Search for: All records

Audio CAPTCHAs are supposed to provide a strong defense for online resources; however, advances in speech-to-text mechanisms have rendered these defenses ineffective. Audio CAPTCHAs cannot simply be abandoned, as they are specifically named by the W3C as important enablers of accessibility. Accordingly, demonstrably more robust audio CAPTCHAs are important to the future of a secure and accessible Web. We look to recent literature on attacks on speech-to-text systems for inspiration for the construction of robust, principle-driven audio defenses. We begin by comparing 20 recent attack papers, classifying and measuring their suitability to serve as the basis of new "robust to transcription" but "easy for humans to understand" CAPTCHAs. After showing that none of these attacks alone are sufficient, we propose a new mechanism that is both comparatively intelligible (evaluated through a user study) and hard to automatically transcribe (i.e., $P({rm transcription}) = 4 times 10^{-5}$). We also demonstrate that our audio samples have a high probability of being detected as CAPTCHAs when given to speech-to-text systems ($P({rm evasion}) = 1.77 times 10^{-4}$). Finally, we show that our method is robust to WaveGuard, a popular mechanism designed to defeat adversarial examples (and enable ASRs to output the original transcript instead of the adversarial one). We show that our method can break WaveGuard with a 99% success rate. In so doing, we not only demonstrate a CAPTCHA that is approximately four orders of magnitude more difficult to crack, but that such systems can be designed based on the insights gained from attack papers using the differences between the ways that humans and computers process audio. 

Mid-infrared Spectroscopic Imaging (MIRSI) provides spatially-resolved molecular specificity by measuring wavelength-dependent mid-infrared absorbance. Infrared microscopes use large numerical aperture objectives to obtain high-resolution images of heterogeneous samples. However, the optical resolution is fundamentally diffraction-limited, and therefore wavelength-dependent. This significantly limits resolution in infrared microscopy, which relies on long wavelengths (2.5 μm to 12.5 μm) for molecular specificity. The resolution is particularly restrictive in biomedical and materials applications, where molecular information is encoded in the fingerprint region (6 μm to 12 μm), limiting the maximum resolving power to between 3 μm and 6 μm. We present an unsupervised curvelet-based image fusion method that overcomes limitations in spatial resolution by augmenting infrared images with label-free visible microscopy. We demonstrate the effectiveness of this approach by fusing images of breast and ovarian tumor biopsies acquired using both infrared and dark-field microscopy. The proposed fusion algorithm generates a hyperspectral dataset that has both high spatial resolution and good molecular contrast. We validate this technique using multiple standard approaches and through comparisons to super-resolved experimentally measured photothermal spectroscopic images. We also propose a novel comparison method based on tissue classification accuracy. 

The axon initial segment (AIS) is a highly regulated subcellular domain required for neuronal firing. Changes in the AIS protein composition and distribution are a form of structural plasticity, which powerfully regulates neuronal activity and may underlie several neuropsychiatric and neurodegenerative disorders. Despite its physiological and pathophysiological relevance, the signaling pathways mediating AIS protein distribution are still poorly studied. Here, we used confocal imaging and whole-cell patch clamp electrophysiology in primary hippocampal neurons to study how AIS protein composition and neuronal firing varied in response to selected kinase inhibitors targeting the AKT/GSK3 pathway, which has previously been shown to phosphorylate AIS proteins. Image-based features representing the cellular pattern distribution of the voltage-gated Na+ (Nav) channel, ankyrin G, βIV spectrin, and the cell-adhesion molecule neurofascin were analyzed, revealing βIV spectrin as the most sensitive AIS protein to AKT/GSK3 pathway inhibition. Within this pathway, inhibition of AKT by triciribine has the greatest effect on βIV spectrin localization to the AIS and its subcellular distribution within neurons, a phenotype that Support Vector Machine classification was able to accurately distinguish from control. Treatment with triciribine also resulted in increased excitability in primary hippocampal neurons. Thus, perturbations to signaling mechanisms within the AKT pathway contribute to changes in βIV spectrin distribution and neuronal firing that may be associated with neuropsychiatric and neurodegenerative disorders. 

Hyperspectral imagery (HSI) has emerged as a highly successful sensing modality for a variety of applications ranging from urban mapping to environmental monitoring and precision agriculture. Despite the efforts by the scientific community, developing reliable algorithms of HSI classification remains a challenging problem especially for high-resolution HSI data where there is often larger intraclass variability combined with scarcity of ground truth data and class imbalance. In recent years, deep neural networks have emerged as a promising strategy for problems of HSI classification where they have shown a remarkable potential for learning joint spectral-spatial features efficiently via backpropagation. In this paper, we propose a deep learning strategy for HSI classification that combines different convolutional neural networks especially designed to efficiently learn joint spatial-spectral features over multiple scales. Our method achieves an overall classification accuracy of 66.73% on the 2018 IEEE GRSS hyperspectral dataset – a high-resolution dataset that includes 20 urban land-cover and land-use classes