Abstract

The Industrial Internet of Things (IIoT) is able to connect machines, analytics and people with IoT smart devices, gateway nodes and edge devices to create powerful intuitivenesses to drive smarter, faster and effective business agreements. IIoT having interconnected machines along with devices can monitor, gather, exchange, and analyze information. Since the communication among the entities in IIoT environment takes place insecurely (for instance, wireless communications and Internet), an intruder can easily tamper with the data. Moreover, physical theft of IoT smart devices provides an intruder to mount impersonation and other attacks. To handle such critical issues, in this work, we design a new private blockchain-envisioned access control scheme for Pervasive Edge Computing (PEC) in IIoT environment, called PBACS-PECIIoT. We consider the private blockchain consisting of the transactions and registration credentials of the entities related to IIoT, because the information is strictly confidential and private. The security of PBACS-PECIIoT is significantly improved due to usage of blockchain as immutability, transparency and decentralization along with protection of various potential attacks. A meticulous comparative analysis exhibits that PBACS-PECIIoT achieves greater security and more functionality features, and requires low costs for communication and computational as compared to other pertinent schemes.

Abstract

This study analysed temperature data in the contiguous Peninsular India from 1991-2020 using the PMiSTIC method, aiming to identify zones with consistent seasonal temperature patterns. Four seasons were considered: DJF, MAM, JJA, and SON, each revealing distinct temperature zones, especially in the high-elevation Himalayan region, with the Western Himalayan and Karakoram zones consistently identified. These regions exhibit Elevation Dependent Warming (EDW) phenomenon, with diurnal temperature range (DTR) being lowest in JJA and highest in MAM. Over the study period, both regions experienced rising temperatures, particularly in DJF and MAM, with the Western Himalayan region showing a slightly higher increase. JJA and SON also displayed increasing trends. Conversely, DJF saw a decreasing temperature trend. DTR exhibited a seasonal cycle, with lowest values in JJA and a gradual increase in SON. Notably, DTR increased during JJA but decreased in DJF. This analysis sheds light on the spatio-temporal variability of temperature patterns in the region, highlighting the influence of elevation on temperature trends throughout the year and the need to incorporate it in climate models for temperature projections

Abstract

Convolutional neural networks (CNN) applied to Mel spectrograms now have a dominant presence in the landscape of speaker recognition systems. Correspondingly, it is also important to evaluate their robustness to adversarial attacks that remains not thoroughly explored for end-to-end trained CNNs for speaker recognition. Our work addresses this gap and investigates variations of the iterative Fast Gradient Sign Method (FGSM) to perform adversarial attacks. We observe that a vanilla iterative FGSM can flip the identity of each speaker sample to that of every other speaker in the LibriSpeech dataset. Furthermore, we propose adversarial attacks specific to Mel spectrogram features by (a) limiting the number of pixels attacked, (b) restricting changes to specific frequency bands, (c) restricting changes to particular time duration, and (d) using a substitute model to craft the adversarial sample. Using thorough qualitative and quantitative results, we demonstrate the fragility and non-intuitive nature of the current CNN-based speaker recognition systems, where the predicted speaker identities can be flipped without any perceptible changes in the audio. The samples are available at "https://advdemo.github.io/speech/"

Abstract

Second language learners often make grammatical mistakes, which can impact the performance of Spoken Language Understanding (SLU) systems. SLU systems consist of two key components: Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU). This work focuses on the effects of grammatical errors which were synthetically generated by manipulating Parts of Speech (POS) tokens on the NLU module. Our analysis comprises three main aspects. Firstly, we assess the impact of grammatical errors on the overall performance of NLU systems, specifically in the domains of Intent Detection and Slot Filling. Secondly, we investigate NLU performance concerning POS tags. Lastly, we utilize an Attention-based NLU model to evaluate the significance of different POS. This study evaluates NLU models on ATIS and SNIPS datasets for Intent Detection and Slot Filling tasks with introduced grammatical errors, leading to a significant performance drop as large as 4.7% for Intent Detection and 5.1% for Slot Filling. However, training on datasets with synthetic errors helps mitigate this drop, and the models are shown to be sensitive to increasing levels of corrupted tokens. Additionally, attention analysis reveals Proper Nouns’ higher weights in determining intent, while specific POS corruption, particularly Auxiliary Verbs and Nouns, is more likely to cause intent misclassification.

Abstract

No Results Found

Abstract

Prior work has shown that pretrained language models often make incorrect predictions for negated inputs. The reason for this behaviour has remained unclear. It has been argued that since language models (LMs) don’t change their predictions about factual propositions under negation, they might not detect negation. We show encoder LMs do detect negation as their representations across layers reliably distinguish negated inputs from non-negated inputs, and when negation leads to contradictions. However, probing experiments show that these LMs indeed don’t use negation when evaluating whether a factual statement is true, even when fine-tuned with the objective of changing outputs on negated sentences (Hosseini et al., 2021). We hypothesize about why pretrained LMs are inconsistent under negation: when the statement could refer to multiple ground entities with conflicting properties, negation may not entail a change in output. This means negation minimal pairs in different training samples can have the same completion in pretraining corpora. We argue pretraining may not provide enough signal to learn the distribution of ground referents a token could have, confusing the LM on how to handle negation.

Abstract

Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving this task exactly is computationally expensive; consequently, recent works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms. In this work, we first outline some necessary criteria for evaluation methods and show no existing evaluation satisfies them all. Then, we design a stronger black-box evaluation method called the Interclass Confusion (IC) test which adversarially manipulates data during training to detect the insufficiency of unlearning procedures. We also propose two analytically motivated baseline methods~(EU-k and CF-k) which outperform several popular inexact unlearning methods. Overall, we demonstrate how adversarial evaluation strategies can help in analyzing various unlearning phenomena which can guide the development of stronger unlearning algorithms.

Abstract

Detecting abusive language in multimodal videos has become a pressing need in ensuring a safe and inclusive online environment. This paper focuses on addressing this challenge through the development of a novel approach for multimodal abusive language detection in Tamil videos and sentiment analysis for Tamil/Malayalam videos. By leveraging state-of-the-art models such as Multiscale Vision Transformers (MViT) for video analysis, OpenL3 for audio analysis, and the bert-basemultilingual-cased model for textual analysis, our proposed framework integrates visual, auditory, and textual features. Through extensive experiments and evaluations, we demonstrate the effectiveness of our model in accurately detecting abusive content and predicting sentiment categories. The limited availability of effective tools for performing these tasks in Dravidian Languages has prompted a new avenue of research in these domains. Keywords: abusive language detection, sentiment analysis, multimodal analysis, video analysis, Dravidian languages.

Abstract

This study addresses the challenge of detecting fake news in Dravidian languages by leveraging Google’s MuRIL (Multilingual Representations for Indian Languages) model. Drawing upon previous research, we investigate the intricacies involved in identifying fake news and explore the potential of transformer-based models for linguistic analysis and contextual understanding. Through supervised learning, we fine-tune the ”muril-base-cased” variant of MuRIL using a carefully curated dataset of labeled comments and posts in Dravidian languages, enabling the model to discern between original and fake news. During the inference phase, the fine-tuned MuRIL model analyzes new textual content, extracting contextual and semantic features to predict the content’s classification. We evaluate the model’s performance using standard metrics, highlighting the effectiveness of MuRIL in detecting fake news in Dravidian languages and contributing to the establishment of a safer digital ecosystem. Keywords: fake news detection, Dravidian languages, MuRIL, transformer-based models, linguistic analysis, contextual understanding.x

Abstract

Abusive comments in online platforms have become a significant concern, necessitating the development of effective detection systems. However, limited work has been done in low resource languages, including Dravidian languages. This paper addresses this gap by focusing on abusive comment detection in a dataset containing Tamil, Tamil-English and TeluguEnglish code-mixed comments. Our methodology involves logistic regression and explores suitablef embeddings to enhance the performance of the detection model. Through rigorous experimentation, we identify the most effective combination of logistic regression and embeddings. The results demonstrate the performance of our proposed model, which contributes to the development of robust abusive comment detection systems in low resource language settings. Keywords: Abusive comment detection, Dravidian languages, logistic regression, embeddings, low resource languages, code-mixed dataset.