arXiv subjects

Srishti Gupta

Publications and source records attributed to Srishti Gupta.

At least 19 recordsLinked to original sources

arXiv2026

The Sense of Misinformation Can Harm Local Community: A Case Study of Community Conflict

During community decision-making and civic collaboration, conflicts can escalate when people suspect misinformation. We introduce the concept of sense of misinformation as experiencing someone's language or behavior as misinformation when it is not, that is to say when no falsehood is involved. Misinformation and sense of misinformation feel similar and can have similar social consequences; but sense of misinformation rests upon a mistaken perception of someone else's information as false. Through a case study of a casino proposal in local community, we examine how sense of misinformation developed over time during a contentious civic process through key factors (i.e., miscoordination governance, miscommunication between local government and citizens, and conflict and the breakdown of civic discourse), undermining trust and community democracy. Distinguishing between misinformation and sense of misinformation presents a challenge, but it is important. We contribute a conceptual distinction to the misinformation literature by identifying this distinct phenomenon and discuss ways to help communities recognize and repair such misattributions. Finally, we discuss design approaches for mitigating sense of misinformation.

cs.HC↗

arXiv2026

False Metallization in Short-Ranged Machine Learned Interatomic Potentials

Machine learned interatomic potentials (MLIPs) have enabled atomistic simulations with ab initio accuracy for a fraction of the computational cost. However, many widely used MLIPs are short-ranged and do not accurately capture long-ranged electrostatic interactions. At interfaces with polar solvents, such as water, this deficiency can drive unphysical long-distance dipolar alignment far away from the interface. Here we reveal that neglecting long-ranged physics leads to spurious metallization of the water layer due to artificially large fluctuations of the total solvent dipole, similar to the electron rearrangement observed to prevent polar catastrophes at polar interfaces. This metallization is eliminated in MLIPs that explicitly include long-ranged electrostatics. Our results showcase a fundamental flaw of short-ranged MLIPs, highlighting that long-ranged electrostatics are essential for studying systems with a polar-liquid component, especially if one is interested in electronic properties.

physics.chem-ph↗

arXiv2026

Evaluation of Audio Language Models for Fairness, Safety, and Security

Audio large language models (ALLMs) have recently advanced spoken interaction by integrating speech processing with large language models. However, existing evaluations of fairness, safety, and security (FSS) remain fragmented, largely because ALLMs differ fundamentally in how acoustic information is represented and where semantic reasoning occurs. Differences that are rarely made explicit. As a result, evaluations often conflate structurally distinct systems, obscuring the relationship between model design and observed FSS behavior. In this work, we introduce a structural taxonomy (system-level and representational) of ALLMs that categorizes systems along two axes: the form of audio input representation (e.g., discrete vs. continuous) and the locus of semantic reasoning (e.g., cascaded, multimodal, or audio-native). Building on the taxonomy, we propose a unified evaluation framework that assesses semantic invariance under paralinguistic variation, refusal and toxicity behavior under unsafe prompts, and robustness to adversarial audio perturbations. We apply this framework to two representative systems and observe systematic differences in refusal rates, attack success, and toxicity between audio and text inputs. Our findings demonstrate that FSS behavior is tightly coupled to how acoustic information is integrated into semantic reasoning, underscoring the need for structure-aware evaluation of audio language models.

cs.SD↗

arXiv2025

Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarking

Recent years have witnessed significant progress in the development of machine learning models across a wide range of fields, fueled by increased computational resources, large-scale datasets, and the rise of deep learning architectures. From malware detection to enabling autonomous navigation, modern machine learning systems have demonstrated remarkable capabilities. However, as these models are deployed in ever-changing real-world scenarios, their ability to remain reliable and adaptive over time becomes increasingly important. For example, in the real world, new malware families are continuously developed, whereas autonomous driving cars are employed in many different cities and weather conditions. Models trained in fixed settings can not respond effectively to novel conditions encountered post-deployment. In fact, most machine learning models are still developed under the assumption that training and test data are independent and identically distributed (i.i.d.), i.e., sampled from the same underlying (unknown) distribution. While this assumption simplifies model development and evaluation, it does not hold in many real-world applications, where data changes over time and unexpected inputs frequently occur. Retraining models from scratch whenever new data appears is computationally expensive, time-consuming, and impractical in resource-constrained environments. These limitations underscore the need for Continual Learning (CL), which enables models to incrementally learn from evolving data streams without forgetting past knowledge, and Out-of-Distribution (OOD) detection, which allows systems to identify and respond to novel or anomalous inputs. Jointly addressing both challenges is critical to developing robust, efficient, and adaptive AI systems.

cs.LG↗

arXiv2025

Chasing Shadows: Pitfalls in LLM Security Research

Large language models (LLMs) are increasingly prevalent in security research. Their unique characteristics, however, introduce challenges that undermine established paradigms of reproducibility, rigor, and evaluation. Prior work has identified common pitfalls in traditional machine learning research, but these studies predate the advent of LLMs. In this paper, we identify nine common pitfalls that have become (more) relevant with the emergence of LLMs and that can compromise the validity of research involving them. These pitfalls span the entire computation process, from data collection, pre-training, and fine-tuning to prompting and evaluation. We assess the prevalence of these pitfalls across all 72 peer-reviewed papers published at leading Security and Software Engineering venues between 2023 and 2024. We find that every paper contains at least one pitfall, and each pitfall appears in multiple papers. Yet only 15.7% of the present pitfalls were explicitly discussed, suggesting that the majority remain unrecognized. To understand their practical impact, we conduct four empirical case studies showing how individual pitfalls can mislead evaluation, inflate performance, or impair reproducibility. Based on our findings, we offer actionable guidelines to support the community in future work.

cs.CR↗

arXiv2025

Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware

Denoising Diffusion Probabilistic Models (DDPMs) have established a new state-of-the-art in generative image synthesis, yet their deployment is hindered by significant computational overhead during inference, often requiring up to 1,000 iterative steps. This study presents a rigorous comparative analysis of DDPMs against the emerging Flow Matching (Rectified Flow) paradigm, specifically isolating their geometric and efficiency properties on low-resource hardware. By implementing both frameworks on a shared Time-Conditioned U-Net backbone using the MNIST dataset, we demonstrate that Flow Matching significantly outperforms Diffusion in efficiency. Our geometric analysis reveals that Flow Matching learns a highly rectified transport path (Curvature $\mathcal{C} \approx 1.02$), which is near-optimal, whereas Diffusion trajectories remain stochastic and tortuous ($\mathcal{C} \approx 3.45$). Furthermore, we establish an ``efficiency frontier'' at $N=10$ function evaluations, where Flow Matching retains high fidelity while Diffusion collapses. Finally, we show via numerical sensitivity analysis that the learned vector field is sufficiently linear to render high-order ODE solvers (Runge-Kutta 4) unnecessary, validating the use of lightweight Euler solvers for edge deployment. \textbf{This work concludes that Flow Matching is the superior algorithmic choice for real-time, resource-constrained generative tasks.}

cs.LG↗

arXiv2025

Regression-aware Continual Learning for Android Malware Detection

Malware evolves rapidly, forcing machine learning-based detectors to be continuously updated. With antivirus vendors processing hundreds of thousands of new samples daily, datasets can grow to billions of examples, making full retraining impractical. Continual learning (CL) has emerged as a scalable alternative, enabling incremental updates without full data access while mitigating catastrophic forgetting. In this work, we analyze a critical yet overlooked issue in this context: security regression. Unlike forgetting, which manifests as a drop in average performance on previously seen data, security regression captures harmful sample-level prediction changes, e.g., malware samples that were correctly detected before an update but evade detection afterward. This poses serious risks in security-critical applications, as the silent reintroduction of previously detected threats may undermine users' trust in the update process, leading them to perceive a regression in security even if the average model performance has actually improved. We first formalize and quantify security regression in CL-based malware detectors, revealing that up to 3-6% of malware experience it after model updates. We then address this issue by introducing a regression-aware framework to the CL setting. Specifically, we instantiate it via Positive Congruent Training (PCT), showing seamless integration with any prior CL strategy. Experiments on the ELSA, Tesseract, and AZ-Class datasets show that our method effectively halves regression across different CL scenarios while maintaining strong detection performance over time.

cs.LG↗

arXiv2025

Buffer-free Class-Incremental Learning with Out-of-Distribution Detection

Class-incremental learning (CIL) poses significant challenges in open-world scenarios, where models must not only learn new classes over time without forgetting previous ones but also handle inputs from unknown classes that a closed-set model would misclassify. Recent works address both issues by (i)~training multi-head models using the task-incremental learning framework, and (ii) predicting the task identity employing out-of-distribution (OOD) detectors. While effective, the latter mainly relies on joint training with a memory buffer of past data, raising concerns around privacy, scalability, and increased training time. In this paper, we present an in-depth analysis of post-hoc OOD detection methods and investigate their potential to eliminate the need for a memory buffer. We uncover that these methods, when applied appropriately at inference time, can serve as a strong substitute for buffer-based OOD detection. We show that this buffer-free approach achieves comparable or superior performance to buffer-based methods both in terms of class-incremental learning and the rejection of unknown samples. Experimental results on CIFAR-10, CIFAR-100 and Tiny ImageNet datasets support our findings, offering new insights into the design of efficient and privacy-preserving CIL systems for open-world settings.

cs.LG↗

arXiv2024

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is considered one of the main suspects of the neural networks' vulnerability to adversarial example -- input samples crafted ad-hoc to induce a desired misclassification. Relevant literature has claimed contradictory remarks in support of and against the robustness of over-parameterized networks. These contradictory findings might be due to the failure of the attack employed to evaluate the networks' robustness. Previous research has demonstrated that depending on the considered model, the algorithm employed to generate adversarial examples may not function properly, leading to overestimating the model's robustness. In this work, we empirically study the robustness of over-parameterized networks against adversarial examples. However, unlike the previous works, we also evaluate the considered attack's reliability to support the results' veracity. Our results show that over-parameterized networks are robust against adversarial attacks as opposed to their under-parameterized counterparts.

cs.LG↗

arXiv2024

TONE: A 3-Tiered ONtology for Emotion analysis

Emotions have played an important part in many sectors, including psychology, medicine, mental health, computer science, and so on, and categorizing them has proven extremely useful in separating one emotion from another. Emotions can be classified using the following two methods: (1) The supervised method's efficiency is strongly dependent on the size and domain of the data collected. A categorization established using relevant data from one domain may not work well in another. (2) An unsupervised method that uses either domain expertise or a knowledge base of emotion types already exists. Though this second approach provides a suitable and generic categorization of emotions and is cost-effective, the literature doesn't possess a publicly available knowledge base that can be directly applied to any emotion categorization-related task. This pushes us to create a knowledge base that can be used for emotion classification across domains, and ontology is often used for this purpose. In this study, we provide TONE, an emotion-based ontology that effectively creates an emotional hierarchy based on Dr. Gerrod Parrot's group of emotions. In addition to ontology development, we introduce a semi-automated vocabulary construction process to generate a detailed collection of terms for emotions at each tier of the hierarchy. We also demonstrate automated methods for establishing three sorts of dependencies in order to develop linkages between different emotions. Our human and automatic evaluation results show the ontology's quality. Furthermore, we describe three distinct use cases that demonstrate the applicability of our ontology.

cs.AI↗

arXiv2023

IKDSumm: Incorporating Key-phrases into BERT for extractive Disaster Tweet Summarization

Online social media platforms, such as Twitter, are one of the most valuable sources of information during disaster events. Therefore, humanitarian organizations, government agencies, and volunteers rely on a summary of this information, i.e., tweets, for effective disaster management. Although there are several existing supervised and unsupervised approaches for automated tweet summary approaches, these approaches either require extensive labeled information or do not incorporate specific domain knowledge of disasters. Additionally, the most recent approaches to disaster summarization have proposed BERT-based models to enhance the summary quality. However, for further improved performance, we introduce the utilization of domain-specific knowledge without any human efforts to understand the importance (salience) of a tweet which further aids in summary creation and improves summary quality. In this paper, we propose a disaster-specific tweet summarization framework, IKDSumm, which initially identifies the crucial and important information from each tweet related to a disaster through key-phrases of that tweet. We identify these key-phrases by utilizing the domain knowledge (using existing ontology) of disasters without any human intervention. Further, we utilize these key-phrases to automatically generate a summary of the tweets. Therefore, given tweets related to a disaster, IKDSumm ensures fulfillment of the summarization key objectives, such as information coverage, relevance, and diversity in summary without any human intervention. We evaluate the performance of IKDSumm with 8 state-of-the-art techniques on 12 disaster datasets. The evaluation results show that IKDSumm outperforms existing techniques by approximately 2-79% in terms of ROUGE-N F1-score.

cs.CL↗

arXiv2022

Security of Deep Reinforcement Learning for Autonomous Driving: A Survey

Reinforcement learning (RL) enables agents to learn optimal behaviors through interaction with their environment and has been increasingly deployed in safety-critical applications, including autonomous driving. Despite its promise, RL is susceptible to attacks designed either to compromise policy learning or to induce erroneous decisions by trained agents. Although the literature on RL security has grown rapidly and several surveys exist, existing categorizations often fall short in guiding the selection of appropriate defenses for specific systems. In this work, we present a comprehensive survey of 86 recent studies on RL security, addressing these limitations by systematically categorizing attacks and defenses according to defined threat models and single- versus multi-agent settings. Furthermore, we examine the relevance and applicability of state-of-the-art attacks and defense mechanisms within the context of autonomous driving, providing insights to inform the design of robust RL systems.

cs.LG↗

arXiv2022

Not Another Day Zero: Design Hackathons for Community-Based Water Quality Monitoring

This study looks at water quality monitoring and management as a new form of community engagement. Through a series of a unique research method called `design hackathons', we engaged with a hyperlocal community of citizens who are actively involved in monitoring and management of their local watershed. These design hackathons sought to understand the motivation, practices, collaboration and experiences of these citizens. Qualitative analysis of data revealed the nature of the complex stakeholder network, workflow practices, initiatives to engage with a larger community, current state of technological infrastructure being used, and innovative design scenarios proposed by the hackathon participants. Based on this comprehensive analysis, we conceptualize water quality monitoring and management as community-based monitoring and management, and water data as community data. Such a conceptualization sheds light on how these practices can help in preempting water crisis by empowering citizens through increased awareness, active participation and informal learning of water data and resources.

cs.HC↗

arXiv2019

Heterogeneous Edge Embeddings for Friend Recommendation

We propose a friend recommendation system (an application of link prediction) using edge embeddings on social networks. Most real-world social networks are multi-graphs, where different kinds of relationships (e.g. chat, friendship) are possible between a pair of users. Existing network embedding techniques do not leverage signals from different edge types and thus perform inadequately on link prediction in such networks. We propose a method to mine network representation that effectively exploits heterogeneity in multi-graphs. We evaluate our model on a real-world, active social network where this system is deployed for friend recommendation for millions of users. Our method outperforms various state-of-the-art baselines on Hike's social network in terms of accuracy as well as user satisfaction.

cs.SI↗

arXiv2018

Under the Shadow of Sunshine: Characterizing Spam Campaigns Abusing Phone Numbers Across Online Social Networks

Cybercriminals abuse Online Social Networks (OSNs) to lure victims into a variety of spam. Among different spam types, a less explored area is OSN abuse that leverages the telephony channel to defraud users. Phone numbers are advertized via OSNs, and users are tricked into calling these numbers. To expand the reach of such scam / spam campaigns, phone numbers are advertised across multiple platforms like Facebook, Twitter, GooglePlus, Flickr, and YouTube. In this paper, we present the first data-driven characterization of cross-platform campaigns that use multiple OSN platforms to reach their victims and use phone numbers for monetization. We collect 23M posts containing 1.8M unique phone numbers from Twitter, Facebook, GooglePlus, Youtube, and Flickr over a period of six months. Clustering these posts helps us identify 202 campaigns operating across the globe with Indonesia, United States, India, and United Arab Emirates being the most prominent originators. We find that even though Indonesian campaigns generate highest volume (3.2M posts), only 1.6% of the accounts propagating Indonesian campaigns have been suspended so far. By examining campaigns running across multiple OSNs, we discover that Twitter detects and suspends 93% more accounts than Facebook. Therefore, sharing intelligence about abuse-related user accounts across OSNs can aid in spam detection. According to our dataset, around 35K victims and 8.8M USD could have been saved if intelligence was shared across the OSNs. By analyzing phone number based spam campaigns running on OSNs, we highlight the unexplored variety of phone-based attacks surfacing on OSNs.

cs.CY↗

arXiv2018

Collective Classification of Spam Campaigners on Twitter: A Hierarchical Meta-Path Based Approach

Cybercriminals have leveraged the popularity of a large user base available on Online Social Networks to spread spam campaigns by propagating phishing URLs, attaching malicious contents, etc. However, another kind of spam attacks using phone numbers has recently become prevalent on OSNs, where spammers advertise phone numbers to attract users' attention and convince them to make a call to these phone numbers. The dynamics of phone number based spam is different from URL-based spam due to an inherent trust associated with a phone number. While previous work has proposed strategies to mitigate URL-based spam attacks, phone number based spam attacks have received less attention. In this paper, we aim to detect spammers that use phone numbers to promote campaigns on Twitter. To this end, we collected information about 3,370 campaigns spread by 670,251 users. We model the Twitter dataset as a heterogeneous network by leveraging various interconnections between different types of nodes present in the dataset. In particular, we make the following contributions: (i) We propose a simple yet effective metric, called Hierarchical Meta-Path Score (HMPS) to measure the proximity of an unknown user to the other known pool of spammers. (ii) We design a feedback-based active learning strategy and show that it significantly outperforms three state-of-the-art baselines for the task of spam detection. Our method achieves 6.9% and 67.3% higher F1-score and AUC, respectively compared to the best baseline method. (iii) To overcome the problem of less training instances for supervised learning, we show that our proposed feedback strategy achieves 25.6% and 46% higher F1-score and AUC respectively than other oversampling strategies. Finally, we perform a case study to show how our method is capable of detecting those users as spammers who have not been suspended by Twitter (and other baselines) yet.

cs.SI↗

arXiv2015

Abusing Phone Numbers and Cross-Application Features for Crafting Targeted Attacks

With the convergence of Internet and telephony, new applications (e.g., WhatsApp) have emerged as an important means of communication for billions of users. These applications are becoming an attractive medium for attackers to deliver spam and carry out more targeted attacks. Since such applications rely on phone numbers, we explore the feasibility, automation, and scalability of phishing attacks that can be carried out by abusing a phone number. We demonstrate a novel system that takes a potential victim's phone number as an input, leverages information from applications like Truecaller and Facebook about the victim and his / her social network, checks the presence of phone number's owner (victim) on the attack channels (over-the-top or OTT messaging applications, voice, e-mail, or SMS), and finally targets the victim on the chosen channel. As a proof of concept, we enumerate through a random pool of 1.16 million phone numbers. By using information provided by popular applications, we show that social and spear phishing attacks can be launched against 51,409 and 180,000 users respectively. Furthermore, voice phishing or vishing attacks can be launched against 722,696 users. We also found 91,487 highly attractive targets who can be attacked by crafting whaling attacks. We show the effectiveness of one of these attacks, phishing, by conducting an online roleplay user study. We found that social (69.2%) and spear (54.3%) phishing attacks are more successful than non-targeted phishing attacks (35.5%) on OTT messaging applications. Although similar results were found for other mediums like e-mail, we demonstrate that due to the significantly increased user engagement via new communication applications and the ease with which phone numbers allow collection of information necessary for these attacks, there is a clear need for better protection of OTT messaging applications.

cs.SI↗

arXiv2014

Emerging Phishing Trends and Effectiveness of the Anti-Phishing Landing Page

Each month, more attacks are launched with the aim of making web users believe that they are communicating with a trusted entity which compels them to share their personal, financial information. Phishing costs Internet users billions of dollars every year. Researchers at Carnegie Mellon University (CMU) created an anti-phishing landing page supported by Anti-Phishing Working Group (APWG) with the aim to train users on how to prevent themselves from phishing attacks. It is used by financial institutions, phish site take down vendors, government organizations, and online merchants. When a potential victim clicks on a phishing link that has been taken down, he / she is redirected to the landing page. In this paper, we present the comparative analysis on two datasets that we obtained from APWG's landing page log files; one, from September 7, 2008 - November 11, 2009, and other from January 1, 2014 - April 30, 2014. We found that the landing page has been successful in training users against phishing. Forty six percent users clicked lesser number of phishing URLs from January 2014 to April 2014 which shows that training from the landing page helped users not to fall for phishing attacks. Our analysis shows that phishers have started to modify their techniques by creating more legitimate looking URLs and buying large number of domains to increase their activity. We observed that phishers are exploiting ICANN accredited registrars to launch their attacks even after strict surveillance. We saw that phishers are trying to exploit free subdomain registration services to carry out attacks. In this paper, we also compared the phishing e-mails used by phishers to lure victims in 2008 and 2014. We found that the phishing e-mails have changed considerably over time. Phishers have adopted new techniques like sending promotional e-mails and emotionally targeting users in clicking phishing URLs.

cs.CY↗