Search

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are primarily attributed from the purity of the training samples, therefore the deep learning architectures are often susceptible to adversarial attacks. Adversarial attacks are often obtained by making subtle perturbations to normal images, which are mostly imperceptible to humans, but can seriously confuse the state-of-the-art machine learning models. We propose a framework, named APuDAE, leveraging Denoising AutoEncoders (DAEs) to purify these samples by using them in an adaptive way and thus improve the classification accuracy of the target classifier networks that have been attacked. We also show how using DAEs adaptively instead of using them directly, improves classification accuracy further and is more robust to the possibility of designing adaptive attacks to fool them. We demonstrate our results over MNIST, CIFAR-10, ImageNet dataset and show how our framework (APuDAE) provides comparable and in most cases better performance to the baseline methods in purifying adversaries. We also design adaptive attack specifically designed to attack our purifying model and demonstrate how our defense is robust to that., Submitted to AAAI 2023

The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the deep learning systems are vulnerable to crafted adversarial examples, which may be imperceptible to the human eye, but can lead the model to misclassify. Protections against adversarial perturbations on ensemble-based techniques have either been shown to be vulnerable to stronger adversaries or shown to lack an end-to-end evaluation. In this paper, we attempt to develop a new ensemble-based solution that constructs defender models with diverse decision boundaries with respect to the original model. The ensemble of classifiers constructed by (1) transformation of the input by a method called Split-and-Shuffle, and (2) restricting the significant features by a method called Contrast-Significant-Features are shown to result in diverse gradients with respect to adversarial attacks, which reduces the chance of transferring adversarial examples from the original to the defender model targeting the same class. We present extensive experimentations using standard image classification datasets, namely MNIST, CIFAR-10 and CIFAR-100 against state-of-the-art adversarial attacks to demonstrate the robustness of the proposed ensemble-based defense. We also evaluate the robustness in the presence of a stronger adversary targeting all the models within the ensemble simultaneously. Results for the overall false positives and false negatives have been furnished to estimate the overall performance of the proposed methodology.

Agent-Based Models are very useful for simulation of physical or social processes, such as the spreading of a pandemic in a city. Such models proceed by specifying the behavior of individuals (agents) and their interactions, and parameterizing the process of infection based on such interactions based on the geography and demography of the city. However, such models are computationally very expensive, and the complexity is often linear in the total number of agents. This seriously limits the usage of such models for simulations, which often have to be run hundreds of times for policy planning and even model parameter estimation. An alternative is to develop an emulator, a surrogate model that can predict the Agent-Based Simulator's output based on its initial conditions and parameters. In this paper, we discuss a Deep Learning model based on Dilated Convolutional Neural Network that can emulate such an agent based model with high accuracy. We show that use of this model instead of the original Agent-Based Model provides us major gains in the speed of simulations, allowing much quicker calibration to observations, and more extensive scenario analysis. The models we consider are spatially explicit, as the locations of the infected individuals are simulated instead of the gross counts. Another aspect of our emulation framework is its divide-and-conquer approach that divides the city into several small overlapping blocks and carries out the emulation in them parallelly, after which these results are merged together. This ensures that the same emulator can work for a city of any size, and also provides significant improvement of time complexity of the emulator, compared to the original simulator.

Multi-Agent Path Finding (MAPF) is the problem of finding collision-free paths for multiple agents from their start locations to end locations. We consider an extension to this problem, Precedence Constrained Multi-Agent Path Finding (PC-MAPF), wherein agents are assigned a sequence of planning tasks that contain precedence constraints between them. PC-MAPF has various applications, for example in multi-agent pickup and delivery problems where some objects might require multiple agents to collaboratively pickup and move them in unison. Precedence constraints also arise in warehouse assembly problems where before a manufacturing task can begin, its input resources must be manufactured and delivered. We propose a novel algorithm, Precedence Constrained Conflict Based Search (PC-CBS), which finds makespan-optimal solutions for this class of problems. PC-CBS utilizes a Precedence-Constrained Task-Graph to define valid intervals for each planning task and updates them when precedence conflicts are encountered. We benchmark the performance of this algorithm over various warehouse assembly, and multi-agent pickup and delivery tasks, and use it to evaluate the sub-optimality of a recently proposed efficient baseline.

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are primarily attributed from the purity of the training samples, therefore the deep learning architectures are often susceptible to adversarial attacks. Adversarial attacks are often obtained by making subtle perturbations to normal images, which are mostly imperceptible to humans, but can seriously confuse the state-of-the-art machine learning models. What is so special in the slightest intelligent perturbations or noise additions over normal images that it leads to catastrophic classifications by the deep neural networks? Using statistical hypothesis testing, we find that Conditional Variational AutoEncoders (CVAE) are surprisingly good at detecting imperceptible image perturbations. In this paper, we show how CVAEs can be effectively used to detect adversarial attacks on image classification networks. We demonstrate our results over MNIST, CIFAR-10 dataset and show how our method gives comparable performance to the state-of-the-art methods in detecting adversaries while not getting confused with noisy images, where most of the existing methods falter., Accepted at Adversarial Machine Learning (AdvML) workshop, AAAI 2022

The security of Deep Learning classifiers is a critical field of study because of the existence of adversarial attacks. Such attacks usually rely on the principle of transferability, where an adversarial example crafted on a surrogate classifier tends to mislead the target classifier trained on the same dataset even if both classifiers have quite different architecture. Ensemble methods against adversarial attacks demonstrate that an adversarial example is less likely to mislead multiple classifiers in an ensemble having diverse decision boundaries. However, recent ensemble methods have either been shown to be vulnerable to stronger adversaries or shown to lack an end-to-end evaluation. This paper attempts to develop a new ensemble methodology that constructs multiple diverse classifiers using a Pairwise Adversarially Robust Loss (PARL) function during the training procedure. PARL utilizes gradients of each layer with respect to input in every classifier within the ensemble simultaneously. The proposed training procedure enables PARL to achieve higher robustness against black-box transfer attacks compared to previous ensemble methods without adversely affecting the accuracy of clean examples. We also evaluate the robustness in the presence of white-box attacks, where adversarial examples are crafted using parameters of the target classifier. We present extensive experiments using standard image classification datasets like CIFAR-10 and CIFAR-100 trained using standard ResNet20 classifier against state-of-the-art adversarial attacks to demonstrate the robustness of the proposed ensemble methodology.

During the Covid-19 pandemic, most governments across the world imposed policies like lock-down of public spaces and restrictions on people's movements to minimize the spread of the virus through physical contact. However, such policies have grave social and economic costs, and so it is important to pre-assess their impacts. In this work we aim to visualize the dynamics of the pandemic in a city under different intervention policies, by simulating the behavior of the residents. We develop a very detailed agent-based model for a city, including its residents, physical and social spaces like homes, marketplaces, workplaces, schools/colleges etc. We parameterize our model for Kolkata city in India using ward-level demographic and civic data. We demonstrate that under appropriate choice of parameters, our model is able to reproduce the observed dynamics of the Covid-19 pandemic in Kolkata, and also indicate the counter-factual outcomes of alternative intervention policies.

Reliability and fault tolerance are critical attributes of embedded cyber-physical systems that require a high safety-integrity level. For such systems, the use of formal functional safety specifications has been strongly advocated in most industrial safety standards, but reliability and fault tolerance have traditionally been treated as platform issues. We believe that addressing reliability and fault tolerance at the functional safety level widens the scope for resource optimization, targeting those functionalities that are safety-critical, rather than the entire platform. Moreover, for software based control functionalities, temporal redundancies have become just as important as replication of physical resources, and such redundancies can be modeled at the functional specification level. The ability to formally model functional reliability at a specification level enables early estimation of physical resources and computation bandwidth requirements. In this paper we propose, for the first time, a resource estimation methodology from a formal functional safety specification augmented by reliability annotations. The proposed reliability specification is overlaid on the safety-critical functional specification and our methodology extracts a constraint satisfaction problem for determining the optimal set of resources for meeting the reliability target for the safety-critical behaviors. We use SMT (Satisfiability Modulo Theories) / ILP (Integer Linear Programming) solvers at the back end to solve the optimization problem, and demonstrate the feasibility of our methodology on a Satellite Launch Vehicle Navigation, Guidance and Control (NGC) System., 23 pages

Until 2014, admissions to the Indian Institutes of Technology (IITs) were conducted under one umbrella, whereas the admissions to the non-IIT Centrally Funded Government Institutes (CFTIs) were conducted under a different umbrella, the Central Seat Allocation Board. In 2015, a new Multi-Round Multi-Run Deferred Acceptance joint seat allocation process was implemented, improving the efficiency and productivity of concerned stakeholders. The process brings all CFTIs under one umbrella for admissions: 100 institutes and approximately 39000 seats in 2018. In this scheme, each candidate submits a single choice list over all available programs, and receives no more than a single seat from the system, based on the choices and the ranks in the relevant merit lists. Significantly, overbooking of seats is forbidden. In this report, we provide details of our safe, fair and optimal algorithm. Novel features include the ability to handle multiple merit lists, seat guarantee across multiple rounds, implementing reservation, and de-reservation rules, handling escalation of ranks due to a revision of marks by state boards during the allocation process, and dealing with last minute de-recognition of other backward caste categories. A notable rule required the allocation of supernumerary seats to females, provided the program did not have a sufficient desired percentage, while, at the same time, not reducing the number of seats available to non-females. Looking forward, we posit first that it is inevitable that different colleges will prefer different mechanisms of judging merit, and assigning relative rank. We believe the ability of our algorithm to gracefully handle multiple merit lists gives us hope to express optimism that all undergraduate admissions in the country, beyond the CFTIs, can beneficially use the suggested scheme.

Recent studies have shown that adaptively regulating the sampling rate results in significant reduction in computational resources in embedded software based control. Selecting a uniform sampling rate for a control loop is robust, but overtly pessimistic for sharing processors among multiple control loops. Fine grained regulation of periodicity achieves better resource utilization, but is hard to implement online in a robust way. In this paper we propose multi-mode sampling period selection, derived from an offline control theoretic analysis of the system. We report significant gains in computational efficiency without trading off control performance., Work in Progress Poster, 51st Design Automation Conference (DAC), San Francisco, CA, 7-11, June 2014