Searcharxiv⌕ Search

arXiv subjects

Majid Zamani

Publications and source records attributed to Majid Zamani.

At least 19 recordsLinked to original sources

Scalable Neural Safety Certification via Monotonicity

Learning-based safety certification offers a promising route for verifying complex dynamical systems when explicit models are unavailable, but existing data-driven methods often scale poorly: they treat the system as a black box, rely on dense discretizations or Lipschitz bounds, and consequently suffer from sample complexity that grows exponentially with dimension. This paper shows that a common structural property of dynamical systems--monotonicity--can be used to break this curse of dimensionality. We develop a data-driven framework for robust safety verification and safe controller synthesis for unknown monotone systems using only simulator queries. Our main theoretical result proves that, for monotone systems with upper-closed unsafe sets, safety is completely characterized by the existence of monotone inductive barrier certificates. This structure reduces certificate verification over continuous state spaces to localized boundary checks over finitely many cells. To learn such certificates, we introduce Max-Monotone Networks, a monotone neural architecture with universal approximation guarantees for monotone functions. We then propose a training and refinement algorithm that, upon successful termination, returns formally valid neural barrier certificates and, under mild partition assumptions, requires only $O(n)$ simulator queries. Across high-dimensional benchmarks, including oscillator networks with up to $13{,}659$ states and traffic networks with $1{,}000$ states, our method certifies safety in regimes where prior approaches either do not converge or exceed memory limits. These results demonstrate that exploiting order structure can make neural safety certification both scalable and formally sound.

eess.SY↗

FoSeRL: Formal Sequential Robustness Certification for Reinforcement Learning Policies

Even a few action perturbations can substantially degrade the performance of a deployed decision policy. Certifying the resulting return loss is challenging in stochastic environments, where returns vary even without an attack. We introduce FoSeRL, a framework for certifying deployed RL policies against precommitted, temporally sparse action attacks. The deployed policy is unchanged, with no smoothing or retraining. Certification requires a resettable simulator supporting shared randomness and independent one-step successor queries, but no analytical dynamics model. FoSeRL certifies that an attacked episode loses no more than a prescribed amount of return relative to the same episode unattacked, with at least a target probability and at a user-specified confidence level. Both runs share the initial state and randomness, so the measured loss reflects the attack, not the episode; carrying the running return gap as a state coordinate makes it the terminal value, reducing trajectory-level certification to terminal safety. Time-dependent barrier conditions on the augmented state bound the terminal failure probability: satisfied exactly, they certify every admissible precommitted attack; learned from sampled trajectories and verified on held-out data, they certify the same guarantee under a specified attack-episode setting. Across six stochastic continuous-control environments and three RL policy families (TD3, SAC, and PPO), FoSeRL certifies non-trivial cardinality--magnitude robustness frontiers, achieves substantially larger certified budgets than policy smoothing, and reveals marked robustness differences among policies with comparable nominal performance.

cs.LG↗

Data-Driven Compositional Safety Verification of Interconnected Monotone Systems

This paper introduces a sample-efficient compositional method for formal safety verification of interconnected monotone systems without requiring explicit models of the local subsystems. Existing data-driven approaches either lack formal safety guarantees or rely on dense Lipschitz-based discretizations of the state space to provide such guarantees, which leads to significant computational overhead and limits scalability. In contrast, we leverage the monotonicity of local subsystems to construct tractable local interval-barrier certificates using only boundary evaluations of each subsystem in a decentralized manner, together with a global condition that guarantees the safety of the overall interconnected system. At the local level, our framework learns interval-barrier certificates using monotone neural networks from boundary samples induced by partitions of the local state and internal-input spaces. At the global level, it composes these local neural interval-barrier certificates using the interconnection structure to certify the safety of the overall system. Furthermore, under appropriate structural assumptions, we reformulate the global safety condition into a scalable form that can be directly incorporated into the neural network loss. This enables the enforcement of overall system safety during local training. The experimental results demonstrate the effectiveness and scalability of the proposed method.

eess.SY↗

Real-Time Synthesis of Robust Controlled Invariant Sets for Monotone Systems

Safety-critical control of autonomous systems requires formal safety certificates, such as controlled invariant sets, that must be computed online as conditions change. Although standard synthesis algorithms scale poorly with state dimension, monotone dynamical systems with lower-closed safety specifications allow for accelerated computation of controlled invariant sets. In particular, lazy fixed-point algorithms exploit monotonicity and track only the antichain basis of the set. However, membership tests and redundancy checks against an evolving basis remain major bottlenecks. We introduce a threshold-function reformulation in which a lower-closed set on a d-dimensional grid is represented by its column heights along a designated axis. This reformulates the greatest-fixed-point iteration as independent one-dimensional binary searches, one per grid column, yielding an embarrassingly parallel iteration with asymptotically lower computational complexity than the lazy fixed-point algorithm. Experiments synthesize invariant sets on 3D grids with 10^9 cells in under 50 ms and 10^14 cells in under two minutes. We further demonstrate online re-synthesis in a safety-informed model predictive controller example.

eess.SY↗

Hierarchical Control for Continuous-time Systems via General Approximate Alternating Simulation Relations

This paper introduces a general approximate alternating simulation relation (\emph{$\varepsilon$-gAAS relation}) for continuous-time systems, which relaxes existing simulation relations to tolerate larger mismatches between abstract and concrete models. The definition of gAAS for continuous-time systems is first proposed, and its properties are investigated. Then, a control refinement method is developed to enable hierarchical control for the gAAS relation. Finally, case studies demonstrate the effectiveness of the proposed approach, highlighting its advantages over existing methods.

eess.SY↗

Data-Driven Formal Methods for Complex Dynamical Systems: A Survey

Data-driven approaches with formal guarantees have recently emerged as a powerful means for the verification and controller synthesis of complex dynamical systems. Interest in these methods is rapidly growing, as system models are often unavailable in practice, and challenges such as nonlinear behavior, uncertainty, and the curse of dimensionality typically render accurate modeling infeasible. These difficulties motivate leveraging limited data collected from the system while still providing formal guarantees on its overall behavior. The community has therefore proposed a few hundred articles on the development of data-driven frameworks that enable the formal verification and synthesis of dynamical systems without explicit models, addressing complex specifications beyond stability. Despite this rapid growth, existing results remain scattered and lack a coherent organization, limiting a clear understanding of their principles, distinctions, and practical potential. This survey fills this gap by providing a comprehensive overview of these data-driven methods for both deterministic and stochastic dynamical systems. We structure the literature around three main methodological pillars in formal methods: (in)finite-abstraction-based techniques, functional certificate approaches, such as control barrier certificates, and compositional methods. For each of these approaches, we classify the resulting data-driven guarantees into three main categories: (i) statistical guarantees grounded in probably approximately correct and scenario-based frameworks, (ii) guarantees derived from Lipschitz continuity, and (iii) guarantees exploiting structural properties. While the literature on deterministic systems is considerably richer, we also devote particular attention to the stochastic counterpart, highlighting the inherent differences and challenges that arise compared to the deterministic case.

eess.SY↗

Robustness Certificates for Neural Networks Against Data Poisoning and Evasion Attacks

The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that corrupt training data to degrade performance or induce unsafe behavior. Most existing defenses lack formal guarantees or rely on restrictive assumptions about the model class, attack type, extent of poisoning, or point-wise certification, limiting their practical reliability. This paper introduces a principled formal robustness certification framework that models gradient-based training as a discrete-time dynamical system (dt-DS) and formulates poisoning robustness as a formal safety verification problem. By adapting the concept of barrier certificates (BCs) from control theory, we introduce sufficient conditions to certify a robust radius ensuring that the terminal model remains safe under worst-case ${\ell}_p$-norm-based poisoning. To make this practical, we parameterize BCs as neural networks trained on finite sets of poisoned trajectories. We further derive probably approximately correct (PAC) bounds by solving a scenario convex program (SCP), which yields a confidence lower bound on the certified robustness radius generalizing beyond the training set. Importantly, our framework also extends to certification against test-time attacks, making it the first unified framework to provide formal guarantees in both training and test-time attack settings. Experiments on MNIST, SVHN, CIFAR-10, and CIFAR-100 show that our approach certifies non-trivial perturbation budgets while being model-agnostic and requiring no prior knowledge of the attack or contamination level.

cs.LG↗

DBNN: Neural Spike Classification Using a Deep Binarized Neural Network

Implantable brain-computer interfaces require on-node spike sorting to reduce telemetry bandwidth and power while maintaining reliable neural decoding. This paper presents a hardware-oriented deep binarized neural network (DBNN) spike-sorting system with two binarized hidden layers with 256 neurons and a fixed-point output layer to enable multiplier-free inference dominated by sign-controlled accumulation and bit-wise logic. The proposed classifier operates on compact 16-sample spike waveforms to reduce the implementation cost (16-256-256-3) and achieves a median classification accuracy of 98.7% on both synthetic and in-vivo datasets. An FPGA prototype on a Cyclone V device operates at 50 MHz and requires 528 cycles per spike, corresponding to a 0.01 ms compute latency, while consuming 828 ALMs and 1023 registers with zero DSP blocks. For ASIC feasibility, the DBNN is implemented using FreePDK45-based flow; synthesis in Synopsys Design Compiler indicates an estimated silicon area of 0.014 mm2 and an operating power of 122 nW at 20 kHz under a 1.1 V supply. These results demonstrate that the proposed DBNN spike sorter offers a favorable trade-off between accuracy and implementation cost, supporting low-power, implantable neural interfaces. Overall, the proposed DBNN spike sorter achieves high accuracy (98.7%) with extremely low hardware cost (0.014 mm2, 122 nW at 20 kHz) and multiplier-free operation, making it suitable for low-power, implantable neural interfaces. This paper introduces the first DBNN designed for real-time neural spike sorting, striking an excellent balance between input data size and network complexity.

eess.SP↗

Trajectory-based Safety of Monotone Systems: Verification and Control Synthesis

This paper presents a novel data-driven framework for the robust safety verification and safe control synthesis of unknown monotone discrete-time systems. While existing data-driven safety analysis approaches are often either heuristic in nature or require large amounts of data to provide rigorous guarantees, we leverage the structural property of monotonicity to significantly reduce data requirements while still ensuring formal safety guarantees. Our approach is built upon a new class of certificates called dominance functions, constructed directly from collected system trajectories, which themselves need not be safe. By exploiting the monotone structure of the dynamics, we show that dominance functions are (i) dissipative, meaning that they decrease monotonically along system trajectories, and (ii) sufficiently \expressive to characterize safety certificates for monotone systems. Together, these properties establish dominance functions as principled building blocks for the systematic construction of formal safety certificates directly from trajectory data. For both robust safety verification and safe control synthesis, we develop an efficient sampling-based optimization framework that searches for safety certificates represented as linear combinations of dominance functions constructed from collected trajectories. We validate our data-driven framework on two monotone systems by successfully deriving safety certificates from a small number of trajectories.

eess.SY↗

HyperCertificates: Verification of Discrete-time Dynamical Systems against HyperLTL Specifications

We introduce a functional inductive framework to verify discrete-time dynamical systems against hyperproperties specified as Hyperlinear temporal logic formulae via a notion of HyperCertificates. Unlike linear temporal logic (LTL) formulae which are concerned with individual traces of a system, hyperproperties are properties that are concerned with how the traces of a system relate to one another. HyperLTL is an extension of LTL for hyperproperties, and is useful to describe specifications such as opacity, privacy as well as notions of robustness. Our notion of HyperCertificates consists of a pair of functions, where the first models the lookahead, and the second relies on a combination of barrier and ranking functions. We use closure certificates, to act as a model for this lookahead and then rely on barrier and ranking function arguments modulo this lookahead to provide guarantees against HyperLTL formulae. We demonstrate how our approach is automatable via existing techniques such as sum-of-squares optimization (SOS) and satisfiability modulo theories (SMT) solvers. Finally, we demonstrate our approach on some case studies.

eess.SY↗

Controlled Invariant Sets for Gaussian Process State Space Models

We compute probabilistic controlled invariant sets for nonlinear systems using Gaussian process state space models, which are data-driven models that account for unmodeled and unknown nonlinear dynamics. We propose a semidefinite programming scheme for designing state-feedback controllers that maximize the probability of the trajectories staying within a probabilistic controlled invariant set while satisfying input constraints. The results are validated on a quadrotor, both in simulation and on a physical platform.

eess.SY↗

Digital Guardians: The Past and The Future of Cyber-Physical Resilience

Resilience in cyber-physical systems (CPS) is the fundamental ability to maintain safety and critical functionality despite adverse "perturbations," which includes security attacks, environmental disruptions, and hardware or software failures. This survey provides a comprehensive review of CPS resilience, framing the field through five interconnected themes that are required in an integrated whole to achieve real-world resilience. The article first posits that resilience is a system-wide property emerging from interactions between hardware, software, and human users. Second, it addresses the challenges of learning-enabled CPS, which often operate in data-scarce environments characterized by imbalanced or noisy data, requiring innovative solutions like synthetic data generation and foundation model adaptation. Third, the survey examines proactive measures for resilience, which include distinctive aspects of verification, testing, and redundancy. Fourth, it explores recovery mechanisms, moving beyond traditional fault models to design "just good enough" recovery strategies that prioritize safety-critical functions during perturbations. Finally, it highlights the central role of the human, focusing on the different levels of human intervention, the necessity of trust calibration, and the requirement for explainable AI to support human-CPS teaming. These themes are illustrated through representative application domains, primarily Connected and Autonomous Transportation Systems (CATS) and Medical CPS (MCPS). By integrating the five interconnected themes, this survey provides a systematic roadmap for achieving the resilient CPS in increasingly complex and adversarial environments.

cs.CR↗

MetaSort: An Accelerated Approach for Non-uniform Compression and Few-shot Classification of Neural Spike Waveforms

Many previous works in spike sorting study spike classification and compression independently. In this paper, a novel algorithm is proposed called MetaSort to address these two problems. To deal with compression, a novel adaptive level crossing algorithm is proposed to approximate spike shapes with high fidelity. Meanwhile, the latent feature representation is used to handle the classification problem. Besides, to guarantee MetaSort is robust and discriminative, the geometric information of data is exploited simultaneously in the proposed framework by meta-transfer learning. Empirical experiments with in-vivo spike data demonstrate that MetaSort delivers promising performance, highlighting its potential and motivating continued development toward an ultra-low-power, on-chip implementation.

eess.SP↗

Vector Certificates for $ω$-regular Specifications

The recently introduced notions of ranking functions and closure certificates utilize well-foundedness arguments to facilitate the verification of dynamical systems against $ω$-regular properties. A ranking function and a closure certificate are real-valued functions defined over states and state pairs of a dynamical system whose zero superlevel sets are inductive state invariant and inductive transition invariant, respectively. The search for such certificates can be automated by fixing a specific template class, such as a polynomial of a fixed degree, and then using optimization techniques such as sum-of-squares (SOS) programming to find it. Unfortunately, such certificates may not be found for a fixed template. In such a case, one must change the template; for example, increase the degree of the polynomial. In this paper, we consider a notion of multiple functions in the form of vector certificates. Taking inspiration from the literature on vector barrier certificates as generalizations of standard barrier certificates for safety verification, we propose vector co-Büchi ranking functions and vector closure certificates as nontrivial generalizations of ranking functions and closure certificates, respectively. Both notions consist of a set of functions that jointly overapproximate an inductive invariant by considering each function to be a linear combination of the others. The advantage of such certificates is that they allow us to prove properties even when a single function for a fixed template cannot be found using standard approaches. We present an SOS programming approach to search for these functions and demonstrate the effectiveness of our proposed method in verifying $ω$-regular specifications in several case studies.

eess.SY↗

Interpolation-Inspired Closure Certificates

Barrier certificates, a form of state invariants, provide an automated approach to the verification of the safety of dynamical systems. Similarly to barrier certificates, recent works explore the notion of closure certificates, a form of transition invariants, to verify dynamical systems against $ω$-regular properties including safety. A closure certificate, defined over state pairs of a dynamical system, is a real-valued function whose zero superlevel set characterizes an inductive transition invariant of the system. The search for such a certificate can be effectively automated by assuming it to be within a specific template class, e.g. a polynomial of a fixed degree, and then using optimization techniques such as sum-of-squares (SOS) programming to find it. Unfortunately, one may not be able to find such a certificate for a fixed template. In such a case, one must change the template, e.g. increase the degree of the polynomial. In this paper, we consider a notion of multiple closure certificates dubbed interpolation-inspired closure certificates. An interpolation-inspired closure certificate consists of a set of functions which jointly over-approximate a transition invariant by first considering one-step transitions, then two, and so on until a transition invariant is obtained. The advantage of interpolation-inspired closure certificates is that they allow us to prove properties even when a single function for a fixed template cannot be found using standard approaches. We present SOS programming and a scenario program to find these sets of functions and demonstrate the effectiveness of our proposed method to verify persistence and general $ω$-regular specifications in some case studies.

eess.SY↗

Monotone Neural Barrier Certificates

This report presents a neurosymbolic framework for safety verification and control synthesis in high-dimensional monotone dynamical systems without relying on explicit models or conservative Lipschitz bounds. The approach combines the expressiveness of neural networks with the rigor of symbolic reasoning via barrier certificates, functional analogs of inductive invariants that formally guarantee safety. Prior data-driven methods often treat dynamics as black-box models, relying on dense state-space discretization or Lipschitz overapproximations, leading to exponential sample complexity. In contrast, monotonicity--a pervasive structural property in many real-world systems--provides a symbolic scaffold that simplifies both learning and verification. Exploiting order preservation reduces verification to localized boundary checks, transforming a high-dimensional problem into a tractable, low-dimensional one. Barrier certificates are synthesized using monotone neural network architectures with embedded monotonicity constraints--trained via gradient-based optimization guided by barrier conditions. This enables scalable, formally sound verification directly from simulation data, bridging black-box learning and formal guarantees within a unified neurosymbolic framework.

eess.SY↗

Co-Buchi Barrier Certificates for Discrete-time Dynamical Systems

Barrier certificates provide functional overapproximations for the reachable set of dynamical systems and provide inductive guarantees on the safe evolution of the system. In automata-theoretic verification, a key query is to determine whether the system visits a given predicate over the states finitely often, typically resulting from the complement of the traditional Buchi acceptance condition. This paper proposes a barrier certificate approach to answer such queries by developing a notion of co-Buchi barrier certificates (CBBCs) that generalize classic barrier certificates to ensure that the traces of a system visit a given predicate a fixed number of times. Our notion of CBBC is inspired from bounded synthesis paradigm to LTL realizability, where the LTL specifications are converted to safety automata via universal co-Buchi automata with a bound on final state visitations provided as a hyperparameter. Our application of CBBCs in verification is analogous: we fix a bound and search for a suitable barrier certificate, increasing the bound if no suitable function can be found. We then use these CBBCs to verify our system against properties specified by co-Buchi automata and demonstrate their effectiveness via some case studies.

cs.FL↗

$k$-Inductive and Interpolation-Inspired Barrier Certificates for Stochastic Dynamical Systems

In this paper, we introduce two new types of barrier certificates that are based on multiple functions rather than a single one. A conventional barrier certificate for a stochastic dynamical system is a nonnegative real-valued function whose expected value does not increase as the system evolves. This requirement guarantees that the barrier certificate forms a nonnegative supermartingale and can be used to derive a lower bound on the probability that the system remains safe. A key advantage of such certificates is that they can be automatically searched for using tools such as optimization programs instantiated with a fixed template. When this search is unsuccessful, the common practice is to modify the template and attempt the synthesis again. Drawing inspiration from logical interpolation, we first propose an alternative framework that uses a collection of functions to jointly serve as a barrier certificate. We refer to this construct as an interpolation-inspired barrier certificate. Nonetheless, we observe that these certificates still require one function in the collection to satisfy a supermartingale condition. Motivated by recent work in the literature, we next combine k-induction with interpolation-inspired certificates to relax this supermartingale constraint. We develop a general and more flexible notion of barrier certificates, which we call k-inductive interpolation-inspired barrier certificates. This formulation encompasses multiple ways of integrating interpolation-inspired barrier certificates with k-induction. We highlight two specific instantiations among these possible combinations. For polynomial systems, we employ sum-of-squares (SOS) programming to synthesize the corresponding set of functions. Finally, through our case studies, we show that the proposed methods enable the use of simpler templates and yield tighter lower bounds on the safety probability.

math.OC↗