BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Mani Srivastava

Mani Srivastava appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Machine LearningCryptography and SecurityArtificial IntelligenceComputer Visioneess.SPOther Computer ScienceApplicationsHuman-Computer InteractionInformation Retrieval

Catalog footprint

What is connected

14works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

14 published item(s)

preprint2026arXiv

Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges

Spatiotemporal reasoning plays a key role in Cyber-Physical Systems (CPS). Despite advances in Large Language Models (LLMs) and Large Reasoning Models (LRMs), their capacity to reason about complex spatiotemporal signals remains underexplored. This paper proposes a hierarchical SpatioTemporal reAsoning benchmaRK, STARK, to systematically evaluate LLMs across three levels of reasoning complexity: state estimation (e.g., predicting field variables, localizing and tracking events in space and time), spatiotemporal reasoning over states (e.g., inferring spatial-temporal relationships), and world-knowledge-aware reasoning that integrates contextual and domain knowledge (e.g., intent prediction, landmark-aware navigation). We curate 26 distinct spatiotemporal tasks with diverse sensor modalities, comprising 14,552 challenges where models answer directly or by Python Code Interpreter. Evaluating 3 LRMs and 8 LLMs, we find LLMs achieve limited success in tasks requiring geometric reasoning (e.g., multilateration or triangulation), particularly as complexity increases. Surprisingly, LRMs show robust performance across tasks with various levels of difficulty, often competing or surpassing traditional first-principle-based methods. Our results show that in reasoning tasks requiring world knowledge, the performance gap between LLMs and LRMs narrows, with some LLMs even surpassing LRMs. However, the LRM o3 model continues to achieve leading performance across all evaluated tasks, a result attributed primarily to the larger size of the reasoning models. STARK motivates future innovations in model architectures and reasoning paradigms for intelligent CPS by providing a structured framework to identify limitations in the spatiotemporal reasoning of LLMs and LRMs.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations

Multimodal deep neural networks deployed in realistic environments must contend with runtime variations: changes in modality quality, overall input complexity, and available platform resources. Current networks struggle with such fluctuations -- adaptive networks cannot adhere to a strict compute budget, controller-based networks neglect to consider input complexity, and statically provisioned networks fail at all the above. Consequently, they do not extract maximum utility from the expended computational resources. We present SWAN (Sample and World-Aware Multimodal Network), the first adaptive multimodal network that accomplishes all three goals. SWAN employs a quality-aware controller to assign resources among modalities according to a variable user-specified maximum budget. Within this budget, an adaptive gating module further optimizes efficiency by scaling layer utilization according to sample complexity. For further gains, SWAN also employs a token dropping module that masks semantically irrelevant multimodal features before performing detections. We evaluate SWAN in the domain of autonomous driving with complex multi-object 3D detection, reducing FLOPs by up to 49% with minimal degradation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Automatic Concept Extraction for Concept Bottleneck-based Video Classification

Recent efforts in interpretable deep learning models have shown that concept-based explanation methods achieve competitive accuracy with standard end-to-end models and enable reasoning and intervention about extracted high-level visual concepts from images, e.g., identifying the wing color and beak length for bird-species classification. However, these concept bottleneck models rely on a necessary and sufficient set of predefined concepts-which is intractable for complex tasks such as video classification. For complex tasks, the labels and the relationship between visual elements span many frames, e.g., identifying a bird flying or catching prey-necessitating concepts with various levels of abstraction. To this end, we present CoDEx, an automatic Concept Discovery and Extraction module that rigorously composes a necessary and sufficient set of concept abstractions for concept-based video classification. CoDEx identifies a rich set of complex concept abstractions from natural language explanations of videos-obviating the need to predefine the amorphous set of concepts. To demonstrate our method's viability, we construct two new public datasets that combine existing complex video classification datasets with short, crowd-sourced natural language explanations for their labels. Our method elicits inherent complex concept abstractions in natural language to generalize concept-bottleneck methods to complex tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Combining Individual and Joint Networking Behavior for Intelligent IoT Analytics

The IoT vision of a trillion connected devices over the next decade requires reliable end-to-end connectivity and automated device management platforms. While we have seen successful efforts for maintaining small IoT testbeds, there are multiple challenges for the efficient management of large-scale device deployments. With Industrial IoT, incorporating millions of devices, traditional management methods do not scale well. In this work, we address these challenges by designing a set of novel machine learning techniques, which form a foundation of a new tool, it IoTelligent, for IoT device management, using traffic characteristics obtained at the network level. The design of our tool is driven by the analysis of 1-year long networking data, collected from 350 companies with IoT deployments. The exploratory analysis of this data reveals that IoT environments follow the famous Pareto principle, such as: (i) 10% of the companies in the dataset contribute to 90% of the entire traffic; (ii) 7% of all the companies in the set own 90% of all the devices. We designed and evaluated CNN, LSTM, and Convolutional LSTM models for demand forecasting, with a conclusion of the Convolutional LSTM model being the best. However, maintaining and updating individual company models is expensive. In this work, we design a novel, scalable approach, where a general demand forecasting model is built using the combined data of all the companies with a normalization factor. Moreover, we introduce a novel technique for device management, based on autoencoders. They automatically extract relevant device features to identify device groups with similar behavior to flag anomalous devices.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On the amplification of security and privacy risks by post-hoc explanations in machine learning models

A variety of explanation methods have been proposed in recent years to help users gain insights into the results returned by neural networks, which are otherwise complex and opaque black-boxes. However, explanations give rise to potential side-channels that can be leveraged by an adversary for mounting attacks on the system. In particular, post-hoc explanation methods that highlight input dimensions according to their importance or relevance to the result also leak information that weakens security and privacy. In this work, we perform the first systematic characterization of the privacy and security risks arising from various popular explanation techniques. First, we propose novel explanation-guided black-box evasion attacks that lead to 10 times reduction in query count for the same success rate. We show that the adversarial advantage from explanations can be quantified as a reduction in the total variance of the estimated gradient. Second, we revisit the membership information leaked by common explanations. Contrary to observations in prior studies, via our modified attacks we show significant leakage of membership information (above 100% improvement over prior results), even in a much stricter black-box setting. Finally, we study explanation-guided model extraction attacks and demonstrate adversarial gains through a large reduction in query count.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

PhysioGAN: Training High Fidelity Generative Model for Physiological Sensor Readings

Generative models such as the variational autoencoder (VAE) and the generative adversarial networks (GAN) have proven to be incredibly powerful for the generation of synthetic data that preserves statistical properties and utility of real-world datasets, especially in the context of image and natural language text. Nevertheless, until now, there has no successful demonstration of how to apply either method for generating useful physiological sensory data. The state-of-the-art techniques in this context have achieved only limited success. We present PHYSIOGAN, a generative model to produce high fidelity synthetic physiological sensor data readings. PHYSIOGAN consists of an encoder, decoder, and a discriminator. We evaluate PHYSIOGAN against the state-of-the-art techniques using two different real-world datasets: ECG classification and activity recognition from motion sensors datasets. We compare PHYSIOGAN to the baseline models not only the accuracy of class conditional generation but also the sample diversity and sample novelty of the synthetic datasets. We prove that PHYSIOGAN generates samples with higher utility than other generative models by showing that classification models trained on only synthetic data generated by PHYSIOGAN have only 10% and 20% decrease in their classification accuracy relative to classification models trained on the real data. Furthermore, we demonstrate the use of PHYSIOGAN for sensor data imputation in creating plausible results.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

VindiCo: Privacy Safeguard Against Adaptation Based Spyware in Human-in-the-Loop IoT

Personalized IoT adapts their behavior based on contextual information, such as user behavior and location. Unfortunately, the fact that personalized IoT adapts to user context opens a side-channel that leaks private information about the user. To that end, we start by studying the extent to which a malicious eavesdropper can monitor the actions taken by an IoT system and extract users' private information. In particular, we show two concrete instantiations (in the context of mobile phones and smart homes) of a new category of spyware which we refer to as Context-Aware Adaptation Based Spyware (SpyCon). Experimental evaluations show that the developed SpyCon can predict users' daily behavior with an accuracy of 90.3%. The rest of this paper is devoted to introducing VindiCo, a software mechanism designed to detect and mitigate possible SpyCon. Being new spyware with no known prior signature or behavior, traditional spyware detection that is based on code signature or app behavior is not adequate to detect SpyCon. Therefore, VindiCo proposes a novel information-based detection engine along with several mitigation techniques to restrain the ability of the detected SpyCon to extract private information. By having general detection and mitigation engines, VindiCo is agnostic to the inference algorithm used by SpyCon. Our results show that VindiCo reduces the ability of SpyCon to infer user context from 90.3% to the baseline accuracy (accuracy based on random guesses) with negligible execution overhead.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Towards Imperceptible Query-limited Adversarial Attacks with Perceptual Feature Fidelity Loss

Recently, there has been a large amount of work towards fooling deep-learning-based classifiers, particularly for images, via adversarial inputs that are visually similar to the benign examples. However, researchers usually use Lp-norm minimization as a proxy for imperceptibility, which oversimplifies the diversity and richness of real-world images and human visual perception. In this work, we propose a novel perceptual metric utilizing the well-established connection between the low-level image feature fidelity and human visual sensitivity, where we call it Perceptual Feature Fidelity Loss. We show that our metric can robustly reflect and describe the imperceptibility of the generated adversarial images validated in various conditions. Moreover, we demonstrate that this metric is highly flexible, which can be conveniently integrated into different existing optimization frameworks to guide the noise distribution for better imperceptibility. The metric is particularly useful in the challenging black-box attack with limited queries, where the imperceptibility is hard to achieve due to the non-trivial perturbation power.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

MANGO: A Python Library for Parallel Hyperparameter Tuning

Tuning hyperparameters for machine learning algorithms is a tedious task, one that is typically done manually. To enable automated hyperparameter tuning, recent works have started to use techniques based on Bayesian optimization. However, to practically enable automated tuning for large scale machine learning training pipelines, significant gaps remain in existing libraries, including lack of abstractions, fault tolerance, and flexibility to support scheduling on any distributed computing framework. To address these challenges, we present Mango, a Python library for parallel hyperparameter tuning. Mango enables the use of any distributed scheduling framework, implements intelligent parallel search strategies, and provides rich abstractions for defining complex hyperparameter search spaces that are compatible with scikit-learn. Mango is comparable in performance to Hyperopt, another widely used library. Mango is available open-source and is currently used in production at Arm Research to provide state-of-art hyperparameter tuning capabilities.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Quick Question: Interrupting Users for Microtasks with Reinforcement Learning

Human attention is a scarce resource in modern computing. A multitude of microtasks vie for user attention to crowdsource information, perform momentary assessments, personalize services, and execute actions with a single touch. A lot gets done when these tasks take up the invisible free moments of the day. However, an interruption at an inappropriate time degrades productivity and causes annoyance. Prior works have exploited contextual cues and behavioral data to identify interruptibility for microtasks with much success. With Quick Question, we explore use of reinforcement learning (RL) to schedule microtasks while minimizing user annoyance and compare its performance with supervised learning. We model the problem as a Markov decision process and use Advantage Actor Critic algorithm to identify interruptible moments based on context and history of user interactions. In our 5-week, 30-participant study, we compare the proposed RL algorithm against supervised learning methods. While the mean number of responses between both methods is commensurate, RL is more effective at avoiding dismissal of notifications and improves user experience over time.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Attack Resilience and Recovery using Physical Challenge Response Authentication for Active Sensors Under Integrity Attacks

Embedded sensing systems are pervasively used in life- and security-critical systems such as those found in airplanes, automobiles, and healthcare. Traditional security mechanisms for these sensors focus on data encryption and other post-processing techniques, but the sensors themselves often remain vulnerable to attacks in the physical/analog domain. If an adversary manipulates a physical/analog signal prior to digitization, no amount of digital security mechanisms after the fact can help. Fortunately, nature imposes fundamental constraints on how these analog signals can behave. This work presents PyCRA, a physical challenge-response authentication scheme designed to protect active sensing systems against physical attacks occurring in the analog domain. PyCRA provides security for active sensors by continually challenging the surrounding environment via random but deliberate physical probes. By analyzing the responses to these probes, and by using the fact that the adversary cannot change the underlying laws of physics, we provide an authentication mechanism that not only detects malicious attacks but provides resilience against them. We demonstrate the effectiveness of PyCRA through several case studies using two sensing systems: (1) magnetic sensors like those found wheel speed sensors in robotics and automotive, and (2) commercial RFID tags used in many security-critical applications. Finally, we outline methods and theoretical proofs for further enhancing the resilience of PyCRA to active attacks by means of a confusion phase---a period of low signal to noise ratio that makes it more difficult for an attacker to correctly identify and respond to PyCRA's physical challenges. In doing so, we evaluate both the robustness and the limitations of PyCRA, concluding by outlining practical considerations as well as further applications for the proposed authentication mechanism.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Data Driven Energy Efficiency in Buildings

Buildings across the world contribute significantly to the overall energy consumption and are thus stakeholders in grid operations. Towards the development of a smart grid, utilities and governments across the world are encouraging smart meter deployments. High resolution (often at every 15 minutes) data from these smart meters can be used to understand and optimize energy consumptions in buildings. In addition to smart meters, buildings are also increasingly managed with Building Management Systems (BMS) which control different sub-systems such as lighting and heating, ventilation, and air conditioning (HVAC). With the advent of these smart meters, increased usage of BMS and easy availability and widespread installation of ambient sensors, there is a deluge of building energy data. This data has been leveraged for a variety of applications such as demand response, appliance fault detection and optimizing HVAC schedules. Beyond the traditional use of such data sets, they can be put to effective use towards making buildings smarter and hence driving every possible bit of energy efficiency. Effective use of this data entails several critical areas from sensing to decision making and participatory involvement of occupants. Picking from wide literature in building energy efficiency, we identify five crust areas (also referred to as 5 Is) for realizing data driven energy efficiency in buildings : i) instrument optimally; ii) interconnect sub-systems; iii) inferred decision making; iv) involve occupants and v) intelligent operations. We classify prior work as per these 5 Is and dis-cuss challenges, opportunities and applications across them. Building upon these 5 Is we discuss a well studied problem in building energy efficiency -non-intrusive load monitoring (NILM) and how research in this area spans across the 5 Is.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Demo Abstract: NILMTK v0.2: A Non-intrusive Load Monitoring Toolkit for Large Scale Data Sets

In this demonstration, we present an open source toolkit for evaluating non-intrusive load monitoring research; a field which aims to disaggregate a household's total electricity consumption into individual appliances. The toolkit contains: a number of importers for existing public data sets, a set of preprocessing and statistics functions, a benchmark disaggregation algorithm and a set of metrics to evaluate the performance of such algorithms. Specifically, this release of the toolkit has been designed to enable the use of large data sets by only loading individual chunks of the whole data set into memory at once for processing, before combining the results of each chunk.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

NILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring

Non-intrusive load monitoring, or energy disaggregation, aims to separate household energy consumption data collected from a single point of measurement into appliance-level consumption data. In recent years, the field has rapidly expanded due to increased interest as national deployments of smart meters have begun in many countries. However, empirically comparing disaggregation algorithms is currently virtually impossible. This is due to the different data sets used, the lack of reference implementations of these algorithms and the variety of accuracy metrics employed. To address this challenge, we present the Non-intrusive Load Monitoring Toolkit (NILMTK); an open source toolkit designed specifically to enable the comparison of energy disaggregation algorithms in a reproducible manner. This work is the first research to compare multiple disaggregation approaches across multiple publicly available data sets. Our toolkit includes parsers for a range of existing data sets, a collection of preprocessing algorithms, a set of statistics for describing data sets, two reference benchmark disaggregation algorithms and a suite of accuracy metrics. We demonstrate the range of reproducible analyses which are made possible by our toolkit, including the analysis of six publicly available data sets and the evaluation of both benchmark disaggregation algorithms across such data sets.

0 citations0 reviewsNo code linkedOpen access