1 code implementation • 22 May 2023 • Haitham Khedr, Yasser Shoukry
In this paper, we ask the following question; can we replace the ReLU activation function with one that opens the door to incomplete certification algorithms that are easy to compute but can produce tight bounds on the NN's outputs?
no code implementations • 25 Apr 2023 • Momina Sajid, Yanning Shen, Yasser Shoukry
We introduce the problem of model-extraction attacks in cyber-physical systems in which an attacker attempts to estimate (or extract) the feedback controller of the system.
no code implementations • 24 Feb 2023 • Mohanad Odema, James Ferlez, Yasser Shoukry, Mohammad Abdullah Al Faruque
Runtime energy management has become quintessential for multi-sensor autonomous systems at the edge for achieving high performance given the platform constraints.
no code implementations • 13 Feb 2023 • Mohanad Odema, James Ferlez, Goli Vaisi, Yasser Shoukry, Mohammad Abdullah Al Faruque
To mitigate the high energy demand of Neural Network (NN) based Autonomous Driving Systems (ADSs), we consider the problem of offloading NN controllers from the ADS to nearby edge-computing infrastructure, but in such a way that formal vehicle safety properties are guaranteed.
no code implementations • 22 Nov 2022 • Wael Fatnassi, Haitham Khedr, Valen Yamamoto, Yasser Shoukry
Bernstein polynomials enjoy several interesting properties that allow BERN-NN to obtain tighter bounds compared to those relying on linear and convex approximations.
no code implementations • 20 Sep 2022 • James Ferlez, Yasser Shoukry
In this paper, we consider the computational complexity of bounding the reachable set of a Linear Time-Invariant (LTI) system controlled by a Rectified Linear Unit (ReLU) Two-Level Lattice (TLL) Neural Network (NN) controller.
no code implementations • 20 May 2022 • Haitham Khedr, Yasser Shoukry
We propose a fairness loss that can be used during training to enforce fair outcomes for similar individuals.
no code implementations • 11 Apr 2022 • Wael Fatnassi, Yasser Shoukry
Constraints solvers play a significant role in the analysis, synthesis, and formal verification of complex embedded and cyber-physical systems.
Logic in Computer Science Systems and Control Systems and Control
no code implementations • 29 Mar 2022 • Ulices Santa Cruz, Yasser Shoukry
A central challenge for the safety and liveness verification of vision-based closed-loop systems is the lack of mathematical models that captures the relation between the system states (e. g., position of the aircraft) and the images processed by the vision-based NN controller.
no code implementations • 17 Nov 2021 • James Ferlez, Haitham Khedr, Yasser Shoukry
In this paper, we present the tool Fast Box Analysis of Two-Level Lattice Neural Networks (Fast BATLLNN) as a fast verifier of box-like output constraints for Two-Level Lattice (TLL) Neural Networks (NNs).
no code implementations • 17 Nov 2021 • Xiaowu Sun, Yasser Shoukry
In this paper, we introduce NNSynth, a new framework that uses machine learning techniques to guide the design of abstraction-based controllers with correctness guarantees.
no code implementations • 21 Sep 2021 • James Ferlez, Yasser Shoukry
In this paper, we consider the problem of automatically designing a Rectified Linear Unit (ReLU) Neural Network (NN) architecture (number of layers and number of neurons per layer) with the assurance that it is sufficiently parametrized to control a nonlinear system; i. e. control the system to satisfy a given formal specification.
no code implementations • 3 Sep 2021 • Xiaowu Sun, Wael Fatnassi, Ulices Santa Cruz, Yasser Shoukry
While conventional reinforcement learning focuses on designing agents that can perform one task, meta-learning aims, instead, to solve the problem of designing agents that can generalize to different tasks (e. g., environments, obstacles, and goals) that were not considered during the design or the training of these agents.
no code implementations • 6 Apr 2021 • Ulices Santa Cruz, James Ferlez, Yasser Shoukry
In this paper, we consider the problem of repairing a data-trained Rectified Linear Unit (ReLU) Neural Network (NN) controller for a discrete-time, input-affine system.
no code implementations • 22 Feb 2021 • Xiaowu Sun, Yasser Shoukry
In this paper, we consider the problem of training neural network (NN) controllers for nonlinear dynamical systems that are guaranteed to satisfy safety and liveness (e. g., reach-avoid) properties.
no code implementations • 12 Jan 2021 • Wael Fatnassi, Yasser Shoukry
Third, it allows for a highly parallelizable usage of off-the-shelf solvers to analyze the regions in which the convex relaxation failed to provide solutions.
Optimization and Control Systems and Control Systems and Control
no code implementations • 22 Dec 2020 • James Ferlez, Yasser Shoukry
Specifically, we show that for two different NN architectures -- shallow NNs and Two-Level Lattice (TLL) NNs -- the verification problem with (convex) polytopic constraints is polynomial in the number of neurons in the NN to be verified, when all other aspects of the verification problem held fixed.
1 code implementation • 18 Jun 2020 • Haitham Khedr, James Ferlez, Yasser Shoukry
However, unique in our approach is the way we use a convex solver not only as a linear feasibility checker, but also as a means of penalizing the amount of relaxation allowed in solutions.
no code implementations • 16 Jun 2020 • James Ferlez, Mahmoud Elnaggar, Yasser Shoukry, Cody Fleming
In this paper, we consider the problem of creating a safe-by-design Rectified Linear Unit (ReLU) Neural Network (NN), which, when composed with an arbitrary control NN, makes the composition provably safe.
no code implementations • 20 Apr 2020 • James Ferlez, Xiaowu Sun, Yasser Shoukry
In this paper, we consider the problem of automatically designing a Rectified Linear Unit (ReLU) Neural Network (NN) architecture (number of layers and number of neurons per layer) with the guarantee that it is sufficiently parametrized to control a nonlinear system.
no code implementations • 5 Nov 2019 • James Ferlez, Yasser Shoukry
In this paper, we consider the problem of automatically designing a Rectified Linear Unit (ReLU) Neural Network (NN) architecture that is sufficient to implement the optimal Model Predictive Control (MPC) strategy for an LTI system with quadratic cost.
no code implementations • 31 Oct 2018 • Xiaowu Sun, Haitham Khedr, Yasser Shoukry
In this paper, we consider the problem of formally verifying the safety of an autonomous robot equipped with a Neural Network (NN) controller that processes LiDAR images to produce control actions.
1 code implementation • 7 Sep 2018 • Andreea B. Alexandru, Konstantinos Gatsis, Yasser Shoukry, Sanjit A. Seshia, Paulo Tabuada, George J. Pappas
The development of large-scale distributed control systems has led to the outsourcing of costly computations to cloud-computing platforms, as well as to concerns about privacy of the collected sensitive data.
Optimization and Control Cryptography and Security Systems and Control