arXiv subjects

Yasser Shoukry

Publications and source records attributed to Yasser Shoukry.

At least 19 recordsLinked to original sources

arXiv2026

Bern2Edge: A Neurosymbolic Compiler for Edge Deployment via Bernstein Polynomial Networks

Deploying high-accuracy neural networks on resource-constrained edge devices remains challenging, as existing approaches treat training, compression, and hardware synthesis as separate stages, leaving a gap between software-trained models and efficient end-to-end deployment with limited support for interpretability. We propose Bern2Edge, an end-to-end framework that uses knowledge distillation to convert a pretrained teacher feed-forward network into hardware-efficient representations via Bernstein polynomial activations. This representation enables two deployment paths: (i) a high-fidelity LUT-based realization that preserves model fidelity under compression, and (ii) a symbolic rule-based representation derived from Bernstein activation geometry, enabling interpretable inference with explicit input-space constraints. The resulting BNNs achieve up to 2.12 percentage-point (pp) accuracy improvement over ReLU under identical compression constraints. At the system level, Bern2Edge achieves up to 99.8% latency reduction and 95.2% BRAM reduction relative to a W8A8 quantized teacher on an AMD Xilinx KV260 FPGA, while maintaining accuracy within 0.5 pp, and further deploys on a low-power Spartan-7 XC7S15 FPGA. The rule-based path reduces DSP usage by up to 89.0% at a cost of 1.5 pp in total accuracy.

cs.LG↗

arXiv2026

Perception with Guarantees: Certified Pose Estimation via Reachability Analysis

Agents in cyber-physical systems are increasingly entrusted with safety-critical tasks. Ensuring safety of these agents often requires localizing the 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., guaranteeing safety even in the worst-case scenario, and external services might additionally not be trustworthy. We address this problem by presenting a 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.

cs.CV↗

arXiv2026

PACIFIC: Can LLMs Discern the Traits Influencing Your Preferences? Evaluating Personality-Driven Preference Alignment in LLMs

User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet how to reliably leverage preference signals for answer generation remains under-explored. In practice, preferences can be noisy, incomplete, or even misleading, which can degrade answer quality when applied naively. Motivated by the observation that stable personality traits shape everyday preferences, we study personality as a principled ''latent'' signal behind preference statements. Through extensive experiments, we find that conditioning on personality-aligned preferences substantially improves personalized question answering: selecting preferences consistent with a user's inferred personality increases answer-choice accuracy from 29.25% to 76%, compared to using randomly selected preferences. Based on these findings, we introduce PACIFIC (Preference Alignment Choices Inference for Five-factor Identity Characterization), a personality-labeled preference dataset containing 1200 preference statements spanning diverse domains (e.g., travel, movies, education), annotated with Big-Five (OCEAN) trait directions. Finally, we propose a framework that enables an LLM model to automatically retrieve personality-aligned preferences and incorporate them during answer generation.

cs.CL↗

arXiv2026

Exponential Approximation Rates and Parameter Efficiency of Learnable Bernstein Activations

The choice of activation function fundamentally shapes the representational capacity and parameter efficiency of deep neural networks, yet most widely used activations lack rigorous theoretical guarantees on these properties. We provide a theoretical analysis of DeepBern-Nets (DBNs) -- networks employing learnable Bernstein polynomial activations -- showing that their approximation error decays with the network depth $L$ and the polynomial order $n$ with a rate of $\mathcal{O}(n^{-L})$, exponentially faster than the polynomial rate of ReLU architectures while remaining fully differentiable. We validate these predictions through $1{,}344$ experiments on large scientific datasets (HIGGS and SUSY), comparing DBNs against ReLU, Leaky ReLU, SELU, and GeLU. DBNs achieve over $70\%$ parameter reduction across the majority of architectures -- reaching $99.9\%$ at scale -- converge to ReLU's final loss in as few as $26\%$ of the training epochs, and attain up to $45\%$ lower final loss. These advantages hold over all tested activations, confirming that DBN's gains stem from the learnable polynomial structure rather than mere smoothness.

cs.LG↗

arXiv2026

Correct-by-Construction Vision-based Pose Estimation using Geometric Generative Models

We consider the problem of vision-based pose estimation for autonomous systems. While deep neural networks have been successfully used for vision-based tasks, they inherently lack provable guarantees on the correctness of their output, which is crucial for safety-critical applications. We present a framework for designing certifiable neural networks (NNs) for perception-based pose estimation that integrates physics-driven modeling with learning-based estimation. The proposed framework begins by leveraging the known geometry of planar objects commonly found in the environment, such as traffic signs and runway markings, referred to as target objects. At its core, it introduces a geometric generative model (GGM), a neural-network-like model whose parameters are derived from the image formation process of a target object observed by a camera. Once designed, the GGM can be used to train NN-based pose estimators with certified guarantees in terms of their estimation errors. We first demonstrate this framework in uncluttered environments, where the target object is the only object present in the camera's field of view. We extend this using ideas from NN reachability analysis to design certified object NN that can detect the presence of the target object in cluttered environments. Subsequently, the framework consolidates the certified object detector with the certified pose estimator to design a multi-stage perception pipeline that generalizes the proposed approach to cluttered environments, while maintaining its certified guarantees. We evaluate the proposed framework using both synthetic and real images of various planar objects commonly encountered by autonomous vehicles. Using images captured by an event-based camera, we show that the trained encoder can effectively estimate the pose of a traffic sign in accordance with the certified bound provided by the framework.

cs.RO↗

arXiv2025

RampoNN: A Reachability-Guided System Falsification for Efficient Cyber-Kinetic Vulnerability Detection

Detecting kinetic vulnerabilities in Cyber-Physical Systems (CPS), vulnerabilities in control code that can precipitate hazardous physical consequences, is a critical challenge. This task is complicated by the need to analyze the intricate coupling between complex software behavior and the system's physical dynamics. Furthermore, the periodic execution of control code in CPS applications creates a combinatorial explosion of execution paths that must be analyzed over time, far exceeding the scope of traditional single-run code analysis. This paper introduces RampoNN, a novel framework that systematically identifies kinetic vulnerabilities given the control code, a physical system model, and a Signal Temporal Logic (STL) specification of safe behavior. RampoNN first analyzes the control code to map the control signals that can be generated under various execution branches. It then employs a neural network to abstract the physical system's behavior. To overcome the poor scaling and loose over-approximations of standard neural network reachability, RampoNN uniquely utilizes Deep Bernstein neural networks, which are equipped with customized reachability algorithms that yield orders of magnitude tighter bounds. This high-precision reachability analysis allows RampoNN to rapidly prune large sets of guaranteed-safe behaviors and rank the remaining traces by their potential to violate the specification. The results of this analysis are then used to effectively guide a falsification engine, focusing its search on the most promising system behaviors to find actual vulnerabilities. We evaluated our approach on a PLC-controlled water tank system and a switched PID controller for an automotive engine. The results demonstrate that RampoNN leads to acceleration of the process of finding kinetic vulnerabilities by up to 98.27% and superior scalability compared to other state-of-the-art methods.

cs.CR↗

arXiv2025

KoALA: KL-L0 Adversarial Detector via Label Agreement

Deep neural networks are highly susceptible to adversarial attacks, which pose significant risks to security- and safety-critical applications. We present KoALA (KL-L0 Adversarial detection via Label Agreement), a novel, semantics-free adversarial detector that requires no architectural changes or adversarial retraining. KoALA operates on a simple principle: it detects an adversarial attack when class predictions from two complementary similarity metrics disagree. These metrics - KL divergence and an L0-based similarity - are specifically chosen to detect different types of perturbations. The KL divergence metric is sensitive to dense, low-amplitude shifts, while the L0-based similarity is designed for sparse, high-impact changes. We provide a formal proof of correctness for our approach. The only training required is a simple fine-tuning step on a pre-trained image encoder using clean images to ensure the embeddings align well with both metrics. This makes KoALA a lightweight, plug-and-play solution for existing models and various data modalities. Our extensive experiments on ResNet/CIFAR-10 and CLIP/Tiny-ImageNet confirm our theoretical claims. When the theorem's conditions are met, KoALA consistently and effectively detects adversarial examples. On the full test sets, KoALA achieves a precision of 0.96 and a recall of 0.97 on ResNet/CIFAR-10, and a precision of 0.71 and a recall of 0.94 on CLIP/Tiny-ImageNet.

cs.LG↗

arXiv2025

Certified Learning-Enabled Noise-Aware Motion Planning for Urban Air Mobility

Urban Air Mobility (UAM) has emerged as a promising solution to alleviate urban congestion and transportation challenges. Nevertheless, the noise generated by eVTOL aircrafts poses a significant barrier to public acceptance and regulatory approval, potentially limiting the operational scope and scalability of UAM systems. Hence, the successful adoption of UAM systems hinges on the ability to predict generated noise levels, and further develop motion planning strategies that comply with community-level noise regulations while maintaining operational efficiency. To this end, this paper proposes a novel noise-aware motion planning framework for UAM systems that ensures compliance with noise regulations. We first develop a certifiable neural network model to accurately predict eVTOL noise propagation patterns in urban environments, providing provable bounds on its correctness. To achieve a desired level of accuracy, we propose an active sampling strategy to efficiently build the dataset used to train and test the noise model. Next, we develop a noise-aware motion planning algorithm that utilizes the noise model to generate eVTOL trajectories that guarantee compliance with community noise regulations. The algorithm exploits the monotonic structure of the noise model to efficiently sample the configuration space, ensuring that the generated trajectories are both noise-compliant and operationally efficient. We demonstrate the effectiveness of the proposed framework through a number of experiments for Vahana eVTOLs. The results show that the framework can generate noise-compliant flight plans for a fleet of eVTOLs that adhere to community noise regulations while optimizing operational efficiency.

eess.SY↗

arXiv2025

Extracting Forward Invariant Sets from Neural Network-Based Control Barrier Functions

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. In this way, our algorithm soundly finds a subset of states on which the NN is certified as a BF. We further demonstrate the effectiveness of our algorithm at certifying for real-world NNs as BFs in two case studies. We complemented these with scalability experiments that demonstrate the efficiency of our algorithm.

cs.LG↗

arXiv2024

Passivity Tools for Hybrid Learning Rules in Large Populations

Recent work has pioneered the use of system-theoretic passivity to study equilibrium stability for the dynamics of noncooperative strategic interactions in large populations of learning agents. In this and related works, the stability analysis leverages knowledge that certain ``canonical'' classes of learning rules used to model the agents' strategic behaviors satisfy a passivity condition known as $\delta$-passivity. In this paper, we consider that agents exhibit learning behaviors that do not align with a canonical class. Specifically, we focus on characterizing $\delta$-passivity for hybrid learning rules that combine elements from canonical classes. Our analysis also introduces and uses a more general version of $\delta$-passivity, which, for the first time, can handle discontinuous learning rules, including those showing best-response behaviors. We state and prove theorems establishing $\delta$-passivity for two broad convex cones of hybrid learning rules. These cones can merge into a larger one preserving $\delta$-passivity in scenarios limited to two strategies. In our proofs, we establish intermediate facts that are significant on their own and could potentially be used to further generalize our work. We illustrate the applicability of our results through numerical examples.

math.DS↗

arXiv2024

Rampo: A CEGAR-based Integration of Binary Code Analysis and System Falsification for Cyber-Kinetic Vulnerability Detection

This paper presents a novel tool, named Rampo, that can perform binary code analysis to identify cyber kinetic vulnerabilities in CPS. The tool takes as input a Signal Temporal Logic (STL) formula that describes the kinetic effect, i.e., the behavior of the physical system, that one wants to avoid. The tool then searches the possible cyber trajectories in the binary code that may lead to such physical behavior. This search integrates binary code analysis tools and hybrid systems falsification tools using a Counter-Example Guided Abstraction Refinement (CEGAR) approach. Rampo starts by analyzing the binary code to extract symbolic constraints that represent the different paths in the code. These symbolic constraints are then passed to a Satisfiability Modulo Theories (SMT) solver to extract the range of control signals that can be produced by each path in the code. The next step is to search over possible physical trajectories using a hybrid systems falsification tool that adheres to the behavior of the cyber paths and yet leads to violations of the STL formula. Since the number of cyber paths that need to be explored increases exponentially with the length of physical trajectories, we iteratively perform refinement of the cyber path constraints based on the previous falsification result and traverse the abstract path tree obtained from the control program to explore the search space of the system. To illustrate the practical utility of binary code analysis in identifying cyber kinetic vulnerabilities, we present case studies from diverse CPS domains, showcasing how they can be discovered in their control programs. Our tool could compute the same number of vulnerabilities while leading to a speedup that ranges from 3x to 98x.

cs.CR↗

arXiv2023

Certified Vision-based State Estimation for Autonomous Landing Systems using Reachability Analysis

This paper studies the problem of designing a certified vision-based state estimator for autonomous landing systems. In such a system, a neural network (NN) processes images from a camera to estimate the aircraft relative position with respect to the runway. We propose an algorithm to design such NNs with certified properties in terms of their ability to detect runways and provide accurate state estimation. At the heart of our approach is the use of geometric models of perspective cameras to obtain a mathematical model that captures the relation between the aircraft states and the inputs. We show that such geometric models enjoy mixed monotonicity properties that can be used to design state estimators with certifiable error bounds. We show the effectiveness of the proposed approach using an experimental testbed on data collected from event-based cameras.

cs.RO↗

arXiv2023

DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation

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 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 comprehensive experiments in adversarial robustness and reachability analysis settings to assess the effectiveness of the proposed Bernstein polynomial activation in enhancing the certification process. Our proposed framework achieves high certified accuracy for adversarially-trained NNs, which is often a challenging task for certifiers of ReLU-based NNs. Moreover, using Bern-IBP bounds for certified training results in NNs with state-of-the-art certified accuracy compared to ReLU networks. This work establishes Bernstein polynomial activation as a promising alternative for improving NN certification tasks across various applications.

cs.LG↗

arXiv2023

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. Extracting (or estimating) the controller provides an unmatched edge to attackers since it allows them to predict the future control actions of the system and plan their attack accordingly. Hence, it is important to understand the ability of the attackers to perform such an attack. In this paper, we focus on the setting when a Deep Neural Network (DNN) controller is trained using Reinforcement Learning (RL) algorithms and is used to control a stochastic system. We play the role of the attacker that aims to estimate such an unknown DNN controller, and we propose a two-phase algorithm. In the first phase, also called the offline phase, the attacker uses side-channel information about the RL-reward function and the system dynamics to identify a set of candidate estimates of the unknown DNN. In the second phase, also called the online phase, the attacker observes the behavior of the unknown DNN and uses these observations to shortlist the set of final policy estimates. We provide theoretical analysis of the error between the unknown DNN and the estimated one. We also provide numerical results showing the effectiveness of the proposed algorithm.

cs.LG↗

arXiv2023

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. 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.

eess.SY↗

arXiv2023

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. In particular, we propose the EnergyShield framework, which repurposes a controller ''shield'' as a low-power runtime safety monitor for the ADS vehicle. Specifically, the shield in EnergyShield provides not only safety interventions but also a formal, state-based quantification of the tolerable edge response time before vehicle safety is compromised. Using EnergyShield, an ADS can then save energy by wirelessly offloading NN computations to edge computers, while still maintaining a formal guarantee of safety until it receives a response (on-vehicle hardware provides a just-in-time fail safe). To validate the benefits of EnergyShield, we implemented and tested it in the Carla simulation environment. Our results show that EnergyShield maintains safe vehicle operation while providing significant energy savings compared to on-vehicle NN evaluation: from 24% to 54% less energy across a range of wireless conditions and edge delays.

eess.SY↗

arXiv2022

BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic

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.

cs.LG↗

arXiv2022

Neurosymbolic Motion and Task Planning for Linear Temporal Logic Tasks

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 Linear Temporal Logic (LTL) 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, LTL formula, and dynamic constraints of a robot) is unknown 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 unknown tasks where state-of-the-art meta-reinforcement learning techniques fail.

cs.RO↗