Search Results for author:
Found 23 papers, 3 papers with code
DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation
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?
Model Extraction Attacks Against Reinforcement Learning Based Controllers
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.
SEO: Safety-Aware Energy Optimization Framework for Multi-Sensor Neural Controllers at the Edge
Runtime energy management has become quintessential for multi-sensor autonomous systems at the edge for achieving high performance given the platform constraints.
EnergyShield: Provably-Safe Offloading of Neural Network Controllers for Energy Efficiency
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.
BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic
Bernstein polynomials enjoy several interesting properties that allow BERN-NN to obtain tighter bounds compared to those relying on linear and convex approximations.
Polynomial-Time Reachability for LTI Systems with Two-Level Lattice Neural Network Controllers
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.
CertiFair: A Framework for Certified Global Fairness of Neural Networks
We propose a fairness loss that can be used during training to enforce fair outcomes for similar individuals.
PolyARBerNN: A Neural Network Guided Solver and Optimizer for Bounded Polynomial Inequalities
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
NNLander-VeriF: A Neural Network Formal Verification Framework for Vision-Based Autonomous Aircraft Landing
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.
NNSynth: Neural Network Guided Abstraction-Based Controller Synthesis for Stochastic Systems
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.
Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networks
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).
Assured Neural Network Architectures for Control and Identification of Nonlinear Systems
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.
Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach
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.
Safe-by-Repair: A Convex Optimization Approach for Repairing Unsafe Two-Level Lattice Neural Network Controllers
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.
Provably Correct Training of Neural Network Controllers Using Reachability Analysis
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.
PolyAR: A Highly Parallelizable Solver For Polynomial Inequality Constraints Using Convex Abstraction Refinement
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
Bounding the Complexity of Formally Verifying Neural Networks: A Geometric Approach
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.
PEREGRiNN: Penalized-Relaxation Greedy Neural Network Verifier
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.
ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers
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.
Two-Level Lattice Neural Network Architectures for Control of Nonlinear Systems
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.
AReN: Assured ReLU NN Architecture for Model Predictive Control of LTI Systems
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.
Formal Verification of Neural Network Controlled Autonomous Systems
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.
Cloud-based Quadratic Optimization with Partially Homomorphic Encryption
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
