arXiv subjects

Mani Srivastava

Publications and source records attributed to Mani Srivastava.

At least 73 records · Page 4Linked to original sources

arXiv2022

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.

cs.CR↗

arXiv2021

Using DeepProbLog to perform Complex Event Processing on an Audio Stream

In this paper, we present an approach to Complex Event Processing (CEP) that is based on DeepProbLog. This approach has the following objectives: (i) allowing the use of subsymbolic data as an input, (ii) retaining the flexibility and modularity on the definitions of complex event rules, (iii) allowing the system to be trained in an end-to-end manner and (iv) being robust against noisily labelled data. Our approach makes use of DeepProbLog to create a neuro-symbolic architecture that combines a neural network to process the subsymbolic data with a probabilistic logic layer to allow the user to define the rules for the complex events. We demonstrate that our approach is capable of detecting complex events from an audio stream. We also demonstrate that our approach is capable of training even with a dataset that has a moderate proportion of noisy data.

cs.SD↗

arXiv2021

I Always Feel Like Somebody's Sensing Me! A Framework to Detect, Identify, and Localize Clandestine Wireless Sensors

The increasing ubiquity of low-cost wireless sensors has enabled users to easily deploy systems to remotely monitor and control their environments. However, this raises privacy concerns for third-party occupants, such as a hotel room guest who may be unaware of deployed clandestine sensors. Previous methods focused on specific modalities such as detecting cameras but do not provide a generalized and comprehensive method to capture arbitrary sensors which may be "spying" on a user. In this work, we propose SnoopDog, a framework to not only detect common Wi-Fi-based wireless sensors that are actively monitoring a user, but also classify and localize each device. SnoopDog works by establishing causality between patterns in observable wireless traffic and a trusted sensor in the same space, e.g., an inertial measurement unit (IMU) that captures a user's movement. Once causality is established, SnoopDog performs packet inspection to inform the user about the monitoring device. Finally, SnoopDog localizes the clandestine device in a 2D plane using a novel trial-based localization technique. We evaluated SnoopDog across several devices and various modalities and were able to detect causality for snooping devices 95.2% of the time and localize devices to a sufficiently reduced sub-space.

cs.CR↗

arXiv2021

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.

cs.CV↗

arXiv2020

An Experimentation Platform for Explainable Coalition Situational Understanding

We present an experimentation platform for coalition situational understanding research that highlights capabilities in explainable artificial intelligence/machine learning (AI/ML) and integration of symbolic and subsymbolic AI/ML approaches for event processing. The Situational Understanding Explorer (SUE) platform is designed to be lightweight, to easily facilitate experiments and demonstrations, and open. We discuss our requirements to support coalition multi-domain operations with emphasis on asset interoperability and ad hoc human-machine teaming in a dense urban terrain setting. We describe the interface functionality and give examples of SUE applied to coalition situational understanding tasks.

cs.AI↗

arXiv2020

Towards human-agent knowledge fusion (HAKF) in support of distributed coalition teams

Future coalition operations can be substantially augmented through agile teaming between human and machine agents, but in a coalition context these agents may be unfamiliar to the human users and expected to operate in a broad set of scenarios rather than being narrowly defined for particular purposes. In such a setting it is essential that the human agents can rapidly build trust in the machine agents through appropriate transparency of their behaviour, e.g., through explanations. The human agents are also able to bring their local knowledge to the team, observing the situation unfolding and deciding which key information should be communicated to the machine agents to enable them to better account for the particular environment. In this paper we describe the initial steps towards this human-agent knowledge fusion (HAKF) environment through a recap of the key requirements, and an explanation of how these can be fulfilled for an example situation. We show how HAKF has the potential to bring value to both human and machine agents working as part of a distributed coalition team in a complex event processing setting with uncertain sources.

cs.MA↗

arXiv2020

A Hybrid Neuro-Symbolic Approach for Complex Event Processing

Training a model to detect patterns of interrelated events that form situations of interest can be a complex problem: such situations tend to be uncommon, and only sparse data is available. We propose a hybrid neuro-symbolic architecture based on Event Calculus that can perform Complex Event Processing (CEP). It leverages both a neural network to interpret inputs and logical rules that express the pattern of the complex event. Our approach is capable of training with much fewer labelled data than a pure neural network approach, and to learn to classify individual events even when training in an end-to-end manner. We demonstrate this comparing our approach against a pure neural network approach on a dataset based on Urban Sounds 8K.

cs.AI↗

arXiv2020

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.

cs.HC↗

arXiv2020

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.

cs.LG↗

arXiv2019

NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations

Deep neural networks have achieved state-of-the-art performance on various tasks. However, lack of interpretability and transparency makes it easier for malicious attackers to inject trojan backdoor into the neural networks, which will make the model behave abnormally when a backdoor sample with a specific trigger is input. In this paper, we propose NeuronInspect, a framework to detect trojan backdoors in deep neural networks via output explanation techniques. NeuronInspect first identifies the existence of backdoor attack targets by generating the explanation heatmap of the output layer. We observe that generated heatmaps from clean and backdoored models have different characteristics. Therefore we extract features that measure the attributes of explanations from an attacked model namely: sparse, smooth and persistent. We combine these features and use outlier detection to figure out the outliers, which is the set of attack targets. We demonstrate the effectiveness and efficiency of NeuronInspect on MNIST digit recognition dataset and GTSRB traffic sign recognition dataset. We extensively evaluate NeuronInspect on different attack scenarios and prove better robustness and effectiveness over state-of-the-art trojan backdoor detection techniques Neural Cleanse by a great margin.

cs.CR↗

arXiv2019

CryptoImg: Privacy Preserving Processing Over Encrypted Images

Cloud computing services provide a scalable solution for the storage and processing of images and multimedia files. However, concerns about privacy risks prevent users from sharing their personal images with third-party services. In this paper, we describe the design and implementation of CryptoImg, an open source library (Source at https://github.com/TarekIbnZiad/CryptoImg) of modular privacy preserving image processing operations over encrypted images. By using homomorphic encryption, CryptoImg allows the users to delegate their image processing operations to remote servers without any privacy concerns. Currently, CryptoImg supports a subset of the most frequently used image processing operations such as image adjustment, spatial filtering, edge sharpening, histogram equalization and others. We implemented our library as an extension to the popular computer vision library OpenCV. CryptoImg can be used from either mobile or desktop clients. Our experimental results demonstrate that CryptoImg is efficient while performing operations over encrypted images with negligible error and reasonable time overheads on the supported platforms

cs.CR↗

arXiv2019

NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning

Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their decisions. Over the past few years, researchers have studied the problem of providing explanations of why DNNs predicted their results. However, existing techniques are either obtrusive, requiring changes in model training, or suffer from low output quality. In this paper, we present a novel method, NeuroMask, for generating an interpretable explanation of classification model results. When applied to image classification models, NeuroMask identifies the image parts that are most important to classifier results by applying a mask that hides/reveals different parts of the image, before feeding it back into the model. The mask values are tuned by minimizing a properly designed cost function that preserves the classification result and encourages producing an interpretable mask. Experiments using state-of-the-art Convolutional Neural Networks for image recognition on different datasets (CIFAR-10 and ImageNet) show that NeuroMask successfully localizes the parts of the input image which are most relevant to the DNN decision. By showing a visual quality comparison between NeuroMask explanations and those of other methods, we find NeuroMask to be both accurate and interpretable.

cs.CV↗

arXiv2019

GenAttack: Practical Black-box Attacks with Gradient-Free Optimization

Deep neural networks are vulnerable to adversarial examples, even in the black-box setting, where the attacker is restricted solely to query access. Existing black-box approaches to generating adversarial examples typically require a significant number of queries, either for training a substitute network or performing gradient estimation. We introduce GenAttack, a gradient-free optimization technique that uses genetic algorithms for synthesizing adversarial examples in the black-box setting. Our experiments on different datasets (MNIST, CIFAR-10, and ImageNet) show that GenAttack can successfully generate visually imperceptible adversarial examples against state-of-the-art image recognition models with orders of magnitude fewer queries than previous approaches. Against MNIST and CIFAR-10 models, GenAttack required roughly 2,126 and 2,568 times fewer queries respectively, than ZOO, the prior state-of-the-art black-box attack. In order to scale up the attack to large-scale high-dimensional ImageNet models, we perform a series of optimizations that further improve the query efficiency of our attack leading to 237 times fewer queries against the Inception-v3 model than ZOO. Furthermore, we show that GenAttack can successfully attack some state-of-the-art ImageNet defenses, including ensemble adversarial training and non-differentiable or randomized input transformations. Our results suggest that evolutionary algorithms open up a promising area of research into effective black-box attacks.

cs.LG↗

arXiv2018

Generating Natural Language Adversarial Examples

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to human perception, causing humans and state-of-the-art models to disagree. However, in the natural language domain, small perturbations are clearly perceptible, and the replacement of a single word can drastically alter the semantics of the document. Given these challenges, we use a black-box population-based optimization algorithm to generate semantically and syntactically similar adversarial examples that fool well-trained sentiment analysis and textual entailment models with success rates of 97% and 70%, respectively. We additionally demonstrate that 92.3% of the successful sentiment analysis adversarial examples are classified to their original label by 20 human annotators, and that the examples are perceptibly quite similar. Finally, we discuss an attempt to use adversarial training as a defense, but fail to yield improvement, demonstrating the strength and diversity of our adversarial examples. We hope our findings encourage researchers to pursue improving the robustness of DNNs in the natural language domain.

cs.CL↗

arXiv2018

Optimization vs. Reinforcement Learning for Wirelessly Powered Sensor Networks

We consider a sensing application where the sensor nodes are wirelessly powered by an energy beacon. We focus on the problem of jointly optimizing the energy allocation of the energy beacon to different sensors and the data transmission powers of the sensors in order to minimize the field reconstruction error at the sink. In contrast to the standard ideal linear energy harvesting (EH) model, we consider practical non-linear EH models. We investigate this problem under two different frameworks: i) an optimization approach where the energy beacon knows the utility function of the nodes, channel state information and the energy harvesting characteristics of the devices; hence optimal power allocation strategies can be designed using an optimization problem and ii) a learning approach where the energy beacon decides on its strategies adaptively with battery level information and feedback on the utility function. Our results illustrate that deep reinforcement learning approach can obtain the same error levels with the optimization approach and provides a promising alternative to the optimization framework.

cs.IT↗

arXiv2018

Realizing Uncertainty-Aware Timing Stack in Embedded Operating System

Time awareness is critical to a broad range of emerging applications -- in Cyber-Physical Systems and Internet of Things -- running on commodity platforms and operating systems. Traditionally, time is synchronized across devices through a best-effort background service whose performance is neither observable nor controllable, thus consuming system resources independently of application needs while not allowing the applications and OS services to adapt to changes in uncertainty in system time. We advocate for rethinking how time is managed in a system stack. In this paper, we propose a new clock model that characterizes various sources of timing uncertainties in true time. We then present a Kalman filter based time synchronization protocol that adapts to the uncertainties exposed by the clock model. Our realization of a uncertainty-aware clock model and synchronization protocol is based on a standard embedded Linux platform.

cs.RO↗

arXiv2018

SecSens: Secure State Estimation with Application to Localization and Time Synchronization

Research evidence in Cyber-Physical Systems (CPS) shows that the introduced tight coupling of information technology with physical sensing and actuation leads to more vulnerability and security weaknesses. But, the traditional security protection mechanisms of CPS focus on data encryption while neglecting the sensors which are vulnerable to attacks in the physical domain. Accordingly, researchers attach utmost importance to the problem of state estimation in the presence of sensor attacks. In this work, we present SecSens, a novel approach for secure nonlinear state estimation in the presence of modeling and measurement noise. SecSens consists of two independent algorithms, namely, SecEKF and SecOPT, which are based on Extended Kalman Filter and Maximum Likelihood Estimation, respectively. We adopt a holistic approach to introduce security awareness among state estimation algorithms without requiring specialized hardware, or cryptographic techniques. We apply SecSens to securely localize and time synchronize networked mobile devices. SecSens provides good performance at run-time several order of magnitude faster than the state of art solutions under the presence of powerful attacks. Our algorithms are evaluated on a testbed with static nodes and a mobile quadrotor all equipped with commercial ultra-wide band wireless devices.

cs.CR↗

arXiv2018

Did you hear that? Adversarial Examples Against Automatic Speech Recognition

Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction between humans and machines. Recently, researchers have demonstrated powerful attacks against machine learning models that can fool them to produceincorrect results. However, nearly all previous research in adversarial attacks has focused on image recognition and object detection models. In this short paper, we present a first of its kind demonstration of adversarial attacks against speech classification model. Our algorithm performs targeted attacks with 87% success by adding small background noise without having to know the underlying model parameter and architecture. Our attack only changes the least significant bits of a subset of audio clip samples, and the noise does not change 89% the human listener's perception of the audio clip as evaluated in our human study.

cs.CL↗