The deep neural network (DNN) model for computer vision tasks (object detection and classification) is widely used in autonomous vehicles, such as driverless cars and unmanned aerial vehicles. However, DNN models are shown to be vulnerable to adversarial image perturbations. The generation of adversarial examples against inferences of DNNs has been actively studied recently. The generation typically relies on optimizations taking an entire image frame as the decision variable. Hence, given a new image, the computationally expensive optimization needs to start over as there is no learning between the independent optimizations. Very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous vehicles, their mission, and the environment. The article presents a multi-level reinforcement learning framework that can effectively generate adversarial perturbations to misguide autonomous vehicles’ missions. In the existing image attack methods against autonomous vehicles, optimization steps are repeated for every image frame. This framework removes the need for fully converged optimization at every frame. Using multi-level reinforcement learning, we integrate a state estimator and a generative adversarial network that generates the adversarial perturbations. Due to the reinforcement learning agent consisting of state estimator, actor, and critic that only uses image streams, the proposed framework can misguide the vehicle to increase the adversary’s reward without knowing the states of the vehicle and the environment. Simulation studies and a robot demonstration are provided to validate the proposed framework’s performance.

This article proposes a novel extension of the Simplex architecture with model switching and model learning to achieve safe velocity regulation of self-driving vehicles in dynamic and unforeseen environments. To guarantee the reliability of autonomous vehicles, an ℒ 1 adaptive controller that compensates for uncertainties and disturbances is employed by the Simplex architecture as a verified high-assurance controller (HAC) to tolerate concurrent software and physical failures. Meanwhile, the safe switching controller is incorporated into the HAC for safe velocity regulation in the dynamic (prepared) environments, through the integration of the traction control system and anti-lock braking system. Due to the high dependence of vehicle dynamics on the driving environments, the HAC leverages the finite-time model learning to timely learn and update the vehicle model for ℒ 1 adaptive controller, when any deviation from the safety envelope or the uncertainty measurement threshold occurs in the unforeseen driving environments. With the integration of ℒ 1 adaptive controller, safe switching controller and finite-time model learning, the vehicle’s angular and longitudinal velocities can asymptotically track the provided references in the dynamic and unforeseen driving environments, while the wheel slips are restricted to safety envelopes to prevent slipping and sliding. Finally, the effectiveness of the proposed Simplex architecture for safe velocity regulation is validated by the AutoRally platform.

We propose a communication efficient quasi-Newton method for large-scale multi-agent convex composite optimization. We assume the setting of a network of agents that cooperatively solve a global minimization problem with strongly convex local cost functions augmented with a non-smooth convex regularizer. By introducing consensus variables, we obtain a block-diagonal Hessian and thus eliminate the need for additional communication when approximating the objective curvature information. Moreover, we reduce computational costs of existing primal-dual quasi-Newton methods from $\mathcal{O}\left( {{d^3}} \right)$ to $\mathcal{O}\left( {cd} \right)$ by storing c pairs of vectors of dimension d. An asynchronous implementation is presented that removes the need for coordination. Global linear convergence rate in expectation is established, and we demonstrate the merit of our algorithm numerically with real datasets.

The security of computers is at risk because of information leaking through their power consumption. Attackers can use advanced signal measurement and analysis to recover sensitive data from this side channel.To address this problem, this paper presents Maya, a simple and effective defense against power side channels. The idea is to use formal control to re-shape the power dissipated by a computer in an application-transparent manner—preventing attackers from learning any information about the applications that are running. With formal control, a controller can reliably keep power close to a desired target function even when runtime conditions change unpredictably. By selecting the target function intelligently, the controller can make power to follow any desired shape, appearing to carry activity information which, in reality, is unrelated to the application. Maya can be implemented in privileged software, firmware, or simple hardware. In this paper, we implement Maya on three machines using privileged threads only, and show its effectiveness and ease of deployment. Maya has already thwarted a newly-developed remote power attack.

Resource control in heterogeneous computers built with subsystems from different vendors is challenging. There is a tension between the need to quickly generate local decisions in each subsystem and the desire to coordinate the different subsystems for global optimization. In practice, global coordination among subsystems is considered hard, and current commercial systems use centralized controllers. The result is high response time and high design cost due to lack of modularity.

Since computers increasingly execute in constrained environments, they are being equipped with controllers for resource management. However, the operation of modern computer systems is structured in multiple layers, such as the hardware, OS, and networking layers—each with its own resources. Managing such a system scalably and portably requires that we have a controller in each layer, and that the different controllers coordinate their operation. In addition, such controllers should not rely on heuristics, but be based on formal control theory. This paper presents a new approach to build coordinated multilayer formal controllers for computers. The approach uses Structured Singular Value (SSV) controllers from Robust Control Theory. Such controllers are especially suited for multilayer computer system control. Indeed, SSV controllers can read signals from other controllers to coordinate multilayer operation. In addition, they allow designers to specify the discrete values allowed in each input, and the desired bounds on output value deviations. Finally, they accept uncertainty guardbands, which incorporate the effects of interference between the controllers. We call this approach Yukta. To assess its effectiveness, we prototype it in an 8-core big. LITTLE board. We build a two-layer SSV controller, and show that it is very effective. Yukta reduces the ExD and the execution time of a set of applications by an average of 50% and 38%, respectively, over advanced heuristic-based coordinated controllers.

Multicores increasingly execute in constrained environments, and are being equipped with controllers for resource management. However, modern multicore systems are structured in multiple complex layers, such as the hardware, OS, and networking layers, each with its own resources. Managing such a system scalably and portably requires that we have a controller in each layer, and that the different controllers coordinate their operation. We present a novel methodology to build coordinated multilevel formal controllers in computing. We consider Robust Control Theory, which focuses on decision making in uncertain environments, and pick the popular Structured Singular Value (SSV) controller. This is the first work to utilize Robust Control Theory for compute resource management. Our contribution are: 1) Novel interdisciplinary application of SSV controllers from robust control theory for coordinating multilayer controllers in computers; and 2) A practical methodology for independent teams to design coordinating multilayer SSV controllers.

As processors seek more resource efficiency, they increasingly need to target multiple goals at the same time, such as a level of performance, power consumption, and average utilization. Robust control solutions cannot come from heuristic-based controllers or even from formal approaches that combine multiple single-parameter controllers. Such controllers may end-up working against each other. What is needed is control-theoretical MIMO (multiple input, multiple output) controllers, which actuate on multiple inputs and control multiple outputs in a coordinated manner. In this paper, we use MIMO control-theory techniques to develop controllers to dynamically tune architectural parameters in processors. To our knowledge, this is the first work in this area. We discuss three ways in which a MIMO controller can be used. We develop an example of MIMO controller and show that it is substantially more effective than controllers based on heuristics or built by combining single-parameter formal controllers. The general approach discussed here is likely to be increasingly relevant as future processors become more resource-constrained and adaptive.

We study the problem of minimizing the total distance incurred in assigning a group of mobile robots to an equal number of static targets. Assuming that the robots have limited, range-based communication and target-sensing capabilities, we present a necessary and sufficient condition for ensuring distance optimality when robots and targets are uniformly randomly distributed. We then provide an explicit, non-asymptotic formula for computing the number of robots needed for guaranteeing optimality in terms of the robots' sensing and communication capabilities with arbitrarily high probabilities. The bound given in the formula is also asymptotically tight. Due to the large number of robots needed for high-probability optimality guarantee, we continue to investigate strategies for cases in which the number of robots cannot be freely chosen. We show that a properly designed strategy can be asymptotically optimal or suboptimal with constant approximation ratios.

In this paper we consider the transmission of discrete-valued data via a communication channel that is subject to (additive) noise with a known upper bound on its magnitude but otherwise completely unrestricted and unknown behavior. We consider a discrete-time setup and extend previous equalization strategies for perfect reconstruction by allowing linear preprocessing of the data and/or linear feedback from the receiver to the transmitter. We are interested in the characterization of general conditions that allow perfect reconstruction of the discrete data with any given (possibly nonzero) delay (and under all possible realizations of channel noise and a limit on the power of transmission) when linear preprocessing of the data and/or linear feedback from the receiver is employed. In particular, we obtain necessary and sufficient conditions for perfect reconstruction under either linear power-limited preprocessing or linear power- limited preprocessing along with linear feedback. We prove that in order to improve the conditions for perfect reconstruction, it is necessary that the feedback and preprocessing systems are unstable. We also consider the case when a Decision Feedback Equalizer (DFE) structure is imposed at the receiver and provide necessary conditions for improvements in the perfect reconstruction in terms of l1norms of appropriate maps. In addition, a procedure that results in parametric l1optimization is developed to design a DFE to improve the maximum tolerable noise bound.

In this paper we consider improving the quantity and quality of data collected and sent to a sink over the lifetime of a network of mobile sensors. The positions of the sensors and the routing strategy chosen are the variables in our problem. The original problem is a multi-objective non-convex optimization problem and we believe it to be tough to solve. The approach taken in this paper is to break down the original problem into sub-problems and develop an iterative scheme to optimize both the quantities. We propose three sub-problems. First, we optimize the way (obtain flows) the data is sent to the sink for a fixed placement of the nodes by solving a linear program (work on this has already been done in the past by others). Once flows have been obtained, they are kept constant and the nodes are then moved in a way such that the lifetime is further improved, keeping the maximum distortion error less than or equal to what it is for the initial node placement. Then for the new node distribution with a better lifetime, we decrease the maximum distortion error keeping the lifetime greater than or equal as compared to the starting configuration. Centralized and decentralized iterative schemes are presented using these subproblems that monotonically improve the lifetime data gathering and reduce maximum distortion error at each step.