizing Automatic Speech Recognition -- Means for a Better Understanding?

Automatic speech recognition (ASR) is improving ever more at mimicking human speech processing. The functioning of ASR, however, remains to a large extent obfuscated by the complex structure of the deep neural networks (DNNs) they are based on. In this paper, we show how so-called attribution methods, that we import from image recognition and suitably adapt to handle audio data, can help to clarify the working of ASR. Taking DeepSpeech, an end-to-end model for ASR, as a case study, we show how these techniques help to visualize which features of the input are the most influential in determining the output. We focus on three visualization techniques: Layer-wise Relevance Propagation (LRP), Saliency Maps, and Shapley Additive Explanations (SHAP). We compare these methods and discuss potential further applications, such as in the detection of adversarial examples.

cs.LG↗

arXiv2020

Towards Resistant Audio Adversarial Examples

Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech recognition is also susceptible to adversarial attacks. However, reliably bridging the air gap (i.e., making the adversarial examples work when recorded via a microphone) has so far eluded researchers. We find that due to flaws in the generation process, state-of-the-art adversarial example generation methods cause overfitting because of the binning operation in the target speech recognition system (e.g., Mozilla Deepspeech). We devise an approach to mitigate this flaw and find that our method improves generation of adversarial examples with varying offsets. We confirm the significant improvement with our approach by empirical comparison of the edit distance in a realistic over-the-air setting. Our approach states a significant step towards over-the-air attacks. We publish the code and an applicable implementation of our approach.

cs.SD↗

arXiv2019

Identifying Mislabeled Instances in Classification Datasets

A key requirement for supervised machine learning is labeled training data, which is created by annotating unlabeled data with the appropriate class. Because this process can in many cases not be done by machines, labeling needs to be performed by human domain experts. This process tends to be expensive both in time and money, and is prone to errors. Additionally, reviewing an entire labeled dataset manually is often prohibitively costly, so many real world datasets contain mislabeled instances. To address this issue, we present in this paper a non-parametric end-to-end pipeline to find mislabeled instances in numerical, image and natural language datasets. We evaluate our system quantitatively by adding a small number of label noise to 29 datasets, and show that we find mislabeled instances with an average precision of more than 0.84 when reviewing our system's top 1\% recommendation. We then apply our system to publicly available datasets and find mislabeled instances in CIFAR-100, Fashion-MNIST, and others. Finally, we publish the code and an applicable implementation of our approach.

cs.LG↗

arXiv2018

Detecting Anisotropy in Fingerprint Growth

From infancy to adulthood, human growth is anisotropic, much more along the proximal-distal axis (height) than along the medial-lateral axis (width), particularly at extremities. Detecting and modeling the rate of anisotropy in fingerprint growth, and possibly other growth patterns as well, facilitates the use of children's fingerprints for long-term biometric identification. Using standard fingerprint scanners, anisotropic growth is highly overshadowed by the varying distortions created by each imprint, and it seems that this difficulty has hampered to date the development of suitable methods, detecting anisotropy, let alone, designing models. We provide a tool chain to statistically detect, with a given confidence, anisotropic growth in fingerprints and its preferred axis, where we only require a standard fingerprint scanner and a minutiae matcher. We build on a perturbation model, a new Procrustes-type algorithm, use and develop several parametric and non-parametric tests for different hypotheses, in particular for neighborhood hypotheses to detect the axis of anisotropy, where the latter tests are tunable to measurement accuracy. Taking into account realistic distortions caused by pressing fingers on scanners, our simulations based on real data indicate that, for example, already in rather small samples (56 matches) we can significantly detect proximal-distal growth if it exceeds medial-lateral growth by only around 5 percent. Our method is well applicable to future datasets of children fingerprint time series and we provide an implementation of our algorithms and tests with matched minutiae pattern data.

stat.AP↗