Open Access. Powered by Scholars. Published by Universities.®

Computer Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 30 of 175

Full-Text Articles in Computer Engineering

Holistic Resource Allocation For Multicore Real-Time Systems, Meng Xu, Linh T.X. Phan, Hyon-Young Choi, Yuhan Lin, Haoran Li, Chenyang Lu, Insup Lee Apr 2019

Holistic Resource Allocation For Multicore Real-Time Systems, Meng Xu, Linh T.X. Phan, Hyon-Young Choi, Yuhan Lin, Haoran Li, Chenyang Lu, Insup Lee

Departmental Papers (CIS)

This paper presents CaM, a holistic cache and memory bandwidth resource allocation strategy for multicore real-time systems. CaM is designed for partitioned scheduling, where tasks are mapped onto cores, and the shared cache and memory bandwidth resources are partitioned among cores to reduce resource interferences due to concurrent accesses. Based on our extension of LITMUSRT with Intel’s Cache Allocation Technology and MemGuard, we present an experimental evaluation of the relationship between the allocation of cache and memory bandwidth resources and a task’s WCET. Our resource allocation strategy exploits this relationship to map tasks onto cores, and to ...


Tactile Perception And Visuotactile Integration For Robotic Exploration, Mabel Zhang Jan 2019

Tactile Perception And Visuotactile Integration For Robotic Exploration, Mabel Zhang

Publicly Accessible Penn Dissertations

As the close perceptual sibling of vision, the sense of touch has historically received less than deserved attention in both human psychology and robotics. In robotics, this may be attributed to at least two reasons. First, it suffers from the vicious cycle of immature sensor technology, which causes industry demand to be low, and then there is even less incentive to make existing sensors in research labs easy to manufacture and marketable. Second, the situation stems from a fear of making contact with the environment, avoided in every way so that visually perceived states do not change before a carefully ...


Visual Perception For Robotic Spatial Understanding, Jason Lawrence Owens Jan 2019

Visual Perception For Robotic Spatial Understanding, Jason Lawrence Owens

Publicly Accessible Penn Dissertations

Humans understand the world through vision without much effort. We perceive the structure, objects, and people in the environment and pay little direct attention to most of it, until it becomes useful. Intelligent systems, especially mobile robots, have no such biologically engineered vision mechanism to take for granted. In contrast, we must devise algorithmic methods of taking raw sensor data and converting it to something useful very quickly. Vision is such a necessary part of building a robot or any intelligent system that is meant to interact with the world that it is somewhat surprising we don't have off-the-shelf ...


Reducing Pulse Oximetry False Alarms Without Missing Life-Threatening Events, Hung Nguyen, Sooyong Jang, Radoslav Ivanov, Christopher P. Bonafide, James Weimer, Insup Lee Sep 2018

Reducing Pulse Oximetry False Alarms Without Missing Life-Threatening Events, Hung Nguyen, Sooyong Jang, Radoslav Ivanov, Christopher P. Bonafide, James Weimer, Insup Lee

Departmental Papers (CIS)

Alarm fatigue has been increasingly recognized as one of the most significant problems in the hospital environment. One of the major causes is the excessive number of false physiologic monitor alarms. An underlying problem is the inefficient traditional threshold alarm system for physiologic parameters such as low blood oxygen saturation (SpO2). In this paper, we propose a robust classification procedure based on the AdaBoost algorithm with reject option that can identify and silence false SpO2 alarms, while ensuring zero misclassified clinically significant alarms. Alarms and vital signs related to SpO2 such as heart rate and pulse rate ...


Bandwidth Optimal Data/Service Delivery For Connected Vehicles Via Edges, Deepak Gangadharan, Oleg Sokolsky, Insup Lee, Baekgyu Kim, Chung-Wei Lin, Shinichi Shiraishi Jul 2018

Bandwidth Optimal Data/Service Delivery For Connected Vehicles Via Edges, Deepak Gangadharan, Oleg Sokolsky, Insup Lee, Baekgyu Kim, Chung-Wei Lin, Shinichi Shiraishi

Departmental Papers (CIS)

The paradigm of connected vehicles is fast gaining lot of attraction in the automotive industry. Recently, a lot of technological innovation has been pushed through to realize this paradigm using vehicle to cloud (V2C), infrastructure (V2I) and vehicle (V2V) communications. This has also opened the doors for efficient delivery of data/service to the vehicles via edge devices that are closer to the vehicles. In this work, we propose an optimization framework that can be used to deliver data/service to the connected vehicles such that a bandwidth cost objective is optimized. For the first time, we also integrate a ...


Towards Overhead-Free Interface Theory For Compositional Hierarchical Real-Time Systems, Jin Hyun Kim, Kygong Hoon Kim, Arvind Easwaran, Insup Lee May 2018

Towards Overhead-Free Interface Theory For Compositional Hierarchical Real-Time Systems, Jin Hyun Kim, Kygong Hoon Kim, Arvind Easwaran, Insup Lee

Technical Reports (CIS)

Much recent research has been conducted on compositional real-time scheduling framework as the framework becomes a useful fundamental theory for real-time OS-Hypervisor. Much recent research has been conducted on compositional real-time scheduling as the framework becomes a useful fundamental theory for real-time OS-Hypervisor. However, compositional frameworks suffer from abstraction overheads in composing components. In this paper, we classify the composition overheads into i) supply abstraction overhead associated with the supply from a resource provider, and ii) demand abstraction overhead associated with the component workload. Then, we provide sufficient conditions for each abstraction overhead to be eliminated. In addition, this paper ...


Data Freshness Over-Engineering: Formulation And Results, Dagaen Golomb, Deepak Gangadharan, Sanjian Chen, Oleg Sokolsky, Insup Lee May 2018

Data Freshness Over-Engineering: Formulation And Results, Dagaen Golomb, Deepak Gangadharan, Sanjian Chen, Oleg Sokolsky, Insup Lee

Departmental Papers (CIS)

In many application scenarios, data consumed by real-time tasks are required to meet a maximum age, or freshness, guarantee. In this paper, we consider the end-to-end freshness constraint of data that is passed along a chain of tasks in a uniprocessor setting. We do so with few assumptions regarding the scheduling algorithm used. We present a method for selecting the periods of tasks in chains of length two and three such that the end-to-end freshness requirement is satisfied, and then extend our method to arbitrary chains. We perform evaluations of both methods using parameters from an embedded benchmark suite (E3S ...


Generic Formal Framework For Compositional Analysis Of Hierarchical Scheduling Systems, Jalil Boudjadar, Jin Hyun Kim, Linh Thi Xuan Phan, Insup Lee, Kim G. Larsen, Ulrik Nyman May 2018

Generic Formal Framework For Compositional Analysis Of Hierarchical Scheduling Systems, Jalil Boudjadar, Jin Hyun Kim, Linh Thi Xuan Phan, Insup Lee, Kim G. Larsen, Ulrik Nyman

Departmental Papers (CIS)

We present a compositional framework for the specification and analysis of hierarchical scheduling systems (HSS). Firstly we provide a generic formal model, which can be used to describe any type of scheduling system. The concept of Job automata is introduced in order to model job instantiation patterns. We model the interaction between different levels in the hierarchy through the use of state-based resource models. Our notion of resource model is general enough to capture multi-core architectures, preemptiveness and non-determinism.


Openice-Lite: Towards A Connectivity Platform For The Internet Of Medical Things, Radoslav Ivanov, Hung Nguyen, James Weimer, Oleg Sokolsky, Insup Lee May 2018

Openice-Lite: Towards A Connectivity Platform For The Internet Of Medical Things, Radoslav Ivanov, Hung Nguyen, James Weimer, Oleg Sokolsky, Insup Lee

Departmental Papers (CIS)

The Internet of Medical Things (IoMT) is poised to revolutionize medicine. However, medical device communication, coordination, and interoperability present challenges for IoMT applications due to safety, security, and privacy concerns. These challenges can be addressed by developing an open platform for IoMT that can provide guarantees on safety, security and privacy. As a first step, we introduce OpenICE-lite, a middleware for medical device interoperability that also provides security guarantees and allows other IoMT applications to view/analyze the data in real time. We describe two applications that currently utilize OpenICE-lite, namely (i) a critical pulmonary shunt predictor for infants during ...


Joint Rate Control And Demand Balancing For Electric Vehicle Charging, Fanxin Kong, Xue Liu, Insup Lee Apr 2018

Joint Rate Control And Demand Balancing For Electric Vehicle Charging, Fanxin Kong, Xue Liu, Insup Lee

Departmental Papers (CIS)

Charging stations have become indispensable infrastructure to support the rapid proliferation of electric vehicles (EVs). The operational scheme of charging stations is crucial to satisfy the stability of the power grid and the quality of service (QoS) to EV users. Most existing schemes target either of the two major operations: charging rate control and demand balancing. This partial focus overlooks the coupling relation between the two operations and thus causes the degradation on the grid stability or customer QoS. A thoughtful scheme should manage both operations together. A big challenge to design such a scheme is the aggregated uncertainty caused ...


Parameter Invariant Monitoring For Signal Temporal Logic, Nima Roohi, Ramneet Kaur, James Weimer, Oleg Sokolsky, Insup Lee Apr 2018

Parameter Invariant Monitoring For Signal Temporal Logic, Nima Roohi, Ramneet Kaur, James Weimer, Oleg Sokolsky, Insup Lee

Departmental Papers (CIS)

Signal Temporal Logic (STL) is a prominent specification formalism for real-time systems, and monitoring these specifications, specially when (for different reasons such as learning) behavior of systems can change over time, is quite important. There are three main challenges in this area: (1) full observation of system state is not possible due to noise or nuisance parameters, (2) the whole execution is not available during the monitoring, and (3) computational complexity of monitoring continuous time signals is very high. Although, each of these challenges has been addressed by different works, to the best of our knowledge, no one has addressed ...


Cyber-Physical System Checkpointing And Recovery, Fanxin Kong, Meng Xu, James Weimer, Oleg Sokolsky, Insup Lee Apr 2018

Cyber-Physical System Checkpointing And Recovery, Fanxin Kong, Meng Xu, James Weimer, Oleg Sokolsky, Insup Lee

Departmental Papers (CIS)

Transitioning to more open architectures has been making Cyber-Physical Systems (CPS) vulnerable to malicious attacks that are beyond the conventional cyber attacks. This paper studies attack-resilience enhancement for a system under emerging attacks in the environment of the controller. An effective way to address this problem is to make system state estimation accurate enough for control regardless of the compromised components. This work follows this way and develops a procedure named CPS checkpointing and recovery, which leverages historical data to recover failed system states. Specially, we first propose a new concept of physical-state recovery. The essential operation is defined as ...


Logsafe: Secure And Scalable Data Logger For Iot Devices, Hung Nguyen, Radoslav Ivanov, Linh T.X. Phan, Oleg Sokolsky, James Weimer, Insup Lee Apr 2018

Logsafe: Secure And Scalable Data Logger For Iot Devices, Hung Nguyen, Radoslav Ivanov, Linh T.X. Phan, Oleg Sokolsky, James Weimer, Insup Lee

Departmental Papers (CIS)

As devices in the Internet of Things (IoT) increase in number and integrate with everyday lives, large amounts of personal information will be generated. With multiple discovered vulnerabilities in current IoT networks, a malicious attacker might be able to get access to and misuse this personal data. Thus, a logger that stores this information securely would make it possible to perform forensic analysis in case of such attacks that target valuable data. In this paper, we propose LogSafe, a scalable, fault-tolerant logger that leverages the use of Intel Software Guard Extensions (SGX) to store logs from IoT devices efficiently and ...


Context-Aware Detection In Medical Cyber-Physical Systems, Radoslav Ivanov, James Weimer, Insup Lee Apr 2018

Context-Aware Detection In Medical Cyber-Physical Systems, Radoslav Ivanov, James Weimer, Insup Lee

Departmental Papers (CIS)

This paper considers the problem of incorporating context in medical cyber-physical systems (MCPS) applications for the purpose of improving the performance of MCPS detectors. In particular, in many applications additional data could be used to conclude that actual measurements might be noisy or wrong (e.g., machine settings might indicate that the machine is improperly attached to the patient); we call such data context. The first contribution of this work is the formal definition of context, namely additional information whose presence is associated with a change in the measurement model (e.g., higher variance). Given this formulation, we developed the ...


Multi-Mode Virtualization For Soft Real-Time Systems, Haoran Li, Meng Xu, Chong Li, Chenyang Lu, Christopher Gill, Linh T.X. Phan, Insup Lee, Oleg Sokolsky Apr 2018

Multi-Mode Virtualization For Soft Real-Time Systems, Haoran Li, Meng Xu, Chong Li, Chenyang Lu, Christopher Gill, Linh T.X. Phan, Insup Lee, Oleg Sokolsky

Departmental Papers (CIS)

Real-time virtualization is an emerging technology for embedded systems integration and latency-sensitive cloud applications. Earlier real-time virtualization platforms require offline configuration of the scheduling parameters of virtual machines (VMs) based on their worst-case workloads, but this static approach results in pessimistic resource allocation when the workloads in the VMs change dynamically. Here, we present Multi-Mode-Xen (M2-Xen), a real-time virtualization platform for dynamic real-time systems where VMs can operate in modes with different CPU resource requirements at run-time. M2-Xen has three salient capabilities: (1) dynamic allocation of CPU resources among VMs in response to their mode changes, (2) overload avoidance at ...


Parameter-Invariant Monitor Design For Cyber Physical Systems, James Weimer, Radoslav Ivanov, Sanjian Chen, Alexander Roederer, Oleg Sokolsky, Insup Lee Jan 2018

Parameter-Invariant Monitor Design For Cyber Physical Systems, James Weimer, Radoslav Ivanov, Sanjian Chen, Alexander Roederer, Oleg Sokolsky, Insup Lee

Departmental Papers (CIS)

The tight interaction between information technology and the physical world inherent in Cyber-Physical Systems (CPS) can challenge traditional approaches for monitoring safety and security. Data collected for robust CPS monitoring is often sparse and may lack rich training data describing critical events/attacks. Moreover, CPS often operate in diverse environments that can have significant inter/intra-system variability. Furthermore, CPS monitors that are not robust to data sparsity and inter/intra-system variability may result in inconsistent performance and may not be trusted for monitoring safety and security. Towards overcoming these challenges, this paper presents recent work on the design of parameter-invariant ...


Strong Memory Consistency For Parallel Programming, Christian Delozier Jan 2018

Strong Memory Consistency For Parallel Programming, Christian Delozier

Publicly Accessible Penn Dissertations

Correctly synchronizing multithreaded programs is challenging, and errors can lead to program failures (e.g., atomicity violations). Existing memory consistency models rule out some possible failures, but are limited by depending on subtle programmer-defined locking code and by providing unintuitive semantics for incorrectly synchronized code. Stronger memory consistency models assist programmers by providing them with easier-to-understand semantics with regard to memory access interleavings in parallel code. This dissertation proposes a new strong memory consistency model based on ordering-free regions (OFRs), which are spans of dynamic instructions between consecutive ordering constructs (e.g. barriers). Atomicity over ordering-free

regions provides stronger atomicity ...


Choose-Your-Own Adventure: A Lightweight, High-Performance Approach To Defect And Variation Mitigation In Reconfigurable Logic, Raphael Yoram Rubin Jan 2018

Choose-Your-Own Adventure: A Lightweight, High-Performance Approach To Defect And Variation Mitigation In Reconfigurable Logic, Raphael Yoram Rubin

Publicly Accessible Penn Dissertations

For field-programmable gate arrays (FPGAs), fine-grained pre-computed alternative configurations, combined with simple test-based selection, produce limited per-chip specialization to counter yield loss, increased delay, and increased energy costs that come from fabrication defects and variation. This lightweight approach achieves much of the benefit of knowledge-based full specialization while reducing to practical, palatable levels the computational, testing, and load-time costs that obstruct the application of the knowledge-based approach. In practice this may more than double the power-limited computational capabilities of dies fabricated with 22nm technologies.

Contributions of this work:

• Choose-Your-own-Adventure (CYA), a novel, lightweight, scalable methodology to achieve defect and variation ...


Automatic Verification Of Linear Controller Software, Junkil Park Jan 2018

Automatic Verification Of Linear Controller Software, Junkil Park

Publicly Accessible Penn Dissertations

Many safety-critical cyber-physical systems have a software-based controller at their core. Since the system behavior relies on the operation of the controller, it is imperative to ensure the correctness of the controller to have a high assurance for such systems. Nowadays, controllers are developed in a model-based fashion. Controller models are designed, and their performances are analyzed first at the model level. Once the control design is complete, software implementation is automatically generated from the mathematical model of the controller by a code generator.

To assure the correctness of the controller implementation, it is necessary to check that the code ...


Lifelong Reinforcement Learning On Mobile Robots, David Isele Jan 2018

Lifelong Reinforcement Learning On Mobile Robots, David Isele

Publicly Accessible Penn Dissertations

Machine learning has shown tremendous growth in the past decades, unlocking new capabilities in a variety of fields including computer vision, natural language processing, and robotic control. While the sophistication of individual problems a learning system can handle has greatly advanced, the ability of a system to extend beyond an individual problem to adapt and solve new problems has progressed more slowly. This thesis explores the problem of progressive learning. The goal is to develop methodologies that accumulate, transfer, and adapt knowledge in applied settings where the system is faced with the ambiguity and resource limitations of operating in the ...


Mc-Adapt: Adaptive Task Dropping In Mixed-Criticality Scheduling, Jaewoo Lee, Hoon Sung Chwa, Linh T.X. Phan, Insik Shin, Insup Lee Oct 2017

Mc-Adapt: Adaptive Task Dropping In Mixed-Criticality Scheduling, Jaewoo Lee, Hoon Sung Chwa, Linh T.X. Phan, Insik Shin, Insup Lee

Departmental Papers (CIS)

Recent embedded systems are becoming integrated systems with components of different criticality. To tackle this, mixed-criticality systems aim to provide different levels of timing assurance to components of different criticality levels while achieving efficient resource utilization. Many approaches have been proposed to execute more lower-criticality tasks without affecting the timeliness of higher-criticality tasks. Those previous approaches however have at least one of the two limitations; i) they penalize all lower-criticality tasks at once upon a certain situation, or ii) they make the decision how to penalize lowercriticality tasks at design time. As a consequence, they underutilize resources by imposing an ...


Data Predictive Control Using Regression Trees And Ensemble Learning, Achin Jain, Francesco Smarra, Rahul Mangharam Sep 2017

Data Predictive Control Using Regression Trees And Ensemble Learning, Achin Jain, Francesco Smarra, Rahul Mangharam

Real-Time and Embedded Systems Lab (mLAB)

Decisions on how to best operate large complex plants such as natural gas processing, oil refineries, and energy efficient buildings are becoming ever so complex that model-based predictive control (MPC) algorithms must play an important role. However, a key factor prohibiting the widespread adoption of MPC, is the cost, time, and effort associated with learning first-principles dynamical models of the underlying physical system. An alternative approach is to employ learning algorithms to build black-box models which rely only on real-time data from the sensors. Machine learning is widely used for regression and classification, but thus far data-driven models have not ...


Monitoring Time Intervals, Teng Zhang, John Wiegley, Insup Lee, Oleg Sokolsky Sep 2017

Monitoring Time Intervals, Teng Zhang, John Wiegley, Insup Lee, Oleg Sokolsky

Departmental Papers (CIS)

Run-time checking of timed properties requires to monitor events occurring within a specified time interval. In a distributed setting, working with intervals is complicated due to uncertainties about network delays and clock synchronization. Determining that an interval can be closed - i.e., that all events occurring within the interval have been observed - cannot be done without a delay. In this paper, we consider how an appropriate delay can be determined based on parameters of a monitoring setup, such as network delay, clock skew and clock rate. We then propose a generic scheme for monitoring time intervals, parameterized by the detection ...


Automated Bug Removal For Software-Defined Networks, Yang Wu, Andreas Haeberlen, Wenchao Zhou, Boon T. Loo, Ang Chen Jul 2017

Automated Bug Removal For Software-Defined Networks, Yang Wu, Andreas Haeberlen, Wenchao Zhou, Boon T. Loo, Ang Chen

Technical Reports (CIS)

When debugging an SDN application, diagnosing the problem is merely the first step: the operator must still find a fix that solves the problem, without causing new problems elsewhere. However, most existing debuggers focus exclusively on diagnosis and offer the network operator little or no help with finding an effective fix. Finding a suitable fix is difficult because the number of candidates can be enormous. In this paper, we propose a step towards automated repair for SDN applications. Our approach consists of two elements. The first is a data structure that we call meta provenance, which can be used to ...


Process Algebraic Approach To The Schedulability Analysis And Workload Abstraction Of Hierarchical Real-Time Systems, Junkil Park, Insup Lee, Oleg Sokolsky, Dae Yon Hwang, Sojin Ahn, Jin-Young Choi, Inhye Kang Jul 2017

Process Algebraic Approach To The Schedulability Analysis And Workload Abstraction Of Hierarchical Real-Time Systems, Junkil Park, Insup Lee, Oleg Sokolsky, Dae Yon Hwang, Sojin Ahn, Jin-Young Choi, Inhye Kang

Departmental Papers (CIS)

Real-time embedded systems have increased in complexity. As microprocessors become more powerful, the software complexity of real-time embedded systems has increased steadily. The requirements for increased functionality and adaptability make the development of real-time embedded software complex and error-prone. Component-based design has been widely accepted as a compositional approach to facilitate the design of complex systems. It provides a means for decomposing a complex system into simpler subsystems and composing the subsystems in a hierarchical manner. A system composed of real-time subsystems with hierarchy is called a hierarchical real-time system

This paper describes a process algebraic approach to schedulability analysis ...


Security Of Cyber-Physical Systems In The Presence Of Transient Sensor Faults, Junkil Park, Radoslav Ivanov, James Weimer, Miroslav Pajic, Sang Hyuk Son, Insup Lee Jul 2017

Security Of Cyber-Physical Systems In The Presence Of Transient Sensor Faults, Junkil Park, Radoslav Ivanov, James Weimer, Miroslav Pajic, Sang Hyuk Son, Insup Lee

Departmental Papers (CIS)

This paper is concerned with the security of modern Cyber-Physical Systems in the presence of transient sensor faults. We consider a system with multiple sensors measuring the same physical variable, where each sensor provides an interval with all possible values of the true state. We note that some sensors might output faulty readings and others may be controlled by a malicious attacker. Different from previous works, in this paper we aim to distinguish between faults and attacks and develop an attack detection algorithm for the latter only. To do this, we note that there are two kinds of faults – transient ...


Dstress: Efficient Differentially Private Computations On Distributed Data, Antonis Papadimitriou, Andreas Haeberlen, Arjun Narayan Jun 2017

Dstress: Efficient Differentially Private Computations On Distributed Data, Antonis Papadimitriou, Andreas Haeberlen, Arjun Narayan

Technical Reports (CIS)

In this paper, we present DStress, a system that can efficiently perform computations on graphs that contain confidential data. DStress assumes that the graph is physically distributed across many participants, and that each participant only knows a small subgraph; it protects privacy by enforcing tight, provable limits on how much each participant can learn about the rest of the graph. We also study one concrete instance of this problem: measuring systemic risk in financial networks. Systemic risk is the likelihood of cascading bankruptcies – as, e.g., during the financial crisis of 2008 – and it can be quantified based on the ...


Extensible Energy Planning Framework For Preemptive Tasks, Jin Hyun Kim, Deepak Gangadharan, Oleg Sokolsky, Axel Legay, Insup Lee May 2017

Extensible Energy Planning Framework For Preemptive Tasks, Jin Hyun Kim, Deepak Gangadharan, Oleg Sokolsky, Axel Legay, Insup Lee

Departmental Papers (CIS)

Cyber-physical systems (CSPs) are demanding energy-efficient design not only of hardware (HW), but also of software (SW). Dynamic Voltage and and Frequency Scaling (DVFS) and Dynamic Power Manage (DPM) are most popular techniques to improve the energy efficiency. However, contemporary complicated HW and SW designs requires more elaborate and sophisticated energy management and efficiency evaluation techniques. This paper is concerned about energy supply planning for real-time scheduling systems (units) of which tasks need to meet deadlines. This paper presents a modelbased compositional energy planning technique that computes a minimal ratio of processor frequency that preserves schedulability of independent and preemptive ...


Automatic Verification Of Finite Precision Implementations Of Linear Controllers, Junkil Park, Miroslav Pajic, Oleg Sokolsky, Insup Lee Apr 2017

Automatic Verification Of Finite Precision Implementations Of Linear Controllers, Junkil Park, Miroslav Pajic, Oleg Sokolsky, Insup Lee

Departmental Papers (CIS)

We consider the problem of verifying finite precision implementation of linear time-invariant controllers against mathematical specifications. A specification may have multiple correct implementations which are different from each other in controller state representation, but equivalent from a perspective of input-output behavior (e.g., due to optimization in a code generator). The implementations may use finite precision computations (e.g. floating-point arithmetic) which cause quantization (i.e., roundoff) errors. To address these challenges, we first extract a controller's mathematical model from the implementation via symbolic execution and floating-point error analysis, and then check approximate input-output equivalence between the extracted model ...


Resilient Linear Classification: An Approach To Deal With Attacks On Training Data, Sangdon Park, James Weimer, Insup Lee Apr 2017

Resilient Linear Classification: An Approach To Deal With Attacks On Training Data, Sangdon Park, James Weimer, Insup Lee

Departmental Papers (CIS)

Data-driven techniques are used in cyber-physical systems (CPS) for controlling autonomous vehicles, handling demand responses for energy management, and modeling human physiology for medical devices. These data-driven techniques extract models from training data, where their performance is often analyzed with respect to random errors in the training data. However, if the training data is maliciously altered by attackers, the effect of these attacks on the learning algorithms underpinning data-driven CPS have yet to be considered. In this paper, we analyze the resilience of classification algorithms to training data attacks. Specifically, a generic metric is proposed that is tailored to measure ...