Arun Balaji Buduru

Orchid Chetia Phukan, Arun Balaji Buduru, Rajesh Sharma

Pre-trained models (PTMs) have shown great promise in the speech and audio domain. Embeddings leveraged from these models serve as inputs for learning algorithms with applications in various downstream tasks. One such crucial task is Speech Emotion Recognition (SER) which has a wide range of applications, including dynamic analysis of customer calls, mental health assessment, and personalized language learning. PTM embeddings have helped advance SER, however, a comprehensive comparison of these PTM embeddings that consider multiple facets such as embedding model architecture, data used for pre-training, and the pre-training procedure being followed is missing. A thorough comparison of PTM embeddings will aid in the faster and more efficient development of models and enable their deployment in real-world scenarios. In this work, we exploit this research gap and perform a comparative analysis of embeddings extracted from eight speech and audio PTMs (wav2vec 2.0, data2vec, wavLM, UniSpeech-SAT, wav2clip, YAMNet, x-vector, ECAPA). We perform an extensive empirical analysis with four speech emotion datasets (CREMA-D, TESS, SAVEE, Emo-DB) by training three algorithms (XGBoost, Random Forest, FCN) on the derived embeddings. The results of our study indicate that the best performance is achieved by algorithms trained on embeddings derived from PTMs trained for speaker recognition followed by wav2clip and UniSpeech-SAT. This can relay that the top performance by embeddings from speaker recognition PTMs is most likely due to the model taking up information about numerous speech features such as tone, accent, pitch, and so on during its speaker recognition training. Insights from this work will assist future studies in their selection of embeddings for applications related to SER.

Neha Kumaru, Garvit Gupta, Shreyas Mongia et al.

The use of Social media to share content is on a constant rise. One of the capsize effect of information sharing on Social media includes the spread of sensitive information on the public domain. With the digital gadget market becoming highly competitive and ever-evolving, the trend of an increasing number of sensitive posts leaking information on devices in social media is observed. Many web-blogs on digital gadget market have mushroomed recently, making the problem of information leak all pervasive. Credible leaks on specifics of an upcoming device can cause a lot of financial damage to the respective organization. Hence, it is crucial to assess the credibility of the platforms that continuously post about a smartphone or digital gadget leaks. In this work, we analyze the headlines of leak web-blog posts and their corresponding official press-release. We first collect 54, 495 leak and press-release headlines for different smartphones. We train our custom NER model to capture the evolving smartphone names with an accuracy of 82.14% on manually annotated results. We further propose a credibility score metric for the web-blog, based on the number of falsified and authentic smartphone leak posts.

Nitin Choudhury, Nikhil Kumar, Aditya Kumar Sinha et al.

Wide exploration on robocall surveillance research is hindered due to limited access to public datasets, due to privacy concerns. In this work, we first curate Robo-SAr, a synthetic robocall dataset designed for robocall surveillance research. Robo-SAr comprises of ~200 unwanted and ~1200 legitimate synthetic robocall samples across three realistic adversarial axes: psycholinguistics-manipulated transcripts, emotion-eliciting speech, and cloned voices. We further propose RoboKA, a Kolmogorov-Arnold Network (KAN)-based multimodal fusion framework designed to model structured nonlinear interactions between acoustic and linguistic cues that characterize diverse adversarial robocall strategies. RoboKA first leverages cross-modal contrastive learning to align latent modality representations and feeds the resulting embeddings to a KAN-projection head for final classification. We benchmark RoboKA against strong unimodal and multimodal baselines in both in-domain and out-of-domain setups, finding RoboKA to surpass all baselines in terms of recall and F1-score.

Orchid Chetia Phukan, Sarthak Jain, Swarup Ranjan Behera et al.

In this study, for the first time, we extensively investigate whether music foundation models (MFMs) or speech foundation models (SFMs) work better for singing voice deepfake detection (SVDD), which has recently attracted attention in the research community. For this, we perform a comprehensive comparative study of state-of-the-art (SOTA) MFMs (MERT variants and music2vec) and SFMs (pre-trained for general speech representation learning as well as speaker recognition). We show that speaker recognition SFM representations perform the best amongst all the foundation models (FMs), and this performance can be attributed to its higher efficacy in capturing the pitch, tone, intensity, etc, characteristics present in singing voices. To our end, we also explore the fusion of FMs for exploiting their complementary behavior for improved SVDD, and we propose a novel framework, FIONA for the same. With FIONA, through the synchronization of x-vector (speaker recognition SFM) and MERT-v1-330M (MFM), we report the best performance with the lowest Equal Error Rate (EER) of 13.74 %, beating all the individual FMs as well as baseline FM fusions and achieving SOTA results.

Nitin Choudhury, Bikrant Bikram Pratap Maurya, Bhavinkumar Vinodbhai Kuwar et al.

Large Language Models (LLMs) trained on massive code corpora are now increasingly capable of generating code that is hard to distinguish from human-written code. This raises practical concerns, including security vulnerabilities and licensing ambiguity, and also motivates a forensic question: 'Who (or which LLM) wrote this piece of code?' We present GoCoMA, a multimodal framework that models an extrinsic hierarchy between (i) code stylometry, capturing higher-level structural and stylistic signatures, and (ii) image representations of binary pre-executable artifacts (BPEA), capturing lower-level, execution-oriented byte semantics shaped by compilation and toolchains. GoCoMA projects modality embeddings into a hyperbolic Poincaré ball, fuses them via a geodesic-cosine similarity-based cross-modal attention (GCSA) fusion mechanism, and back-projects the fused representation to Euclidean space for final LLM-source attribution. Experiments on two open-source benchmarks (CoDET-M4 and LLMAuthorBench) show that GoCoMA consistently outperforms unimodal and Euclidean multimodal baselines under identical evaluation protocols.

Yashwardhan Chaudhuri, Ankit Kumar, Arun Balaji Buduru et al.

Crowd counting is gaining societal relevance, particularly in domains of Urban Planning, Crowd Management, and Public Safety. This paper introduces Fourier-guided attention (FGA), a novel attention mechanism for crowd count estimation designed to address the inefficient full-scale global pattern capture in existing works on convolution-based attention networks. FGA efficiently captures multi-scale information, including full-scale global patterns, by utilizing Fast-Fourier Transformations (FFT) along with spatial attention for global features and convolutions with channel-wise attention for semi-global and local features. The architecture of FGA involves a dual-path approach: (1) a path for processing full-scale global features through FFT, allowing for efficient extraction of information in the frequency domain, and (2) a path for processing remaining feature maps for semi-global and local features using traditional convolutions and channel-wise attention. This dual-path architecture enables FGA to seamlessly integrate frequency and spatial information, enhancing its ability to capture diverse crowd patterns. We apply FGA in the last layers of two popular crowd-counting works, CSRNet and CANNet, to evaluate the module's performance on benchmark datasets such as ShanghaiTech-A, ShanghaiTech-B, UCF-CC-50, and JHU++ crowd. The experiments demonstrate a notable improvement across all datasets based on Mean-Squared-Error (MSE) and Mean-Absolute-Error (MAE) metrics, showing comparable performance to recent state-of-the-art methods. Additionally, we illustrate the interpretability using qualitative analysis, leveraging Grad-CAM heatmaps, to show the effectiveness of FGA in capturing crowd patterns.

Bikrant Bikram Pratap Maurya, Nitin Choudhury, Daksh Agarwal et al.

Acoustic side-channel attacks (ASCA) on keyboards pose a significant security risk, as keystrokes can be inferred from typing acoustics, revealing sensitive information. Prior ASCA studies are limited by small-scale datasets with restricted diversity in users, keyboards, and environments, constraining analysis across devices, microphones, and noise conditions. We introduce HEAR, a dataset designed to study ASCA along three axes: keyboard generalization, noise adaptation, and user bias. HEAR contains recordings from 53 participants using 37 laptop keyboards, collected in three realistic settings: (1) external microphone capture, (2) device microphone capture without network noise, and (3) VoIP-based streaming capture. This enables controlled evaluation across users, keyboards, and environments. On HEAR, we establish an ASCA benchmark spanning conventional features and pre-trained representations from raw audio and spectrograms in unimodal and multimodal settings. We propose DECKER, a domain-invariant keystroke inference framework with four stages: (1) Keyboard Signature Normalization to reduce device coloration, (2) domain-adversarial disentanglement to suppress keyboard identity, (3) supervised cross-keyboard contrastive alignment to enforce key consistency, and (4) Acoustic Style Randomization to synthesize unseen keyboard responses. We further explore sentence-level inference using an LLM-based post-processing layer to refine keystroke sequences via linguistic context. Results on HEAR show DECKER improves keystroke identification over strong baselines, particularly in cross-keyboard and cross-user settings, with further gains from language-model rectification. These findings highlight that ASCA remains effective across diverse users, devices, and noisy environments, underscoring its practical security risk.

Yashwardhan Chaudhuri, Ankit Kumar, Orchid Chetia Phukan et al.

Crowd counting finds direct applications in real-world situations, making computational efficiency and performance crucial. However, most of the previous methods rely on a heavy backbone and a complex downstream architecture that restricts the deployment. To address this challenge and enhance the versatility of crowd-counting models, we introduce two lightweight models. These models maintain the same downstream architecture while incorporating two distinct backbones: MobileNet and MobileViT. We leverage Adjacent Feature Fusion to extract diverse scale features from a Pre-Trained Model (PTM) and subsequently combine these features seamlessly. This approach empowers our models to achieve improved performance while maintaining a compact and efficient design. With the comparison of our proposed models with previously available state-of-the-art (SOTA) methods on ShanghaiTech-A ShanghaiTech-B and UCF-CC-50 dataset, it achieves comparable results while being the most computationally efficient model. Finally, we present a comparative study, an extensive ablation study, along with pruning to show the effectiveness of our models.

Orchid Chetia Phukan, Gautam Siddharth Kashyap, Arun Balaji Buduru et al.

Availability of representations from pre-trained models (PTMs) have facilitated substantial progress in speech emotion recognition (SER). Particularly, representations from PTM trained for paralinguistic speech processing have shown state-of-the-art (SOTA) performance for SER. However, such paralinguistic PTM representations haven't been evaluated for SER in linguistic environments other than English. Also, paralinguistic PTM representations haven't been investigated in benchmarks such as SUPERB, EMO-SUPERB, ML-SUPERB for SER. This makes it difficult to access the efficacy of paralinguistic PTM representations for SER in multiple languages. To fill this gap, we perform a comprehensive comparative study of five SOTA PTM representations. Our results shows that paralinguistic PTM (TRILLsson) representations performs the best and this performance can be attributed to its effectiveness in capturing pitch, tone and other speech characteristics more effectively than other PTM representations.

Orchid Chetia Phukan, Mohd Mujtaba Akhtar, Girish et al.

As video-sharing platforms have grown over the past decade, child viewership has surged, increasing the need for precise detection of harmful content like violence or explicit scenes. Malicious users exploit moderation systems by embedding unsafe content in minimal frames to evade detection. While prior research has focused on visual cues and advanced such fine-grained detection, audio features remain underexplored. In this study, we embed audio cues with visual for fine-grained child harmful content detection and introduce SNIFR, a novel framework for effective alignment. SNIFR employs a transformer encoder for intra-modality interaction, followed by a cascaded cross-transformer for inter-modality alignment. Our approach achieves superior performance over unimodal and baseline fusion methods, setting a new state-of-the-art.

Orchid Chetia Phukan, Priyabrata Mallick, Swarup Ranjan Behera et al.

In this paper, we work towards extending Audio-Visual Question Answering (AVQA) to multilingual settings. Existing AVQA research has predominantly revolved around English and replicating it for addressing AVQA in other languages requires a substantial allocation of resources. As a scalable solution, we leverage machine translation and present two multilingual AVQA datasets for eight languages created from existing benchmark AVQA datasets. This prevents extra human annotation efforts of collecting questions and answers manually. To this end, we propose, MERA framework, by leveraging state-of-the-art (SOTA) video, audio, and textual foundation models for AVQA in multiple languages. We introduce a suite of models namely MERA-L, MERA-C, MERA-T with varied model architectures to benchmark the proposed datasets. We believe our work will open new research directions and act as a reference benchmark for future works in multilingual AVQA.

Satyadwyoom Kumar, Saurabh Gupta, Arun Balaji Buduru

Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. Most of these adversarial attack strategies assume that the adversary has access to the training data, the model parameters, and the input during deployment, hence, focus on perturbing the pixel level information present in the input image. Adversarial Patches were introduced to the community which helped in bringing out the vulnerability of deep learning models in a much more pragmatic manner but here the attacker has a white-box access to the model parameters. Recently, there has been an attempt to develop these adversarial attacks using black-box techniques. However, certain assumptions such as availability large training data is not valid for a real-life scenarios. In a real-life scenario, the attacker can only assume the type of model architecture used from a select list of state-of-the-art architectures while having access to only a subset of input dataset. Hence, we propose an black-box adversarial attack strategy that produces adversarial patches which can be applied anywhere in the input image to perform an adversarial attack.

Mohit Chandra, Manvith Reddy, Shradha Sehgal et al.

The COVID-19 pandemic has disrupted people's lives driving them to act in fear, anxiety, and anger, leading to worldwide racist events in the physical world and online social networks. Though there are works focusing on Sinophobia during the COVID-19 pandemic, less attention has been given to the recent surge in Islamophobia. A large number of positive cases arising out of the religious Tablighi Jamaat gathering has driven people towards forming anti-Muslim communities around hashtags like #coronajihad, #tablighijamaatvirus on Twitter. In addition to the online spaces, the rise in Islamophobia has also resulted in increased hate crimes in the real world. Hence, an investigation is required to create interventions. To the best of our knowledge, we present the first large-scale quantitative study linking Islamophobia with COVID-19. In this paper, we present CoronaBias dataset which focuses on anti-Muslim hate spanning four months, with over 410,990 tweets from 244,229 unique users. We use this dataset to perform longitudinal analysis. We find the relation between the trend on Twitter with the offline events that happened over time, measure the qualitative changes in the context associated with the Muslim community, and perform macro and micro topic analysis to find prevalent topics. We also explore the nature of the content, focusing on the toxicity of the URLs shared within the tweets present in the CoronaBias dataset. Apart from the content-based analysis, we focus on user analysis, revealing that the portrayal of religion as a symbol of patriotism played a crucial role in deciding how the Muslim community was perceived during the pandemic. Through these experiments, we reveal the existence of anti-Muslim rhetoric around COVID-19 in the Indian sub-continent.

Saurabh Gupta, Siddhant Bhambri, Karan Dhingra et al.

Smart homes require every device inside them to be connected with each other at all times, which leads to a lot of power wastage on a daily basis. As the devices inside a smart home increase, it becomes difficult for the user to control or operate every individual device optimally. Therefore, users generally rely on power management systems for such optimization but often are not satisfied with the results. In this paper, we present a novel multi-objective reinforcement learning framework with two-fold objectives of minimizing power consumption and maximizing user satisfaction. The framework explores the trade-off between the two objectives and converges to a better power management policy when both objectives are considered while finding an optimal policy. We experiment on real-world smart home data, and show that the multi-objective approaches: i) establish trade-off between the two objectives, ii) achieve better combined user satisfaction and power consumption than single-objective approaches. We also show that the devices that are used regularly and have several fluctuations in device modes at regular intervals should be targeted for optimization, and the experiments on data from other smart homes fetch similar results, hence ensuring transfer-ability of the proposed framework.

Saurabh Gupta, Arun Balaji Buduru, Ponnurangam Kumaraguru

Generative Adversarial Network (GAN) and its variants have shown promising results in generating synthetic data. However, the issues with GANs are: (i) the learning happens around the training samples and the model often ends up remembering them, consequently, compromising the privacy of individual samples - this becomes a major concern when GANs are applied to training data including personally identifiable information, (ii) the randomness in generated data - there is no control over the specificity of generated samples. To address these issues, we propose imdpGAN - an information maximizing differentially private Generative Adversarial Network. It is an end-to-end framework that simultaneously achieves privacy protection and learns latent representations. With experiments on MNIST dataset, we show that imdpGAN preserves the privacy of the individual data point, and learns latent codes to control the specificity of the generated samples. We perform binary classification on digit pairs to show the utility versus privacy trade-off. The classification accuracy decreases as we increase privacy levels in the framework. We also experimentally show that the training process of imdpGAN is stable but experience a 10-fold time increase as compared with other GAN frameworks. Finally, we extend imdpGAN framework to CelebA dataset to show how the privacy and learned representations can be used to control the specificity of the output.

Mudit Verma, Arun Balaji Buduru

Due to a drastic improvement in the quality of internet services worldwide, there is an explosion of multilingual content generation and consumption. This is especially prevalent in countries with large multilingual audience, who are increasingly consuming media outside their linguistic familiarity/preference. Hence, there is an increasing need for real-time and fine-grained content analysis services, including language identification, content transcription, and analysis. Accurate and fine-grained spoken language detection is an essential first step for all the subsequent content analysis algorithms. Current techniques in spoken language detection may lack on one of these fronts: accuracy, fine-grained detection, data requirements, manual effort in data collection \& pre-processing. Hence in this work, a real-time language detection approach to detect spoken language from 5 seconds' audio clips with an accuracy of 91.8\% is presented with exiguous data requirements and minimal pre-processing. Novel architectures for Capsule Networks is proposed which operates on spectrogram images of the provided audio snippets. We use previous approaches based on Recurrent Neural Networks and iVectors to present the results. Finally we show a ``Non-Class'' analysis to further stress on why CapsNet architecture works for LID task.

Mudit Verma, Siddhant Bhambri, Saurabh Gupta et al.

Rapid advancements in the Internet of Things (IoT) have facilitated more efficient deployment of smart environment solutions for specific user requirement. With the increase in the number of IoT devices, it has become difficult for the user to control or operate every individual smart device into achieving some desired goal like optimized power consumption, scheduled appliance running time, etc. Furthermore, existing solutions to automatically adapt the IoT devices are not capable enough to incorporate the user behavior. This paper presents a novel approach to accurately configure IoT devices while achieving the twin objectives of energy optimization along with conforming to user preferences. Our work comprises of unsupervised clustering of devices' data to find the states of operation for each device, followed by probabilistically analyzing user behavior to determine their preferred states. Eventually, we deploy an online reinforcement learning (RL) agent to find the best device settings automatically. Results for three different smart homes' data-sets show the effectiveness of our methodology. To the best of our knowledge, this is the first time that a practical approach has been adopted to achieve the above mentioned objectives without any human interaction within the system.

Siddhant Bhambri, Sumanyu Muku, Avinash Tulasi et al.

Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life scenarios, pose a severe challenge to their applicability, pushing research into the direction which aims to enhance the robustness of these models. After the introduction of these perturbations by Szegedy et al. [1], significant amount of research has focused on the reliability of such models, primarily in two aspects - white-box, where the adversary has access to the targeted model and related parameters; and the black-box, which resembles a real-life scenario with the adversary having almost no knowledge of the model to be attacked. To provide a comprehensive security cover, it is essential to identify, study, and build defenses against such attacks. Hence, in this paper, we propose to present a comprehensive comparative study of various black-box adversarial attacks and defense techniques.

Kumari Neha, Shashank Srikanth, Sonali Singhal et al.

Users on Twitter are identified with the help of their profile attributes that consists of username, display name, profile image, to name a few. The profile attributes that users adopt can reflect their interests, belief, or thematic inclinations. Literature has proposed the implications and significance of profile attribute change for a random population of users. However, the use of profile attribute for endorsements and to start a movement have been under-explored. In this work, we consider #LokSabhaElections2019 as a movement and perform a large-scale study of the profile of users who actively made changes to profile attributes centered around #LokSabhaElections2019. We collect the profile metadata for 49.4M users for a period of 2 months from April 5, 2019 to June 5, 2019 amid #LokSabhaElections2019. We investigate how the profile changes vary for the influential leaders and their followers over the social movement. We further differentiate the organic and inorganic ways to show the political inclination from the prism of profile changes. We report how the addition of election campaign related keywords lead to spread of behavior contagion and further investigate it with respect to "Chowkidar Movement" in detail.

Saurabh Gupta, Asmit Kumar Singh, Arun Balaji Buduru et al.

Hashtags in online social media have become a way for users to build communities around topics, promote opinions, and categorize messages. In the political context, hashtags on Twitter are used by users to campaign for their parties, spread news, or to get followers and get a general idea by following a discussion built around a hashtag. In the past, researchers have studied certain types and specific properties of hashtags by utilizing a lot of data collected around hashtags. In this paper, we perform a large-scale empirical analysis of elections using only the hashtags shared on Twitter during the 2019 Lok Sabha elections in India. We study the trends and events unfolded on the ground, the latent topics to uncover representative hashtags and semantic similarity to relate hashtags with the election outcomes. We collect over 24 million hashtags to perform extensive experiments. First, we find the trending hashtags to cross-reference them with the tweets in our dataset to list down notable events. Second, we use Latent Dirichlet Allocation to find topic patterns in the dataset. In the end, we use skip-gram word embedding model to find semantically similar hashtags. We propose popularity and an influence metric to predict election outcomes using just the hashtags. Empirical results show that influence is a good measure to predict the election outcome.

Satvik Jain, Arun Balaji Buduru, Anshuman Chhabra

Cloud infrastructures are being increasingly utilized in critical infrastructures such as banking/finance, transportation and utility management. Sophistication and resources used in recent security breaches including those on critical infrastructures show that attackers are no longer limited by monetary/computational constraints. In fact, they may be aided by entities with large financial and human resources. Hence there is urgent need to develop predictive approaches for cyber defense to strengthen cloud infrastructures specifically utilized by critical infrastructures. Extensive research has been done in the past on applying techniques such as Game Theory, Machine Learning and Bayesian Networks among others for the predictive defense of critical infrastructures. However a major drawback of these approaches is that they do not incorporate probabilistic human behavior which limits their predictive ability. In this paper, a stochastic approach is proposed to predict less secure states in critical cloud systems which might lead to potential security breaches. These less-secure states are deemed as `risky' states in our approach. Markov Decision Process (MDP) is used to accurately incorporate user behavior(s) as well as operational behavior of the cloud infrastructure through a set of features. The developed reward/cost mechanism is then used to select appropriate `actions' to identify risky states at future time steps by learning an optimal policy. Experimental results show that the proposed framework performs well in identifying future `risky' states. Through this work we demonstrate the effectiveness of using probabilistic modeling (MDP) to predictively secure critical cloud infrastructures.