Abstract Agents in cyber-physical systems are increasingly entrusted with safety-critical tasks. Ensuring the safety of these agents often requires localizing their pose for subsequent actions. Pose estimates can, e.g., be obtained from various combinations of lidar sensors, cameras, and external services such as GPS. Crucially, in safety-critical domains, a rough estimate is insufficient to formally determine safety, i.e., to guarantee safety even in extreme scenarios, and external services may additionally be untrustworthy. We address this problem by presenting an approach for certified pose estimation in 3D solely from a camera image and a well-known target geometry. This is realized by formally bounding the pose, which is computed by leveraging recent results from reachability analysis and formal neural network verification. Our experiments demonstrate that our approach efficiently and accurately localizes agents in both synthetic and real-world experiments.

Training Neural Networks (NNs) to serve as Barrier Functions (BFs) is a popular way to improve the safety of autonomous dynamical systems. Despite significant practical success, these methods are not generally guaranteed to produce true BFs in a provable sense, which undermines their intended use as safety certificates. In this paper, we consider the problem of formally certifying a learned NN as a BF with respect to state avoidance for an autonomous system: viz. computing a region of the state space on which the candidate NN is provably a BF. In particular, we propose a sound algorithm that efficiently produces such a certificate set for a shallow NN. Our algorithm combines two novel approaches: it first uses NN reachability tools to identify a subset of states for which the output of the NN does not increase along system trajectories; then, it uses a novel enumeration algorithm for hyperplane arrangements to find the intersection of the NN's zero-sub-level set with the first set of states. Thus, our algorithm soundly finds a subset of states on which the NN is certified as a BF. We demonstrate the effectiveness of our algorithm via scalability experiments and two case studies.

Formal certification of Neural Networks (NNs) is crucial for ensuring their safety, fairness, and robustness. Unfortunately, on the one hand, sound and complete certification algorithms of ReLU-based NNs do not scale to large-scale NNs. On the other hand, incomplete certification algorithms are easier to compute, but they result in loose bounds that deteriorate with the depth of NN, which diminishes their effectiveness. 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? We introduce DeepBern-Nets, a class of NNs with activation functions based on Bernstein polynomials instead of the commonly used ReLU activation. Bernstein polynomials are smooth and differentiable functions with desirable properties such as the so-called range enclosure and subdivision properties. We design a novel Interval Bound Propagation (IBP) algorithm, called Bern-IBP, to efficiently compute tight bounds on DeepBern-Nets outputs. Our approach leverages the properties of Bernstein polynomials to improve the tractability of neural network certification tasks while maintaining the accuracy of the trained networks. We conduct experiments in adversarial robustness and reachability analysis settings to assess the effectiveness of the approach. Our proposed framework achieves high certified accuracy for adversarially-trained NNs, which is often a challenging task for certifiers of ReLU-based NNs. This work establishes Bernstein polynomial activation as a promising alternative for improving NN certification tasks across various NNs applications.

Neural networks have emerged as powerful tools across various domains, exhibiting remarkable empirical performance that motivated their widespread adoption in safety-critical applications, which, in turn, necessitates rigorous formal verification techniques to ensure their reliability and robustness. Tight bound propagation plays a crucial role in the formal verification process by providing precise bounds that can be used to formulate and verify properties, such as safety, robustness, and fairness. While state-of-the-art tools use linear and convex approximations to compute upper/lower bounds for each neuron’s outputs, recent advances have shown that nonlinear approximations based on Bernstein polynomials lead to tighter bounds but suffer from scalability issues. To that end, this article introduces BERN-NN-IBF, a significant enhancement of the Bernstein-polynomial-based bound propagation algorithms. BERN-NN-IBF offers three main contributions: 1) a memory-efficient encoding of Bernstein polynomials to scale the bound propagation algorithms; 2) optimized tensor operations for the new polynomial encoding to maintain the integrity of the bounds while enhancing computational efficiency; and 3) tighter under-approximations of the ReLU activation function using quadratic polynomials tailored to minimize approximation errors. Through comprehensive testing, we demonstrate that BERN-NN-IBF achieves tighter bounds and higher computational efficiency compared to the original BERN-NN and state-of-the-art methods, including linear and convex programming used within the winner of the VNN-COMPETITION.

Constraints solvers play a significant role in the analysis, synthesis, and formal verification of complex cyber-physical systems. In this article, we study the problem of designing a scalable constraints solver for an important class of constraints named polynomial constraint inequalities (also known as nonlinear real arithmetic theory). In this article, we introduce a solver named PolyARBerNN that uses convex polynomials as abstractions for highly nonlinears polynomials. Such abstractions were previously shown to be powerful to prune the search space and restrict the usage of sound and complete solvers to small search spaces. Compared with the previous efforts on using convex abstractions, PolyARBerNN provides three main contributions namely (i) a neural network guided abstraction refinement procedure that helps selecting the right abstraction out of a set of pre-defined abstractions, (ii) a Bernstein polynomial-based search space pruning mechanism that can be used to compute tight estimates of the polynomial maximum and minimum values which can be used as an additional abstraction of the polynomials, and (iii) an optimizer that transforms polynomial objective functions into polynomial constraints (on the gradient of the objective function) whose solutions are guaranteed to be close to the global optima. These enhancements together allowed the PolyARBerNN solver to solve complex instances and scales more favorably compared to the state-of-the-art nonlinear real arithmetic solvers while maintaining the soundness and completeness of the resulting solver. In particular, our test benches show that PolyARBerNN achieved 100X speedup compared with Z3 8.9, Yices 2.6, and PVS (a solver that uses Bernstein expansion to solve multivariate polynomial constraints) on a variety of standard test benches. Finally, we implemented an optimizer called PolyAROpt that uses PolyARBerNN to solve constrained polynomial optimization problems. Numerical results show that PolyAROpt is able to solve high-dimensional and high order polynomial optimization problems with higher speed compared to the built-in optimizer in the Z3 8.9 solver.

This paper presents a neurosymbolic framework to solve motion planning problems for mobile robots involving temporal goals. The temporal goals are described using temporal logic formulas such as Bounded Linear Temporal Logic (BLTL) and co-safe LTL (scLTL) to capture complex tasks. The proposed framework trains Neural Network (NN)-based planners that enjoy strong correctness guarantees when applying to unseen tasks, i.e., the exact task (including workspace, temporal logic formula, and errors in the dynamical models of the robot) is not available during the training of NNs. Our approach to achieving theoretical guarantees and computational efficiency is based on two insights. First, we incorporate a symbolic model into the training of NNs such that the resulting NN-based planner inherits the interpretability and correctness guarantees of the symbolic model. Moreover, the symbolic model serves as a discrete “memory”, which is necessary for satisfying temporal logic formulas. Second, we train a library of neural networks offline and combine a subset of the trained NNs into a single NN-based planner at runtime when a task is revealed. In particular, we develop a novel constrained NN training procedure, named formal NN training, to enforce that each neural network in the library represents a “symbol” in the symbolic model. As a result, our neurosymbolic framework enjoys the scalability and flexibility benefits of machine learning and inherits the provable guarantees from control-theoretic and formal-methods techniques. We demonstrate the effectiveness of our framework in both simulations and on an actual robotic vehicle and show that our framework can generalize to unseen tasks where state-of-the-art meta-reinforcement learning techniques fail.

We consider the problem of whether a Neural Network (NN) model satisfies global individual fairness. Individual Fairness (defined in (Dwork et al. 2012)) suggests that similar individuals with respect to a certain task are to be treated similarly by the decision model. In this work, we have two main objectives. The first is to construct a verifier which checks whether the fairness property holds for a given NN in a classification task or provides a counterexample if it is violated, i.e., the model is fair if all similar individuals are classified the same, and unfair if a pair of similar individuals are classified differently. To that end, we construct a sound and complete verifier that verifies global individual fairness properties of ReLU NN classifiers using distance-based similarity metrics. The second objective of this paper is to provide a method for training provably fair NN classifiers from unfair (biased) data. We propose a fairness loss that can be used during training to enforce fair outcomes for similar individuals. We then provide provable bounds on the fairness of the resulting NN. We run experiments on commonly used fairness datasets that are publicly available and we show that global individual fairness can be improved by 96 % without a significant drop in test accuracy.

Runtime energy management has become quintessential for multi-sensor autonomous systems at the edge for achieving high performance given the platform constraints. Typical for such systems, however, is to have their controllers designed with formal guarantees on safety that precede in priority such optimizations, which in turn limits their application in real settings. In this paper, we propose a novel energy optimization framework that is aware of the autonomous system’s safety state, and leverages it to regulate the application of energy optimization methods so that the system’s formal safety properties are preserved. In particular, through the formal characterization of a system’s safety state as a dynamic processing deadline, the computing workloads of the underlying models can be adapted accordingly. For our experiments, we model two popular runtime energy optimization methods, offloading and gating, and simulate an autonomous driving system (ADS) use-case in the CARLA simulation environment with performance characterizations obtained from the standard Nvidia Drive PX2 ADS platform. Our results demonstrate that through a formal awareness of the perceived risks in the test case scenario, energy efficiency gains are still achieved (reaching 89.9%) while maintaining the desired safety properties.

In this paper, we present BERN-NN as an efficient tool to perform bound propagation of Neural Networks (NNs). Bound propagation is a critical step in wide range of NN model checkers and reachability analysis tools. Given a bounded input set, bound propagation algorithms aim to compute tight bounds on the output of the NN. So far, linear and convex optimizations have been used to perform bound propagation. Since neural networks are highly non-convex, state-of-the-art bound propagation techniques suffer from introducing large errors. To circumvent such drawback, BERN-NN approximates the bounds of each neuron using a class of polynomials called Bernstein polynomials. Bernstein polynomials enjoy several interesting properties that allow BERN-NN to obtain tighter bounds compared to those relying on linear and convex approximations. BERN-NN is efficiently parallelized on graphic processing units (GPUs). Extensive numerical results show that bounds obtained by BERN-NN are orders of magnitude tighter than those obtained by state-of-the-art verifiers such as linear programming and linear interval arithmetic. Moreoveer, BERN-NN is both faster and produces tighter outputs compared to convex programming approaches like alpha-CROWN.

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). In particular, Fast BATLLNN can verify whether the output of a given TLL NN always lies within a specified hyper-rectangle whenever its input is constrained to a specified convex polytope (not necessarily a hyper-rectangle). Fast BATLLNN uses the unique semantics of the TLL architecture and the decoupled nature of box-like output constraints to dramatically improve verification performance relative to known polynomial-time verification algorithms for TLLs with generic polytopic output constraints. In this paper, we evaluate the performance and scalability of Fast BATLLNN, both in its own right and compared to state-of-the-art NN verifiers applied to TLL NNs. Fast BATLLNN compares very favorably to even the fastest NN verifiers, completing our synthetic TLL test bench more than 400x faster than its nearest competitor.

Abstract Neural Networks (NNs) have increasingly apparent safety implications commensurate with their proliferation in real-world applications: both unanticipated as well as adversarial misclassifications can result in fatal outcomes. As a consequence, techniques of formal verification have been recognized as crucial to the design and deployment of safe NNs. In this paper, we introduce a new approach to formally verify the most commonly considered safety specifications for ReLU NNs – i.e. polytopic specifications on the input and output of the network. Like some other approaches, ours uses a relaxed convex program to mitigate the combinatorial complexity of the problem. 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. In particular, we encode each ReLU by means of the usual linear constraints, and combine this with a convex objective function that penalizes the discrepancy between the output of each neuron and its relaxation. This convex function is further structured to force the largest relaxations to appear closest to the input layer; this provides the further benefit that the most “problematic” neurons are conditioned as early as possible, when conditioning layer by layer. This paradigm can be leveraged to create a verification algorithm that is not only faster in general than competing approaches, but is also able to verify considerably more safety properties; we evaluated PEREGRiNN on a standard MNIST robustness verification suite to substantiate these claims.

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. Specifically, we propose AReN, an algorithm to generate Assured ReLU Architectures. AReN takes as input an LTI system with quadratic cost specification, and outputs a ReLU NN architecture with the assurance that there exist network weights that exactly implement the associated MPC controller. AReN thus offers new insight into the design of ReLU NN architectures for the control of LTI systems: instead of training a heuristically chosen NN architecture on data - or iterating over many architectures until a suitable one is found - AReN can suggest an adequate NN architecture before training begins. While several previous works were inspired by the fact that ReLU NN controllers and optimal MPC controllers are both Continuous, Piecewise-Linear (CPWL) functions, exploiting this similarity to design NN architectures with correctness guarantees has remained elusive. AReN achieves this using two novel features. First, we reinterpret a recent result about the implementation of CPWL functions via ReLU NNs to show that a CPWL function may be implemented by a ReLU architecture that is determined by the number of distinct affine regions in the function. Second, we show that we can efficiently over-approximate the number of affine regions in the optimal MPC controller without solving the MPC problem exactly. Together, these results connect the MPC problem to a ReLU NN implementation without explicitly solving the MPC: the result is a NN architecture that has the assurance that it can implement the MPC controller. We show through numerical results the effectiveness of AReN in designing an NN architecture.

Accurate localization from Cyber-Physical Systems (CPS) is a critical enabling technology for context-aware applications and control. As localization plays an increasingly safety-critical role, location systems must be able to identify and eliminate faulty measurements to prevent dangerously inaccurate localization. In this article, we consider the range-based localization problem and propose a method to detect coordinated adversarial corruption on anchor positions and distance measurements. Our algorithm, G ordian , rapidly finds attacks by identifying geometric inconsistencies at the graph level without requiring assumptions about hardware, ranging mechanisms, or cryptographic protocols. We give necessary conditions for which attack detection is guaranteed to be successful in the noiseless case, and we use that intuition to extend G ordian to the noisy case where fewer guarantees are possible. In simulations generated from real-world sensor noise, we empirically show that G ordian ’s trilateration counterexample generation procedure enables rapid attack detection even for combinatorially difficult problems.

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. Given a workspace that is characterized by a set of polytopic obstacles, our objective is to compute the set of safe initial states such that a robot trajectory starting from these initial states is guaranteed to avoid the obstacles. Our approach is to construct a finite state abstraction of the system and use standard reachability analysis over the finite state abstraction to compute the set of safe initial states. To mathematically model the imaging function, that maps the robot position to the LiDAR image, we introduce the notion of imaging-adapted partitions of the workspace in which the imaging function is guaranteed to be affine. Given this workspace partitioning, a discrete-time linear dynamics of the robot, and a pre-trained NN controller with Rectified Linear Unit (ReLU) non-linearity, we utilize a Satisfiability Modulo Convex (SMC) encoding to enumerate all the possible assignments of different ReLUs. To accelerate this process, we develop a pre-processing algorithm that could rapidly prune the space of feasible ReLU assignments. Finally, we demonstrate the efficiency of the proposed algorithms using numerical simulations with the increasing complexity of the neural network controller.

We propose an efficient multi-robot motion planning algorithm for missions captured by linear temporal logic (LTL) specifications, in the presence of bounded disturbances and denial-of-service (DoS) attacks against the communication between robots and base stations. Given an LTL formula Ψ, our goal is to construct robot trajectories, and associated control strategies, to satisfy Ψ and continuously establish communication paths between robots and base stations despite the DoS attacks and the disturbances on the robot states. Our approach combines and extends results from robust control and efficient motion planning via satisfiability modulo convex programming (SMC). We first compute a feedback controller that rejects the disturbance together with a perturbation of the DoS-free workspace that accounts for the worst-case disturbance scenario. On the perturbed workspace, we formulate the planning problem as a feasibility problem over Boolean and convex constraints, respectively capturing the DoS-resilient mission constraints and the constraints on the nominal, disturbance-free, robot dynamics. Numerical results show the effectiveness of our algorithm in providing DoS-resilient plans that are robust to disturbances and support the execution of complex missions.

This paper surveys recent challenges and solutions in the design, implementation, and verification of embedded software for robotics. Emphasis is placed on mobile robots, like self-driving cars. In design, it addresses programming support for robotic systems, secure state estimation, and ROS-based monitor generation. In the implementation phase, it describes the synthesis of control software using finite precision arithmetic, real-time platforms and architectures for safety-critical robotics, efficient implementation of neural network based-controllers, and standards for computer vision applications. The issues in verification include verification of neural network-based robotic controllers, and falsification of closed-loop control systems. The paper also describes notable open-source robotic platforms. Along the way, we highlight important research problems for developing the next generation of high-performance, low-resource-usage, correct embedded software.

The design of cyber-physical systems (CPSs) requires methods and tools that can efficiently reason about the interaction between discrete models, e.g., representing the behaviors of “cyber” components, and continuous models of physical processes. Boolean methods such as satisfiability (SAT) solving are successful in tackling large combinatorial search problems for the design and verification of hardware and software components. On the other hand, problems in control, communications, signal processing, and machine learning often rely on convex programming as a powerful solution engine. However, despite their strengths, neither approach would work in isolation for CPSs. In this paper, we present a new satisfiability modulo convex programming (SMC) framework that integrates SAT solving and convex optimization to efficiently reason about Boolean and convex constraints at the same time. We exploit the properties of a class of logic formulas over Boolean and nonlinear real predicates, termed monotone satisfiability modulo convex formulas, whose satisfiability can be checked via a finite number of convex programs. Following the lazy satisfiability modulo theory (SMT) paradigm, we develop a new decision procedure for monotone SMC formulas, which coordinates SAT solving and convex programming to provide a satisfying assignment or determine that the formula is unsatisfiable. A key step in our coordination scheme is the efficient generation of succinct infeasibility proofs for inconsistent constraints that can support conflict-driven learning and accelerate the search. We demonstrate our approach on different CPS design problems, including spacecraft docking mission control, robotic motion planning, and secure state estimation. We show that SMC can handle more complex problem instances than state-of-the-art alternative techniques based on SMT solving and mixed integer convex programming.

We introduce a scalable observer architecture, which can efficiently estimate the states of a discrete-time linear-time-invariant system whose sensors are manipulated by an attacker, and is robust to measurement noise. Given an upper bound on the number of attacked sensors, we build on previous results on necessary and sufficient conditions for state estimation, and propose a novel Multi-Modal Luenberger (MML) observer based on efficient Satisfiability Modulo Theory (SMT) solving. We present two techniques to reduce the complexity of the estimation problem. As a first strategy, instead of a bank of distinct observers, we use a family of filters sharing a single dynamical equation for the states, but different output equations, to generate estimates corresponding to different subsets of sensors. Such an architecture can reduce the memory usage of the observer from an exponential to a linear function of the number of sensors. We then develop an efficient SMT-based decision procedure that is able to reason about the estimates of the MML observer to detect at runtime which sets of sensors are attack-free, and use them to obtain a correct state estimate. Finally, we discuss two optimization-based algorithms that can efficiently select the observer parameters with the goal of minimizing the sensitivity of the estimates with respect to sensor noise. We provide proofs of convergence for our estimation algorithm and report simulation results to compare its runtime performance with alternative techniques. We show that our algorithm scales well for large systems (including up to 5,000 sensors) for which many previously proposed algorithms are not implementable due to excessive memory and time requirements. Finally, we illustrate the effectiveness of our approach, both in terms of resiliency to attacks and robustness to noise, on the design of large-scale power distribution networks.

We address the problem of determining the satisfiability of a Boolean combination of convex constraints over the real numbers, which is common in the context of hybrid system verification and control. We first show that a special type of logic formulas, termed monotone Satisfiability Modulo Convex (SMC) formulas, is the most general class of formulas over Boolean and nonlinear real predicates that reduce to convex programs for any satisfying assignment of the Boolean variables. For this class of formulas, we develop a new satisfiability modulo convex optimization procedure that uses a lazy combination of SAT solving and convex programming to provide a satisfying assignment or determine that the formula is unsatisfiable. Our approach can then leverage the efficiency and the formal guarantees of state-of-the-art algorithms in both the Boolean and convex analysis domains. A key step in lazy satisfiability solving is the generation of succinct infeasibility proofs that can support conflict-driven learning and decrease the number of iterations between the SAT and the theory solver. For this purpose, we propose a suite of algorithms that can trade complexity with the minimality of the generated infeasibility certificates. Remarkably, we show that a minimal infeasibility certificate can be generated by simply solving one convex program for a sub-class of SMC formulas, namely ordered positive unate SMC formulas, that have additional monotonicity properties. Perhaps surprisingly, ordered positive unate formulas appear themselves very frequently in a variety of practical applications. By exploiting the properties of monotone SMC formulas, we can then build and demonstrate effective and scalable decision procedures for problems in hybrid system verification and control, including secure state estimation and robotic motion planning.

This demo abstract presents PrOLoc, a localization system that combines partially homomorphic encryption with a new way of structuring the localization problem to enable efficient and accurate computation of a target's location while preserving the privacy of the observers.

Aided by advances in sensors and algorithms, systems for localizing and tracking target objects or events have become ubiquitous in recent years. Most of these systems operate on the principle of fusing measurements of distance and/or direction to the target made by a set of spatially distributed observers using sensors that measure signals such as RF, acoustic, or optical. The computation of the target's location is done using multilateration and multiangulation algorithms, typically running at an aggregation node that, in addition to the distance/direction measurements, also needs to know the observers' locations. This presents a privacy risk for an observer that does not trust the aggregation node or other observers and could in turn lead to lack of participation. For example, consider a crowd-sourced sensing system where citizens are required to report security threats, or a smart car, stranded with a malfunctioning GPS, sending out localization requests to neighboring cars - in both cases, observer (i.e., citizens and cars respectively) participation can be increased by keeping their location private. This paper presents PrOLoc, a localization system that combines partially homomorphic encryption with a new way of structuring the localization problem to enable efficient and accurate computation of a target's location without requiring observers to make public their locations or measurements. Moreover, and unlike previously proposed perturbation based techniques, PrOLoc is also resilient to malicious active false data injection attacks. We present two realizations of our approach, provide rigorous theoretical guarantees, and also compare the performance of each against traditional methods. Our experiments on real hardware demonstrate that PrOLoc yields location estimates that are accurate while being at least 500x faster than state-of-art secure function evaluation techniques.

Embedded sensing systems are pervasively used in life- and security-critical systems such as those found in airplanes, automobiles, and healthcare. Traditional security mechanisms for these sensors focus on data encryption and other post-processing techniques, but the sensors themselves often remain vulnerable to attacks in the physical/analog domain. If an adversary manipulates a physical/analog signal prior to digitization, no amount of digital security mechanisms after the fact can help. Fortunately, nature imposes fundamental constraints on how these analog signals can behave. This work presents PyCRA, a physical challenge-response authentication scheme designed to protect active sensing systems against physical attacks occurring in the analog domain. PyCRA provides secure active sensing by continually challenging the surrounding environment via random but deliberate physical probes. By analyzing the responses to these probes, the system is able to ensure that the underlying physics involved are not violated, providing an authentication mechanism that not only detects malicious attacks but provides resilience against them. We demonstrate the effectiveness of PyCRA in detecting and mitigating attacks through several case studies using two sensing systems: (1) magnetic sensors like those found on gear and wheel speed sensors in robotics and automotive, and (2) commercial Radio Frequency Identification (RFID) tags used in many security-critical applications. In doing so, we evaluate both the robustness and the limitations of the PyCRA security scheme, concluding by outlining practical considerations as well as further applications for the proposed authentication mechanism.

Motivated by the need to secure cyber-physical systems against attacks, we consider the problem of estimating the state of a noisy linear dynamical system when a subset of sensors is arbitrarily corrupted by an adversary. We propose a secure state estimation algorithm and derive (optimal) bounds on the achievable state estimation error. In addition, as a result of independent interest, we give a coding theoretic interpretation for prior work on secure state estimation against sensor attacks in a noiseless dynamical system.

Robustness is the property that a system only exhibits small deviations from the nominal behavior upon the occurrence of small disturbances. While the importance of robustness in engineering design is well accepted, it is less clear how to verify and design discrete systems for robustness. We present a theory of input-output robustness for discrete systems inspired by existing notions of input-output stability (IO-stability) in continuous control theory. We show that IO-stability captures two intuitive goals of robustness: bounded disturbances lead to bounded deviations from nominal behavior, and the effect of a sporadic disturbance disappears in finitely many steps. We show that existing notions of robustness for discrete systems do not have these two properties. For systems modeled as finite-state transducers, we show that IO-stability can be verified and the synthesis problem can be solved in polynomial time. We illustrate our theory using a reference broadcast synchronization protocol for wireless networks.