4 offres internship trouvées dans Saclay, île-de-france

Simulation of ultrasonic Non Destructive Testing (NDT) is helpful for evaluating performances of inspection techniques and requires the modeling of waves scattered by defects. Two classical flaw scattering models have been previously usually employed and evaluated to deal with inspection of planar or multifaceted defects, the Kirchhoff approximation (KA) for simulating reflection and the Geometrical Theory of Diffraction (GTD) for simulating diffraction. The student will theoretically study existing modified versions of the two previous approximations to deal with rough defects. These two methods will then be implemented, numerically evaluated, and compared with each other and with a reference numerical method. Conformément aux engagements pris par le CEA en faveur de l'intégration des personnes handicapées, cet emploi est ouvert à toutes et à tous. Le CEA propose des aménagements et/ou des possibilités d'organisation pour l'inclusion des travailleurs handicapés.

The internship aims to enhance the existing tooled metodology called QuaRTOS-DSE by improving the formalization and the implementation of the existing methodology. The internship will address the exploration and the evaluation of complex critical SW architecture. Obtained SW architecture will be evaluated by a formal verification of extra functional system properties using existing tools. The exploration and the evaluation of complex critical SW architecture will be performed with an Iterative tool (a first version with a first formalization of the approach exists), at the level of functions, tasks, agents, actors and will integrate some SotA architecture strategies and best practices for critical SW. The approach must integrate an evaluation of some metrics and a connection with evaluation tools. The existing framework has very slight integration of the HW model, limitations on construction of input model (abstraction level) and limitations model transformation/generation for the...

Ultrasonic phased-array imaging is a core technology in non-destructive testing (NDT) for detecting defects such as cracks or voids in industrial components. By electronically steering ultrasonic beams, phased arrays generate detailed 3D images of internal structures. The Total Focusing Method (TFM) is the standard reconstruction algorithm, achieving diffraction-limited resolution by coherently summing signals from all emitter-receiver pairs. However, conventional TFM suffers from key limitations: its resolution is constrained by diffraction and array pitch, grating lobes degrade image quality, and it assumes uniform sound velocity. It also struggles to resolve sub-wavelength defects, limiting its effectiveness in complex or heterogeneous materials. Recent deep learning methods have improved ultrasonic imaging through denoising and super-resolution, but most operate as black boxes without physical interpretability. They often fail to generalize across array geometries or material...

Context: Large Language Models (LLMs) deployed in safety-critical domains face significant threats from backdoor attacks. Recent empirical evidence contradicts previous assumptions about attack scalability: poisoning attacks remain effective regardless of model or dataset size, requiring as few as 250 poisoned documents to compromise models from up to 13B parameters. This suggests data poisoning becomes easier, not harder, as systems scale. Backdoors persist through post-training alignment techniques like Supervised Fine-Tuning and Reinforcement Learning from Human Feedback, compromising current defenses. However, persistence depends critically on poisoning timing and backdoor characteristics. Current verification methods are computationally prohibitive-Proof-of-Learning requires full model retraining and complete training transcript access. While step-wise verification shows promise for runtime detection, scalability to production models and resilience against adaptive adversaries...