Harmful content detection models tend to have higher false positive rates for content from marginalized groups. In the context of marginal abuse modeling on Twitter, such disproportionate penalization poses the risk of reduced visibility, where marginalized communities lose the opportunity to voice their opinion on the platform. Current approaches to algorithmic harm mitigation, and bias detection for NLP models are often very ad hoc and subject to human bias. We make two main contributions in this paper. First, we design a novel methodology, which provides a principled approach to detecting and measuring the severity of potential harms associated with a text-based model. Second, we apply our methodology to audit Twitter's English marginal abuse model, which is used for removing amplification eligibility of marginally abusive content. Without utilizing demographic labels or dialect classifiers, we are still able to detect and measure the severity of issues related to the over-penalization of the speech of marginalized communities, such as the use of reclaimed speech, counterspeech, and identity related terms. In order to mitigate the associated harms, we experiment with adding additional true negative examples and find that doing so provides improvements to our fairness metrics without large degradations in model performance.

Although generative adversarial networks (GANs) have shown promise in medical imaging, they have four main limitations that impeded their utility: computational cost, data requirements, reliable evaluation measures, and training complexity. Our work investigates each of these obstacles in a novel application of StyleGAN2-ADA to high-resolution medical imaging datasets. Our dataset is comprised of liver-containing axial slices from non-contrast and contrast-enhanced computed tomography (CT) scans. Additionally, we utilized four public datasets composed of various imaging modalities. We trained a StyleGAN2 network with transfer learning (from the Flickr-Faces-HQ dataset) and data augmentation (horizontal flipping and adaptive discriminator augmentation). The network's generative quality was measured quantitatively with the Fr\'echet Inception Distance (FID) and qualitatively with a visual Turing test given to seven radiologists and radiation oncologists. The StyleGAN2-ADA network achieved a FID of 5.22 ($\pm$ 0.17) on our liver CT dataset. It also set new record FIDs of 10.78, 3.52, 21.17, and 5.39 on the publicly available SLIVER07, ChestX-ray14, ACDC, and Medical Segmentation Decathlon (brain tumors) datasets. In the visual Turing test, the clinicians rated generated images as real 42% of the time, approaching random guessing. Our computational ablation study revealed that transfer learning and data augmentation stabilize training and improve the perceptual quality of the generated images. We observed the FID to be consistent with human perceptual evaluation of medical images. Finally, our work found that StyleGAN2-ADA consistently produces high-quality results without hyperparameter searches or retraining.

An important step towards explaining deep image classifiers lies in the identification of image regions that contribute to individual class scores in the model's output. However, doing this accurately is a difficult task due to the black-box nature of such networks. Most existing approaches find such attributions either using activations and gradients or by repeatedly perturbing the input. We instead address this challenge by training a second deep network, the Explainer, to predict attributions for a pre-trained black-box classifier, the Explanandum. These attributions are provided in the form of masks that only show the classifier-relevant parts of an image, masking out the rest. Our approach produces sharper and more boundary-precise masks when compared to the saliency maps generated by other methods. Moreover, unlike most existing approaches, ours is capable of directly generating very distinct class-specific masks in a single forward pass. This makes the proposed method very efficient during inference. We show that our attributions are superior to established methods both visually and quantitatively with respect to the PASCAL VOC-2007 and Microsoft COCO-2014 datasets.

Recording the dynamics of unscripted human interactions in the wild is challenging due to the delicate trade-offs between several factors: participant privacy, ecological validity, data fidelity, and logistical overheads. To address these, following a 'datasets for the community by the community' ethos, we propose the Conference Living Lab (ConfLab): a new concept for multimodal multisensor data collection of in-the-wild free-standing social conversations. For the first instantiation of ConfLab described here, we organized a real-life professional networking event at a major international conference. Involving 48 conference attendees, the dataset captures a diverse mix of status, acquaintance, and networking motivations. Our capture setup improves upon the data fidelity of prior in-the-wild datasets while retaining privacy sensitivity: 8 videos (1920x1080, 60 fps) from a non-invasive overhead view, and custom wearable sensors with onboard recording of body motion (full 9-axis IMU), privacy-preserving low-frequency audio (1250 Hz), and Bluetooth-based proximity. Additionally, we developed custom solutions for distributed hardware synchronization at acquisition and time-efficient continuous annotation of body keypoints and actions at high sampling rates. Our benchmarks showcase some of the open research tasks related to in-the-wild privacy-preserving social data analysis: keypoints detection from overhead camera views, skeleton-based no-audio speaker detection, and F-formation detection.

And, it was first published on Dataconomy on Dec 21, 2016; I'm reposting here for ease of access. In May 2017 I gave an updated talk; here's the slides & video.] In recent years, AI (artificial intelligence) researchers have finally cracked problems that they've worked on for decades, from Go to human-level speech recognition. A key piece was the ability to gather and learn on mountains of data, which pulled error rates past the success line. In short, big data has transformed AI, to an almost unreasonable level. Blockchain technology could transform AI too, in its own particular ways. Some applications of blockchains to AI are mundane, like audit trails on AI models. Some appear almost unreasonable, like AI that can own itself -- AI DAOs. All of them are opportunities. This article will explore these applications. Before we discuss applications, let's first review what's different about blockchains compared to traditional big-data distributed databases like MongoDB.

Reservoir computing is a machine learning paradigm that transforms the transient dynamics of high-dimensional nonlinear systems for processing time-series data. Although reservoir computing was initially proposed to model information processing in the mammalian cortex, it remains unclear how the non-random network architecture, such as the modular architecture, in the cortex integrates with the biophysics of living neurons to characterize the function of biological neuronal networks (BNNs). Here, we used optogenetics and fluorescent calcium imaging to record the multicellular responses of cultured BNNs and employed the reservoir computing framework to decode their computational capabilities. Micropatterned substrates were used to embed the modular architecture in the BNNs. We first show that modular BNNs can be used to classify static input patterns with a linear decoder and that the modularity of the BNNs positively correlates with the classification accuracy. We then used a timer task to verify that BNNs possess a short-term memory of ~1 s and finally show that this property can be exploited for spoken digit classification. Interestingly, BNN-based reservoirs allow transfer learning, wherein a network trained on one dataset can be used to classify separate datasets of the same category. Such classification was not possible when the input patterns were directly decoded by a linear decoder, suggesting that BNNs act as a generalization filter to improve reservoir computing performance. Our findings pave the way toward a mechanistic understanding of information processing within BNNs and, simultaneously, build future expectations toward the realization of physical reservoir computing systems based on BNNs.

The advancement in wireless communication technologies is becoming more demanding and pervasive. One of the fundamental parameters that limit the efficiency of the network are the security challenges. The communication network is vulnerable to security attacks such as spoofing attacks and signal strength attacks. Intrusion detection signifies a central approach to ensuring the security of the communication network. In this paper, an Intrusion Detection System based on the framework of graph theory is proposed. A Layerwise Graph Theory-Based Intrusion Detection System (LGTBIDS) algorithm is designed to detect the attacked node. The algorithm performs the layer-wise analysis to extract the vulnerable nodes and ultimately the attacked node(s). For each layer, every node is scanned for the possibility of susceptible node(s). The strategy of the IDS is based on the analysis of energy efficiency and secrecy rate. The nodes with the energy efficiency and secrecy rate beyond the range of upper and lower thresholds are detected as the nodes under attack. Further, detected node(s) are transmitted with a random sequence of bits followed by the process of re-authentication. The obtained results validate the better performance, low time computations, and low complexity. Finally, the proposed approach is compared with the conventional solution of intrusion detection.

Network security has become the biggest concern in the area of cyber security because of the exponential growth in computer networks and applications. Intrusion detection plays an important role in the security of information systems or networks devices. The purpose of an intrusion detection system (IDS) is to detect malicious activities and then generate an alarm against these activities. Having a large amount of data is one of the key problems in detecting attacks. Most of the intrusion detection systems use all features of datasets to evaluate the models and result in is, low detection rate, high computational time and uses of many computer resources. For fast attacks detection IDS needs a lightweight data. A feature selection method plays a key role to select best features to achieve maximum accuracy. This research work conduct experiments by considering on two updated attacks datasets, UNSW-NB15 and CICDDoS2019. This work suggests a wrapper based Genetic Algorithm (GA) features selection method with ensemble classifiers. GA select the best feature subsets and achieve high accuracy, detection rate (DR) and low false alarm rate (FAR) compared to existing approaches. This research focuses on multi-class classification. Implements two ensemble methods: stacking and bagging to detect different types of attacks. The results show that GA improve the accuracy significantly with stacking ensemble classifier.

Conventional frequentist learning is known to yield poorly calibrated models that fail to reliably quantify the uncertainty of their decisions. Bayesian learning can improve calibration, but formal guarantees apply only under restrictive assumptions about correct model specification. Conformal prediction (CP) offers a general framework for the design of set predictors with calibration guarantees that hold regardless of the underlying data generation mechanism. However, when training data are limited, CP tends to produce large, and hence uninformative, predicted sets. This paper introduces a novel meta-learning solution that aims at reducing the set prediction size. Unlike prior work, the proposed meta-learning scheme, referred to as meta-XB, (i) builds on cross-validation-based CP, rather than the less efficient validation-based CP; and (ii) preserves formal per-task calibration guarantees, rather than less stringent task-marginal guarantees. Finally, meta-XB is extended to adaptive non-conformal scores, which are shown empirically to further enhance marginal per-input calibration.

Controlling False Discovery Rate (FDR) while leveraging the side information of multiple hypothesis testing is an emerging research topic in modern data science. Existing methods rely on the test-level covariates while ignoring metrics about test-level covariates. This strategy may not be optimal for complex large-scale problems, where indirect relations often exist among test-level covariates and auxiliary metrics or covariates. We incorporate auxiliary covariates among test-level covariates in a deep Black-Box framework controlling FDR (named as NeurT-FDR) which boosts statistical power and controls FDR for multiple-hypothesis testing. Our method parametrizes the test-level covariates as a neural network and adjusts the auxiliary covariates through a regression framework, which enables flexible handling of high-dimensional features as well as efficient end-to-end optimization. We show that NeurT-FDR makes substantially more discoveries in three real datasets compared to competitive baselines.