Search for: All records

While neuromorphic computing architectures based on Spiking Neural Networks (SNNs) are increasingly gaining interest as a pathway toward bio-plausible machine learning, attention is still focused on computational units like the neuron and synapse. Shifting from this neuro-synaptic perspective, this paper attempts to explore the self-repair role of glial cells, in particular, astrocytes. The work investigates stronger correlations with astrocyte computational neuroscience models to develop macro-models with a higher degree of bio-fidelity that accurately captures the dynamic behavior of the self-repair process. Hardware-software co-design analysis reveals that bio-morphic astrocytic regulation has the potential to self-repair hardware realistic faults in neuromorphic hardware systems with significantly better accuracy and repair convergence for unsupervised learning tasks on the MNIST and F-MNIST datasets. Our implementation source code and trained models are available at https://github.com/NeuroCompLab-psu/Astromorphic_Self_Repair. 

Hydrogen-doped perovskites can be reconfigured by electrical pulses to take on all essential functions necessary for artificial intelligence hardware. 

Abuse in cyber space is a problem requiring immediate attention. Unfortunately, despite advances in Natural Language Processing techniques, there are clear limitations in detecting instances of cyber abuse today. Challenges arising due to different languages that teens communicate with today, and usage of codes along with code mixing and code switching make the design of a comprehensive approach very hard. Existing NLP based approaches for detecting cyber abuse thus suffer from a high degree of false negatives and positives. In this paper, we investigate a new approach to detect instances of cyber abuse. Our approach is motivated by the premise that abusers tend to have unique facial expressions while engaging in an actual abuse episode, and if we are successful, such an approach will be language-agnostic. Here, using only four carefully identified facial features without any language processing, and realistic experiments with 15 users, our system proposed in this paper achieves 98% accuracy for same-user evaluation and up to 74% accuracy for cross-user evaluation in detecting instances of cyber abuse. 

Lying is a (practically) unavoidable component of our day to day interactions with other people, and it includes both oral and textual communications (e.g. text entered via smartphones). Detecting when a person is lying has important applications, especially with the ubiquity of messaging via smart-phones, coupled with rampant increases in (intentional) spread of mis-information today. In this paper, we design a technique to detect whether or not a person's textual inputs when typed via a smartphone indicate lying. To do so, first, we judiciously develop a smartphone based survey that guarantees any participant to provide a mix of true and false responses. While the participant is texting out responses to each question, the smartphone measures readings from its inbuilt inertial sensors, and then computes features like shaking, acceleration, tilt angle, typing speed etc. experienced by it. Subsequently, for each participant (47 in total), we glean the true and false responses using our own experiences with them, and also via informal discussions with each participant. By comparing the responses of each participant, along with the corresponding motion features computed by the smartphone, we implement several machine learning algorithms to detect when a participant is lying, and our accuracy is around 70% in the most stringent leave-one-out evaluation strategy. Later, utilizing findings of our analysis, we develop an architecture for real-time lie detection using smartphones. Yet another user evaluation of our lie detection system yields 84%-90% accuracy in detecting false responses. 

Demand for fast data sharing among smart devices is rapidly increasing. This trend creates challenges towards ensuring essential security for online shared data while maintaining the resource usage at a reasonable level. Existing research studies attempt to leverage compression based encryption for enabling such secure and fast data transmission replacing the traditional resource-heavy encryption schemes. Current compression-based encryption methods mainly focus on error insensitive digital data formats and prone to be vulnerable to different attacks. Therefore, in this paper, we propose and implement a new Huffman compression based Encryption scheme using lightweight dynamic Order Statistic tree (HEliOS) for digital data transmission. The core idea of HEliOS involves around finding a secure encoding method based on a novel notion of Huffman coding, which compresses the given digital data using a small sized "secret" (called as secret_intelligence in our study). HEliOS does this in such a way that, without the possession of the secret intelligence, an attacker will not be able to decode the encoded compressed data. Hence, by encrypting only the small-sized intelligence, we can secure the whole compressed data. Moreover, our rigorous real experimental evaluation for downloading and uploading digital data to and from a personal cloud storage Dropbox server validates efficacy and lightweight nature of HEliOS.