The rapid expansion of connected devices has made them prime targets for cyberattacks. To address these threats, deep learning-based, data-driven intrusion detection systems (IDS) have emerged as powerful tools for detecting and mitigating such attacks. These IDSs analyze network traffic to identify unusual patterns and anomalies that may indicate potential security breaches. However, prior research has shown that deep learning models are vulnerable to backdoor attacks, where attackers inject triggers into the model to manipulate its behavior and cause misclassifications of network traffic. In this article, we explore the susceptibility of deep learning-based IDS systems to backdoor attacks in the context of network traffic analysis. We introduce PCAP - Backdoor , a novel technique that facilitates backdoor attacks on PCAP datasets. Our experiments on real-world Cyber-Physical Systems (CPS) and Internet of Things (IoT) network traffic datasets demonstrate that attackers can effectively backdoor a model by poisoning as little as 2% or less of the entire training dataset. Moreover, we show that an attacker can introduce a trigger into benign traffic during model training yet cause the backdoored model to misclassify malicious traffic when the trigger is present. Finally, we highlight the difficulty of detecting this trigger-based backdoor, even when using existing backdoor defense techniques.

intent is hard to communicat  Prompts need to be detailed and dataspecific  LLM behavior varies across document  Requires fine-grained decomposition A B C Docs & Outputs condition discomfort_level symptoms

Serverless computing is an emerging cloud computing abstraction wherein the cloud platform transparently manages all resources, including explicitly provisioning resources and geographical load balancing when the demand for service spikes. Users provide code as functions, and the cloud platform runs these functions handling all aspects of function execution. While prior work has primarily focused on optimizing performance, this paper focuses on reducing the carbon footprint of these systems making variations in grid carbon intensity and intermittency from renewables transparent to the user. We introduce GreenWhisk, a carbon-aware serverless computing platform built upon Apache OpenWhisk, operating in two modes - grid-connected and grid-isolated - addressing intermittency challenges arising from renewables and the grid’s carbon footprint. Moreover, we develop carbon-aware load balancing algorithms that leverage energy and carbon information to reduce the carbon footprint. Our evaluation results show that GreenWhisk can easily incorporate carbon-aware algorithms, thereby reducing the carbon footprint of functions without significantly impacting the performance of function execution. In doing so, our system design enables the integration of new carbon-aware strategies into a serverless computing platform.

With the recent advent of single-cell level biological understanding, a growing interest is in identifying cell states or subtypes that are homogeneous in terms of gene expression and are also enriched in certain biological conditions, including disease samples versus normal samples (condition-specific cell subtype). Despite the importance of identifying condition-specific cell subtypes, existing methods have the following limitations: since they train models separately between gene expression and the biological condition information, (1) they do not consider potential interactions between them, and (2) the weights from both types of information are not properly controlled. Also, (3) they do not consider non-linear relationships in the gene expression and the biological condition. To address the limitations and accurately identify such condition-specific cell subtypes, we develop scDeepJointClust, the first method that jointly trains both types of information via a deep neural network. scDeepJointClust incorporates results from the power of state-of-the-art gene-expression-based clustering methods as an input, incorporating their sophistication and accuracy. We evaluated scDeepJointClust on both simulation data in diverse scenarios and biological data of different diseases (melanoma and non-small-cell lung cancer) and showed that scDeepJointClust outperforms existing methods in terms of sensitivity and specificity. scDeepJointClust exhibits significant promise in advancing our understanding of cellular states and their implications in complex biological systems.

Three-dimensional (3D) urban models have gained interest because of their applications in many use cases, such as disaster management, energy management, and solar potential analysis. However, generating these 3D representations of buildings require lidar data, which is usually expensive to collect. Consequently, the lidar data are not frequently updated and are not widely available for many regions in the United States. As such, 3D models based on these lidar data are either outdated or limited to those locations where the data is available. In contrast, satellite images are freely available and frequently updated. We propose sat2Map , a novel deep learning–based approach that predicts building roof geometries and heights directly from a single 2D satellite image. Our method first uses sat2pc to predict the point cloud by integrating two distinct loss functions, Chamfer Distance and Earth Mover’s Distance, resulting in a 3D point cloud output that balances overall structure and finer details. Additionally, we introduce sat2height , a height estimation model that estimates the height of the predicted point cloud to generate the final 3D building structure for a given location. We extensively evaluate our model on a building roof dataset and conduct ablation studies to analyze its performance. Our results demonstrate that sat2Map consistently outperforms existing baseline methods by at least 18.6%. Furthermore, we show that our refinement module significantly improves the overall performance, yielding more accurate and fine-grained 3D outputs. Our sat2height model demonstrates a high accuracy in predicting height parameters with a low error rate. Furthermore, our evaluation results show that we can estimate building heights with a median mean absolute error of less than 30 cm while still preserving the overall structure of the building.

Advances in deep vision techniques and the ubiquity of smart cameras will drive the next generation of video analytics. However, video analytics applications consume vast amounts of energy as deep learning techniques are power-hungry. In this article, we focus on a parking video analytics platform and propose RL-CamSleep, a deep reinforcement learning-based technique, to actuate the cameras to reduce the energy footprint while retaining the system’s utility. Our key insight is that many video-analytics applications do not need to be always operational, and we can design policies to activate video analytics only when necessary. We design two modes of operation for the reinforcement learning (RL) controller: (i) cloud-based mode and (ii) grid-isolated solar-powered mode. In the cloud-based mode, the controller runs on the cloud to control the cameras, whereas, in the solar-powered mode, the RL controller is constrained by the energy produced by solar. We evaluate our approach on a city-scale parking dataset having 76 streets spread across a city. Our analysis shows RL-CamSleep can learn an adaptive policy that reduces the average energy consumption by 76% and achieves an average accuracy of 98%. For the grid-isolated mode, RL-CamSleep outperforms other baseline techniques demonstrating the need for adaptive policy in energy-constrained environments.

Differential privacy in federated learning has emerged as a promising solution for big data applications to achieve strong privacy guarantees. While prior work assumes that the privacy requirements are homogeneous across all clients, in practice, privacy requirements can differ across clients. In this paper, we introduce a cohort-based (ϵ, δ)-DP framework where privacy requirements and data distribution differ across these client cohorts. We show that the performance of existing differentially private stochastic algorithms degrade significantly for heterogeneous privacy scenarios, especially when the data is non-independent and identically distributed (non-iid). Moreover, we propose two novel continual learning-based DP training methods — DP-Synaptic intelligence (DP-SI) and DP-Rehearsal (DP-R) — to improve the model performance of cohorts with heterogeneous privacy budgets. We evaluate our approach on real datasets and show that our techniques outperform baseline techniques. Furthermore, our approach adapts to post-hoc privacy budget relaxations, providing greater flexibility in training models without significantly impacting performance.

With billions of the Internet of Things (IoT) world-wide, the proliferation of IoT technologies will increase the global energy footprint. To date, much of the focus has been on addressing privacy exposure with approaches that remove sensitive information and, at the same time, ensure that users still derive utility from the data. In this paper, we bring the energy aspects of privatizers into the modeling and analysis of utility-privacy (UP) tradeoffs in IoT. We present a framework that enables users to examine (a) the energy cost of privatizing data, (b) the effect on the utility of the data, and (c) the privacy achieved. We evaluate our model with audio and image data and show that we can reduce energy consumption while retaining the user's chosen UP tradeoff point.

No abstract available.

The ET-SoC-1 has over a thousand RISC-V processors on a single TSMC 7nm chip, including: • 1088 energy-efficient ET-Minion 64-bit RISC-V in-order cores each with a vector/tensor unit • 4 high-performance ET-Maxion 64-bit RISC-V out-of-order cores • >160 million bytes of on-chip SRAM • Interfaces for large external memory with low-power LPDDR4x DRAM and eMMC FLASH • PCIe x8 Gen4 and other common I/O interfaces • Innovative low-power architecture and circuit techniques allows entire chip to • Compute at peak rates of 100 to 200 TOPS • Operate using under 20 watts for ML recommendation workloads

Rooftop solar deployments are an excellent source for generating clean energy. As a result, their popularity among homeowners has grown significantly over the years. Unfortunately, estimating the solar potential of a roof requires homeowners to consult solar consultants, who manually evaluate the site. Recently there have been efforts to automatically estimate the solar potential for any roof within a city. However, current methods work only for places where LIDAR data is available, thereby limiting their reach to just a few places in the world. In this paper, we propose DeepRoof, a data-driven approach that uses widely available satellite images to assess the solar potential of a roof. Using satellite images, DeepRoof determines the roof's geometry and leverages publicly available real-estate and solar irradiance data to provide a pixel-level estimate of the solar potential for each planar roof segment. Such estimates can be used to identify ideal locations on the roof for installing solar panels. Further, we evaluate our approach on an annotated roof dataset, validate the results with solar experts and compare it to a LIDAR-based approach. Our results show that DeepRoof can accurately extract the roof geometry such as the planar roof segments and their orientation, achieving a true positive rate of 91.1% in identifying roofs and a low mean orientation error of 9.3 degree. We also show that DeepRoof's median estimate of the available solar installation area is within 11% of a LIDAR-based approach.

The proliferation of solar deployments has significantly increased over the years. Analyzing these deployments can lead to the timely detection of anomalies in power generation, which can maximize the benefits from solar energy. In this paper, we propose SolarClique, a data-driven approach that can flag anomalies in power generation with high accuracy. Unlike prior approaches, our work neither depends on expensive instrumentation nor does it require external inputs such as weather data. Rather our approach exploits correlations in solar power generation from geographically nearby sites to predict the expected output of a site and flag anomalies. We evaluate our approach on 88 solar installations located in Austin, Texas. We show that our algorithm can even work with data from few geographically nearby sites (>5 sites) to produce results with high accuracy. Thus, our approach can scale to sparsely populated regions, where there are few solar installations. Further, among the 88 installations, our approach reported 76 sites with anomalies in power generation. Moreover, our approach is robust enough to distinguish between reduction in power output due to anomalies and other factors such as cloudy conditions.

Buildings consume over 40% of the total energy in modern societies and improving their energy efficiency can significantly reduce our energy footprint. In this paper, we present WattHome, a data-driven approach to identify the least energy efficient buildings from a large population of buildings in a city or a region. Unlike previous approaches such as least squares that use point estimates, WattHome uses Bayesian inference to capture the stochasticity in the daily energy usage by estimating the parameter distribution of a building. Further, it compares them with similar homes in a given population using widely available datasets. WattHome also incorporates a fault detection algorithm to identify the underlying causes of energy inefficiency. We validate our approach using ground truth data from different geographical locations, which showcases its applicability in different settings. Moreover, we present results from a case study from a city containing >10,000 buildings and show that more than half of the buildings are inefficient in one way or another indicating a significant potential from energy improvement measures. Additionally, we provide probable cause of inefficiency and find that 41%, 23.73%, and 0.51% homes have poor building envelope, heating, and cooling system faults respectively.

Infrastructure-as-a-Service (IaaS) cloud platforms rent computing resources with different cost and availability tradeoffs. For example, users may acquire virtual machines (VMs) in the spot market-that are cheap, but can be unilaterally terminated by the cloud operator. Because of this revocation risk, spot servers have been conventionally used for delay and risk tolerant batch jobs. In this paper, we develop risk mitigation policies which allow even interactive applications to run on spot servers. Our System, SpotCheck is a derivative cloud platform, and provides the illusion of an IaaS platform that offers always-available VMs on demand for a cost near that of spot servers, and supports unmodified applications. SpotCheck's design combines virtualization-based mechanisms for fault-tolerance, and bidding and server selection policies for managing the risk and cost. We implement SpotCheck on EC2 and show that it i) provides nested VMs with 99.9989 percent availability, ii) achieves upto 2-5x cost savings compared to using on-demand VMs, and iii) eliminates any risk of losing VM state.

Reducing peak demands and achieving a high penetration of renewable energy sources are important goals in achieving a smarter grid. To reduce peak demand, utilities are introducing variable rate electricity prices to incentivize consumers to manually shift their demand to low-price periods. Consumers may also use energy storage to automatically shift their demand by storing energy during low-price periods for use during high-price periods. Unfortunately, variable rate pricing provides only a weak incentive for distributed energy storage and does not promote its adoption at large scales. In this article, we present the storage adoption dilemma to capture the problems with incentivizing energy storage using variable rate prices. To address the problem, we propose a simple pricing scheme, called flat-power pricing , which incentivizes consumers to shift small amounts of load to flatten their demand rather than shift as much of their power usage as possible to low-price, off-peak periods. We show that compared to variable rate pricing, flat-power pricing (i) reduces consumers’ upfront capital costs, as it requires significantly less storage capacity per consumer; (ii) increases energy storage’s return on investment, as it mitigates free riding and maintains the incentive to use energy storage at large scales; and (iii) uses aggregate storage capacity within 31% of an optimal centralized approach. In addition, unlike variable rate pricing, we also show that flat-power pricing incentivizes the scheduling of elastic background loads, such as air conditioners and heaters, to reduce peak demand. We evaluate our approach using real smart meter data from 14,000 homes in a small town.

Infrastructure-as-a-Service (IaaS) cloud platforms rent resources, in the form of virtual machines (VMs), under a variety of contract terms that offer different levels of risk and cost. For example, users may acquire VMs in the spot market that are often cheap but entail significant risk, since their price varies over time based on market supply and demand and they may terminate at any time if the price rises too high. Currently, users must manage all the risks associated with using spot servers. As a result, conventional wisdom holds that spot servers are only appropriate for delay-tolerant batch applications. In this paper, we propose a derivative cloud platform, called SpotCheck, that transparently manages the risks associated with using spot servers for users.

Internet-scale Distributed Networks (IDNs) are large distributed systems that comprise hundreds of thousands of servers located around the world. IDNs consume significant amounts of energy to power their deployed server infrastructure, and nearly as much energy to cool that infrastructure. We study the potential benefits of using renewable open air cooling (OAC) in an IDN. Our results show that by using OAC, a global IDN can extract 51% cooling energy reducing during summers and a 92% reduction in the winter.

BACKGROUND: An important focus of genomic science is the discovery and characterization of all functional elements within genomes. In silico methods are used in genome studies to discover putative regulatory genomic elements (called words or motifs). Although a number of methods have been developed for motif discovery, most of them lack the scalability needed to analyze large genomic data sets. METHODS: This manuscript presents WordSeeker, an enumerative motif discovery toolkit that utilizes multi-core and distributed computational platforms to enable scalable analysis of genomic data. A controller task coordinates activities of worker nodes, each of which (1) enumerates a subset of the DNA word space and (2) scores words with a distributed Markov chain model. RESULTS: A comprehensive suite of performance tests was conducted to demonstrate the performance, speedup and efficiency of WordSeeker. The scalability of the toolkit enabled the analysis of the entire genome of Arabidopsis thaliana; the results of the analysis were integrated into The Arabidopsis Gene Regulatory Information Server (AGRIS). A public version of WordSeeker was deployed on the Glenn cluster at the Ohio Supercomputer Center. CONCLUSION: WordSeeker effectively utilizes concurrent computing platforms to enable the identification of putative functional elements in genomic data sets. This capability facilitates the analysis of the large quantity of sequenced genomic data.

We present a stereo-based obstacle avoidance system for mobile vehicles. The system operates in three steps. First, it models the surface geometry of the supporting surface and removes the supporting surface from the scene. Next, it segments the remaining stereo disparities into connected components in image and disparity space. Finally, it projects the resulting connected components onto the supporting surface and plans a path around them. One interesting aspect of this system is that it can detect both positive and "negative" obstacles (e.g. stairways) in its path. The algorithms we have developed have been implemented on a mobile robot equipped with a real-time stereo system. We present experimental results on indoor environments with planar supporting surfaces that show the algorithms to be both fast and robust.