arXiv subjects

Stefano Di Carlo

Publications and source records attributed to Stefano Di Carlo.

At least 19 recordsLinked to original sources

arXiv2026

GeoIMO: Geometry-Driven Independent Motion Classification for Event Cameras

Existing automotive event datasets rely on appearance-based annotations from frame pipelines, making them poorly suited for motion-aware event perception. We present a geometry-driven, annotation-free framework that classifies detected objects as static or independently moving by exploiting ego-motion structure directly from the event stream. A Focus of Expansion model with yaw compensation estimates global background motion, while objects are labeled as moving when local motion deviates from this prediction, as quantified by a scale-invariant residual. Temporal stabilization improves robustness across consecutive event windows. The method requires no learning, no manual motion labels, and works with any input bounding boxes. Experiments on MVSEC and the Prophesee 1 Megapixel Automotive Detection dataset demonstrate consistent performance across diverse driving scenarios, with yaw compensation improving results during turns and a simple translational local model offering a favorable accuracy-efficiency trade-off.

cs.CV↗

arXiv2026

A benchmark suite of intracellular Boolean model variants and multiscale simulations for computational biology

We present PhysiBench, an open resource for developing and evaluating computational methods in systems biology including a benchmark suite of 612 executable intracellular Boolean regulatory network variants and a dataset of 120,000 time-resolved multiscale stochastic simulations. The benchmark models are derived from seven published Boolean networks spanning cell-cycle control, developmental patterning, cancer signaling, immune response, and cell-fate decisions, and are executable in the PhysiBoSS/PhysiCell multiscale simulation framework. Model variants are generated through mutation-based model construction, online behavioral filtering, and offline sensitivity evaluation. The simulation dataset is produced from 60 selected models under systematically sampled stimulation protocols and fixed model-level initial configurations. Each trajectory is linked to its model identifier, input-parameter file, stochastic seed, and cell-level output file. PhysiBench supports direct simulation, surrogate modeling, data-driven inference, simulation-based optimization, and comparative benchmarking. Technical validation includes file-integrity and executability checks, graph-based structural diversity analyses, and behavioral heterogeneity assessment from multiscale simulation outputs.

cs.DB↗

arXiv2026

InjectV: Modeling Fault Injection Attacks in RISC-V Simulation Environment

Fault Injection Attacks (FIAs) are a significant threat to hardware security, capable of compromising systems by inducing malicious faults in computation or storage. Evaluating resilience against such attacks is challenging due to the high cost, complexity, and limited availability of physical fault experiments, particularly during pre-silicon development. Architectural-level simulation offers a developer-oriented, white-box perspective for systematic vulnerability assessment. This paper introduces InjectV, a fault injection attack framework for RISC-V platforms built on the gem5 simulator. InjectV enables precise, guided fault injection at security-critical execution points, such as control-flow decisions, counters, and comparisons, allowing systematic exploration of attack vectors. It currently supports transient fault attacks in registers and memory, broadening its ability to simulate diverse attack scenarios. Experimental results on security benchmarks from the FISSC suite, including hardened variants of the VerifyPIN application, demonstrate InjectV's ability to effectively identify fault-injection points, achieving a 95.8% time-saving advantage over traditional fault injection approaches.

cs.CR↗

arXiv2026

Spiker-LL: An Energy-Efficient FPGA Accelerator Enabling Adaptive Local Learning in Spiking Neural Networks

Deploying adaptive intelligence at the edge remains challenging due to the high computational and energy cost of training neural models. Spiking Neural Networks (SNNs) offer a promising alternative, but enabling on-device learning requires hardware-algorithm co-design. This paper presents SPIKER-LL, an FPGA-based SNN accelerator that extends the open-source Spiker+ inference architecture with efficient support for the STSF local learning rule. Through targeted microarchitectural extensions, SPIKER-LL performs inference and online learning with minimal overhead. Across MNIST, F-MNIST, and DIGITS, it achieves up to 93% accuracy, sub-millisecond latency, and less than 0.1 mJ per inference, while remaining DSP-free and highly scalable for edge-FPGA deployments.

cs.NE↗

arXiv2026

GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks

Learning visuomotor policies from scarce expert demonstrations remains a core challenge in robotic manipulation. A primary hurdle lies in distilling high-dimensional RGB representations into control-relevant geometry without overfitting. While using frozen pre-trained Vision Foundation Models (VFMs) improves data efficiency, it also shifts most task adaptation onto a small spatial pooling module, which can latch onto task-irrelevant shortcuts and lose geometric grounding when finetuned with few data samples. More broadly, pre-trained visual representations used for policy learning have been observed to struggle under even minor scene perturbations, highlighting the need for robustness-oriented inductive biases. We propose Geometric Anchor Pre-training (GAP), a simple, action-free warm-up stage that regularizes the spatial adapter before downstream imitation learning. GAP pre-trains the pooling layer on a lightweight simulated proxy task where object masks are available at no cost, encouraging the adapter to produce keypoints that lie on the object, cover its spatial extent, and remain sharp and repeatable over time. This yields stable geometric anchors that provide a reliable coordinate interface for few-shot policy learning, while keeping the VFM frozen. We evaluate GAP on RoboMimic and ManiSkill under severe data scarcity (15-50 demonstrations) and domain shift. A simple adapter regularized with GAP consistently outperforms stronger attention-based poolers and end-to-end fine-tuning, achieving 62% success on RoboMimic Can with 15 demonstrations (+16% over AFA), 63% on the long-horizon high-precision Tool Hang task with 50 demonstrations, and 61% on ManiSkill StackCube with 30 demonstrations (+11% over full fine-tuning). The proxy stage is lightweight and fully decoupled from downstream tasks, making it practical to reuse across environments and manipulation skills.

cs.RO↗

arXiv2026

NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework

The rapid expansion of spiking neural networks (SNNs) has led to a proliferation of training algorithms that differ widely in biological inspiration, computational structure, and hardware suitability. Despite this progress, the field lacks a unified, fine-grained taxonomy that systematically organizes these approaches and clarifies their conceptual relationships. This survey provides a comprehensive taxonomy of SNN training algorithms, spanning surrogate-gradient backpropagation, local and three-factor learning rules, biologically inspired plasticity mechanisms, ANN-to-SNN conversion pipelines, and non-standard optimization strategies. We analyze each class in terms of its computational principles, learning signals, and locality properties. To support reproducible research, we release NeuroTrain, an open-source snnTorch-based framework that implements a representative set of these algorithms within a unified, modular, and extendable framework, enabling consistent benchmarking across datasets, architectures, and training regimes. By consolidating fragmented literature and providing a reusable benchmarking framework, this survey identifies common patterns, highlights open challenges, and outlines promising directions for future work on scalable, efficient SNN training.

cs.NE↗

arXiv2026

Elastic Spiking Transformers for Efficient Gesture Understanding

Spiking Neural Networks (SNNs), particularly Spiking Transformers, offer energy-efficient processing of event-based sensor data for healthcare applications. Yet current architectures are rigid: they are trained and deployed as static networks with fixed parameter counts and computational graphs. This limits deployment on neuromorphic hardware such as Loihi and SpiNNaker, where on-chip constraints often require smaller models that trade accuracy for feasibility. We introduce the Elastic Spiking Transformer, a runtime-adaptive architecture that brings elasticity into the spiking paradigm. Inspired by Matryoshka-style representation learning, it embeds nested elasticity in the Feature Extractor, Spiking Self-Attention, and Feed-Forward blocks. Through granularity-aware weight sharing, a single universal model can dynamically slice network width and attention heads at inference time without retraining. This design provides two key advantages for SNNs. First, it allows the model to adjust its parameter footprint to different hardware memory budgets. Second, reducing active neurons also lowers spike firing rates, yielding proportional reductions in synaptic operations, an energy benefit not directly available in standard artificial neural networks. We evaluate the approach on CIFAR10/100, CIFAR10-DVS, and the EHWGesture clinical gesture understanding dataset. Results show that one Elastic Spiking Transformer spans a broad range of complexity-accuracy trade-offs, matching or surpassing independently trained baselines while supporting adaptive, real-time gesture recognition on resource-constrained edge devices.

cs.NE↗

arXiv2026

Experimental Analysis of FreeRTOS Dependability through Targeted Fault Injection Campaigns

Real-Time Operating Systems (RTOSes) play a crucial role in safety-critical domains, where deterministic and predictable task execution is essential. Yet they are increasingly exposed to ionizing radiation, which can compromise system dependability. To assess FreeRTOS under such conditions, we introduce KRONOS, a software-based, non-intrusive post-propagation Fault Injection (FI) framework that injects transient and permanent faults into Operating System-visible kernel data structures without specialized hardware or debug interfaces. Using KRONOS, we conduct an extensive FI campaign on core FreeRTOS kernel components, including scheduler-related variables and Task Control Blocks (TCBs), characterizing the impact of kernel-level corruptions on functional correctness, timing behavior, and availability. The results show that corruption of pointer and key scheduler-related variables frequently leads to crashes, whereas many TCB fields have only a limited impact on system availability.

cs.OS↗

arXiv2025

LuxIA: A Lightweight Unitary matriX-based Framework Built on an Iterative Algorithm for Photonic Neural Network Training

PNNs present promising opportunities for accelerating machine learning by leveraging the unique benefits of photonic circuits. However, current state of the art PNN simulation tools face significant scalability challenges when training large-scale PNNs, due to the computational demands of transfer matrix calculations, resulting in high memory and time consumption. To overcome these limitations, we introduce the Slicing method, an efficient transfer matrix computation approach compatible with back-propagation. We integrate this method into LuxIA, a unified simulation and training framework. The Slicing method substantially reduces memory usage and execution time, enabling scalable simulation and training of large PNNs. Experimental evaluations across various photonic architectures and standard datasets, including MNIST, Digits, and Olivetti Faces, show that LuxIA consistently surpasses existing tools in speed and scalability. Our results advance the state of the art in PNN simulation, making it feasible to explore and optimize larger, more complex architectures. By addressing key computational bottlenecks, LuxIA facilitates broader adoption and accelerates innovation in AI hardware through photonic technologies. This work paves the way for more efficient and scalable photonic neural network research and development.

cs.LG↗

arXiv2025

Power Side-Channel Analysis of the CVA6 RISC-V Core at the RTL Level Using VeriSide

Security in modern RISC-V processors demands more than functional correctness: It requires resilience to side-channel attacks. This paper evaluates the vulnerability of the side channel of the CVA6 RISC-V core by analyzing software-based AES encryption uses an RTL-level power profiling framework called VeriSide. This work represents that this design's Correlation Power Analysis (CPA) reveals significant leakage, enabling key recovery. These findings underscore the importance of early-stage RTL assessments in shaping future secure RISC-V designs.

cs.CR↗

arXiv2025

Uncovering Privacy Vulnerabilities through Analytical Gradient Inversion Attacks

Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. However, recent studies indicate that private training data can still be exposed through gradient inversion attacks. While earlier analytical methods have demonstrated success in reconstructing input data from fully connected layers, their effectiveness significantly diminishes when applied to convolutional layers, high-dimensional inputs, and scenarios involving multiple training examples. This paper extends our previous work \cite{eltaras2024r} and proposes three advanced algorithms to broaden the applicability of gradient inversion attacks. The first algorithm presents a novel data leakage method that efficiently exploits convolutional layer gradients, demonstrating that even with non-fully invertible activation functions, such as ReLU, training samples can be analytically reconstructed directly from gradients without the need to reconstruct intermediate layer outputs. Building on this foundation, the second algorithm extends this analytical approach to support high-dimensional input data, substantially enhancing its utility across complex real-world datasets. The third algorithm introduces an innovative analytical method for reconstructing mini-batches, addressing a critical gap in current research that predominantly focuses on reconstructing only a single training example. Unlike previous studies that focused mainly on the weight constraints of convolutional layers, our approach emphasizes the pivotal role of gradient constraints, revealing that successful attacks can be executed with fewer than 5\% of the constraints previously deemed necessary in certain layers.

cs.CR↗

arXiv2025

EHWGesture -- A dataset for multimodal understanding of clinical gestures

Hand gesture understanding is essential for several applications in human-computer interaction, including automatic clinical assessment of hand dexterity. While deep learning has advanced static gesture recognition, dynamic gesture understanding remains challenging due to complex spatiotemporal variations. Moreover, existing datasets often lack multimodal and multi-view diversity, precise ground-truth tracking, and an action quality component embedded within gestures. This paper introduces EHWGesture, a multimodal video dataset for gesture understanding featuring five clinically relevant gestures. It includes over 1,100 recordings (6 hours), captured from 25 healthy subjects using two high-resolution RGB-Depth cameras and an event camera. A motion capture system provides precise ground-truth hand landmark tracking, and all devices are spatially calibrated and synchronized to ensure cross-modal alignment. Moreover, to embed an action quality task within gesture understanding, collected recordings are organized in classes of execution speed that mirror clinical evaluations of hand dexterity. Baseline experiments highlight the dataset's potential for gesture classification, gesture trigger detection, and action quality assessment. Thus, EHWGesture can serve as a comprehensive benchmark for advancing multimodal clinical gesture understanding.

cs.CV↗

arXiv2025

CANDoSA: A Hardware Performance Counter-Based Intrusion Detection System for DoS Attacks on Automotive CAN bus

The Controller Area Network (CAN) protocol, essential for automotive embedded systems, lacks inherent security features, making it vulnerable to cyber threats, especially with the rise of autonomous vehicles. Traditional security measures offer limited protection, such as payload encryption and message authentication. This paper presents a novel Intrusion Detection System (IDS) designed for the CAN environment, utilizing Hardware Performance Counters (HPCs) to detect anomalies indicative of cyber attacks. A RISC-V-based CAN receiver is simulated using the gem5 simulator, processing CAN frame payloads with AES-128 encryption as FreeRTOS tasks, which trigger distinct HPC responses. Key HPC features are optimized through data extraction and correlation analysis to enhance classification efficiency. Results indicate that this approach could significantly improve CAN security and address emerging challenges in automotive cybersecurity.

cs.CR↗

arXiv2025

SFATTI: Spiking FPGA Accelerator for Temporal Task-driven Inference -- A Case Study on MNIST

Hardware accelerators are essential for achieving low-latency, energy-efficient inference in edge applications like image recognition. Spiking Neural Networks (SNNs) are particularly promising due to their event-driven and temporally sparse nature, making them well-suited for low-power Field Programmable Gate Array (FPGA)-based deployment. This paper explores using the open-source Spiker+ framework to generate optimized SNNs accelerators for handwritten digit recognition on the MNIST dataset. Spiker+ enables high-level specification of network topologies, neuron models, and quantization, automatically generating deployable HDL. We evaluate multiple configurations and analyze trade-offs relevant to edge computing constraints.

cs.NE↗

arXiv2025

Energy-Efficient Digital Design: A Comparative Study of Event-Driven and Clock-Driven Spiking Neurons

This paper presents a comprehensive evaluation of Spiking Neural Network (SNN) neuron models for hardware acceleration by comparing event driven and clock-driven implementations. We begin our investigation in software, rapidly prototyping and testing various SNN models based on different variants of the Leaky Integrate and Fire (LIF) neuron across multiple datasets. This phase enables controlled performance assessment and informs design refinement. Our subsequent hardware phase, implemented on FPGA, validates the simulation findings and offers practical insights into design trade offs. In particular, we examine how variations in input stimuli influence key performance metrics such as latency, power consumption, energy efficiency, and resource utilization. These results yield valuable guidelines for constructing energy efficient, real time neuromorphic systems. Overall, our work bridges software simulation and hardware realization, advancing the development of next generation SNN accelerators.

cs.NE↗

arXiv2025

Braided interferometer mesh for robust photonic matrix-vector multiplications with non-ideal components

Matrix-vector multiplications (MVMs) are essential for a wide range of applications, particularly in modern machine learning and quantum computing. In photonics, there is growing interest in developing architectures capable of performing linear operations with high speed, low latency, and minimal loss. Traditional interferometric photonic architectures, such as the Clements design, have been extensively used for MVM operations. However, as these architectures scale, improving stability and robustness becomes critical. In this paper, we introduce a novel photonic braid interferometer architecture that outperforms both the Clements and Fldzhyan designs in these aspects. Using numerical simulations, we evaluate the performance of these architectures under ideal conditions and systematically introduce non-idealities such as insertion losses, beam splitter imbalances, and crosstalk. The results demonstrate that the braid architecture offers superior robustness due to its symmetrical design and reduced layer count. Further analysis shows that the braid architecture is particularly advantageous in large-scale implementations, delivering better performance as the size of the interferometer increases. We also assess the footprint and total insertion losses of each architecture. Although waveguide crossings in the braid architecture slightly increase the footprint and insertion loss, recent advances in crossing technology significantly minimize these effects. Our study suggests that the braid architecture is a robust solution for photonic neuromorphic computing, maintaining high fidelity in realistic conditions where imperfections are inevitable.

physics.optics↗

arXiv2024

Security and RAS in the Computing Continuum

Security and RAS are two non-functional requirements under focus for current systems developed for the computing continuum. Due to the increased number of interconnected computer systems across the continuum, security becomes especially pervasive at all levels, from the smallest edge device to the high-performance cloud at the other end. Similarly, RAS (Reliability, Availability, and Serviceability) ensures the robustness of a system towards hardware defects. Namely, making them reliable, with high availability and design for easy service. In this paper and as a result of the Vitamin-V EU project, the authors detail the comprehensive approach to malware and hardware attack detection; as well as, the RAS features envisioned for future systems across the computing continuum.

cs.CR↗

arXiv2024

Neuromorphic Heart Rate Monitors: Neural State Machines for Monotonic Change Detection

Detecting monotonic changes in heart rate (HR) is crucial for early identification of cardiac conditions and health management. This is particularly important for dementia patients, where HR trends can signal stress or agitation. Developing wearable technologies that can perform always-on monitoring of HRs is essential to effectively detect slow changes over extended periods of time. However, designing compact electronic circuits that can monitor and process bio-signals continuously, and that can operate in a low-power regime to ensure long-lasting performance, is still an open challenge. Neuromorphic technology offers an energy-efficient solution for real-time health monitoring. We propose a neuromorphic implementation of a Neural State Machine (NSM) network to encode different health states and switch between them based on the input stimuli. Our focus is on detecting monotonic state switches in electrocardiogram data to identify progressive HR increases. This innovative approach promises significant advancements in continuous health monitoring and management.

cs.ET↗