arXiv subjects

Leonardo Pesce

Publications and source records attributed to Leonardo Pesce.

3 recordsLinked to original sources

arXiv2026

Enhanced Athermal Phonon Responsivity in a Kinetic Inductance Detector with Integrated Phonon Collectors

Cryogenic phonon detectors are adopted in light dark matter searches and coherent elastic neutrino-nucleus scattering experiments as they can achieve low energy thresholds. The phonon mediated sensing of silicon particle absorbers has already been proved with Kinetic Inductance Detectors (KIDs), acting both as sensors and athermal phonon absorbers. In this work we present the design and the performance of an improved detector design. In this architecture, the KID acts only as sensor and is coupled to dedicated phonon collectors. When a signal is coming from the substrate, the presence of a separated collector allows to detect an higher increase of quasi-particles density, thereby enhancing its responsivity. The meander of the KID is composed of a 77 nm trilayer wire of Aluminum-Titanium-Aluminum, while the phonon collectors are made of a 100 nm Aluminum layer and act as quasi-particles funnels. Inside the collectors, the absorbed athermal phonons generate quasi-particles which, after diffusion, are trapped in the lower-gap superconducting trilayer. The performance of this setup is compared to that of a standard phonon-mediated KID, showing an increased phonon collection efficiency by a factor of around 7.

physics.ins-det↗

arXiv2025

eXIAA: eXplainable Injections for Adversarial Attack

Post-hoc explainability methods are a subset of Machine Learning (ML) that aim to provide a reason for why a model behaves in a certain way. In this paper, we show a new black-box model-agnostic adversarial attack for post-hoc explainable Artificial Intelligence (XAI), particularly in the image domain. The goal of the attack is to modify the original explanations while being undetected by the human eye and maintain the same predicted class. In contrast to previous methods, we do not require any access to the model or its weights, but only to the model's computed predictions and explanations. Additionally, the attack is accomplished in a single step while significantly changing the provided explanations, as demonstrated by empirical evaluation. The low requirements of our method expose a critical vulnerability in current explainability methods, raising concerns about their reliability in safety-critical applications. We systematically generate attacks based on the explanations generated by post-hoc explainability methods (saliency maps, integrated gradients, and DeepLIFT SHAP) for pretrained ResNet-18 and ViT-B16 on ImageNet. The results show that our attacks could lead to dramatically different explanations without changing the predictive probabilities. We validate the effectiveness of our attack, compute the induced change based on the explanation with mean absolute difference, and verify the closeness of the original image and the corrupted one with the Structural Similarity Index Measure (SSIM).

cs.LG↗

arXiv2025

WS$^2$: Weakly Supervised Segmentation using Before-After Supervision in Waste Sorting

In industrial quality control, to visually recognize unwanted items within a moving heterogeneous stream, human operators are often still indispensable. Waste-sorting stands as a significant example, where operators on multiple conveyor belts manually remove unwanted objects to select specific materials. To automate this recognition problem, computer vision systems offer great potential in accurately identifying and segmenting unwanted items in such settings. Unfortunately, considering the multitude and the variety of sorting tasks, fully supervised approaches are not a viable option to address this challange, as they require extensive labeling efforts. Surprisingly, weakly supervised alternatives that leverage the implicit supervision naturally provided by the operator in his removal action are relatively unexplored. In this paper, we define the concept of Before-After Supervision, illustrating how to train a segmentation network by leveraging only the visual differences between images acquired \textit{before} and \textit{after} the operator. To promote research in this direction, we introduce WS$^2$ (Weakly Supervised segmentation for Waste-Sorting), the first multiview dataset consisting of more than 11 000 high-resolution video frames captured on top of a conveyor belt, including "before" and "after" images. We also present a robust end-to-end pipeline, used to benchmark several state-of-the-art weakly supervised segmentation methods on WS$^2$.

cs.CV↗