An official website of the United States government
Automatic Speech Recognition (ASR) systems convert speech into text and can be placed into two broad categories: traditional and fully end-to-end. Both types have been shown to be vulnerable to adversarial audio examples that sound benign to the human ear but force the ASR to produce malicious transcriptions. Of these attacks, only the "psychoacoustic" attacks can create examples with relatively imperceptible perturbations, as they leverage the knowledge of the human auditory system. Unfortunately, existing psychoacoustic attacks can only be applied against traditional models, and are obsolete against the newer, fully end-to-end ASRs. In this paper, we propose an equalization-based psychoacoustic attack that can exploit both traditional and fully end-to-end ASRs. We successfully demonstrate our attack against real-world ASRs that include DeepSpeech and Wav2Letter. Moreover, we employ a user study to verify that our method creates low audible distortion. Specifically, 80 of the 100 participants voted in favor of all our attack audio samples as less noisier than the existing state-of-the-art attack. Through this, we demonstrate both types of existing ASR pipelines can be exploited with minimum degradation to attack audio quality.
more »
« less
SPARLING: Learning Latent Representations with Extremely Sparse Activations
Real-world processes often contain intermediate state that can be modeled as an extremely sparse tensor. We introduce Sparling, a new kind of informational bottleneck that explicitly models this state by enforcing extreme activation sparsity. We additionally demonstrate that this technique can be used to learn the true intermediate representation with no additional supervision (i.e., from only end-to-end labeled examples), and thus improve the interpretability of the resulting models. On our DigitCircle domain, we are able to get an intermediate state prediction accuracy of 98.84%, even as we only train end-to-end.
more »
« less
- Award ID(s):
- 1918839
- PAR ID:
- 10404352
- Date Published:
- Journal Name:
- arXivorg
- ISSN:
- 2331-8422
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Compositional compiler verification is a difficult problem that focuses on separate compilation of program components with possibly different verified compilers. Logical relations are widely used in proving correctness of program transformations in higher-order languages; however, they do not scale to compositional verification of multi-pass compilers due to their lack of transitivity. The only known technique to apply to compositional verification of multi-pass compilers for higher-order languages is parametric inter-language simulations (PILS), which is however significantly more complicated than traditional proof techniques for compiler correctness. In this paper, we present a novel verification framework forlightweight compositional compiler correctness. We demonstrate that by imposing the additional restriction that program components are compiled by pipelines that go throughthe same sequence of intermediate representations, logical relation proofs can be transitively composed in order to derive an end-to-end compositional specification for multi-pass compiler pipelines. Unlike traditional logical-relation frameworks, our framework supports divergence preservation—even when transformations reduce the number of program steps. We achieve this by parameterizing our logical relations with a pair ofrelational invariants. We apply this technique to verify a multi-pass, optimizing middle-end pipeline for CertiCoq, a compiler from Gallina (Coq’s specification language) to C. The pipeline optimizes and closure-converts an untyped functional intermediate language (ANF or CPS) to a subset of that language without nested functions, which can be easily code-generated to low-level languages. Notably, our pipeline performs more complex closure-allocation optimizations than the state of the art in verified compilation. Using our novel verification framework, we prove an end-to-end theorem for our pipeline that covers both termination and divergence and applies to whole-program and separate compilation, even when different modules are compiled with different optimizations. Our results are mechanized in the Coq proof assistant.more » « less
-
Complex animated transitions may be easier to understand when divided into separate, consecutive stages. However, effective staging requires careful attention to both animation semantics and timing parameters. We present Gemini^2, a system for creating staged animations from a sequence of chart keyframes. Given only a start state and an end state, Gemini^2 can automatically recommend intermediate keyframes for designers to consider. The Gemini^2 recommendation engine leverages Gemini, our prior work, and GraphScape to itemize the given complex change into semantic edit operations and to recombine operations into stages with a guided order for clearly conveying the semantics. To evaluate Gemini^2's recommendations, we conducted a human-subject study in which participants ranked recommended animations from both Gemini^2 and Gemini. We find that Gemini^2's animation recommendation ranking is well aligned with subjects' preferences, and Gemini^2 can recommend favorable animations that Gemini cannot support.more » « less
-
null (Ed.)Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.more » « less
-
Sketch-to-image synthesis method transforms a simple abstract black-and-white sketch into an image. Most sketch-to-image synthesis methods generate an image in an end-to-end manner, leading to generate a non-satisfactory result. The reason is that, in end-to-end models, the models generate images directly from the input sketches. Thus, with very abstract and complicated sketches, the models might struggle in generating naturalistic images due to the simultaneous focus on both factors: overall shape and fine-grained details. In this paper, we propose to divide the problem into subproblems. To this end, an intermediate output, which is a semantic mask map, is first generated from the input sketch via an instance and semantic segmentation. In the instance segmentation stage, the objects' sizes might be modified depending on the surrounding environment and their respective size prior to reflect reality and produce more realistic images. In the semantic seg-mentation stage, a background segmentation is first constructed based on the context of the detected objects. Various natural scenes are implemented for both indoor and outdoor scenes. Following this, a foreground segmentation process is commenced, where each detected object is semantically added into the constructed segmented background. Then, in the next stage, an image-to-image translation model is leveraged to convert the semantic mask map into a colored image. Finally, a post-processing stage is incorporated to further enhance the image result. Extensive experiments demonstrate the superiority of our proposed method over state-of-the-art methods.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
