Results 121 to 130 of about 2,268,403 (339)

Are Robust LLM Fingerprints Adversarially Robust?

Model fingerprinting has emerged as a promising paradigm for claiming model ownership. However, robustness evaluations of these schemes have mostly focused on benign perturbations such as incremental fine-tuning, model merging, and prompting. Lack of systematic investigations into {\em adversarial robustness} against a malicious model host leaves ...
Nasery, Anshul, Contente, Edoardo, Kaz, Alkin, Viswanath, Pramod, Oh, Sewoong   +4 more
openaire   +2 more sources

Robust Generative Adversarial Network

, 2020
Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations. Most existing works focus on stabilizing the training of the discriminator while ignoring the generalization properties.
Zhang, Shufei, Qian, Zhuang, Huang, Kaizhu, Xiao, Jimin, He, Yuan   +4 more
openaire   +2 more sources

Experimental validation of the RESPONSE framework against cyberattacks on cyber‐physical process systems

AIChE Journal, EarlyView.
Abstract This work experimentally validates the RESPONSE (Resilient Process cONtrol SystEm) framework as a solution for maintaining safe, continuous operation of cyber‐physical process systems under cyberattacks. RESPONSE implements a dual‐loop architecture that runs a networked online controller in parallel with a hard‐isolated offline controller ...
Luyang Liu, Pu Du, Zaman Sajid, Benjamin Wilhite, Costas Kravaris, Faisal Khan   +5 more
wiley   +1 more source

Discretization Based Solutions for Secure Machine Learning Against Adversarial Attacks

IEEE Access, 2019
Adversarial examples are perturbed inputs that are designed (from a deep learning network's (DLN) parameter gradients) to mislead the DLN during test time.
Priyadarshini Panda, Indranil Chakraborty, Kaushik Roy   +2 more
doaj   +1 more source

AI‐Enhanced Surface‐Enhanced Raman Scattering for Accurate and Sensitive Biomedical Sensing

Advanced Intelligent Discovery, EarlyView.
AI‐SERS advances spectral interpretation with greater precision and speed, enhancing molecular detection, biomedical analysis, and imaging. This review explores its essential contributions to biofluid analysis, disease identification, therapeutic agent evaluation, and high‐resolution biomedical imaging, aiding diagnostic decision‐making.
Seungki Lee, Rowoon Park, Ho Sang Jung
wiley   +1 more source

Adversarially robust transfer learning

, 2019
Transfer learning, in which a network is trained on one task and re-purposed on another, is often used to produce neural network classifiers when data is scarce or full-scale training is too costly. When the goal is to produce a model that is not only accurate but also adversarially robust, data scarcity and computational limitations become even more ...
Shafahi, Ali, Saadatpanah, Parsa, Zhu, Chen, Ghiasi, Amin, Studer, Christoph; id_orcid0000-0001-8950-6267, Jacobs, David, Goldstein, Tom   +6 more
openaire   +3 more sources

What to Make and How to Make It: Combining Machine Learning and Statistical Learning to Design New Materials

Advanced Intelligent Discovery, EarlyView.
Combining machine learning and probabilistic statistical learning is a powerful way to discover and design new materials. A variety of machine learning approaches can be used to identify promising candidates for target applications, and causal inference can help identify potential ways to make them a reality.
Jonathan Y. C. Ting, Amanda S. Barnard
wiley   +1 more source

RobustCheck: A Python package for black-box robustness assessment of image classifiers

SoftwareX
The robustness of computer vision models against adversarial attacks is a critical matter in machine learning that is often overlooked by researchers and developers.
Andrei Ilie, Alin Stefanescu
doaj   +1 more source

A Solution for Exosome‐Based Analysis: Surface‐Enhanced Raman Spectroscopy and Artificial Intelligence

Advanced Intelligent Discovery, EarlyView.
Exosomes are emerging as powerful biomarkers for disease diagnosis and monitoring. This review highlights the integration of surface‐enhanced Raman spectroscopy with artificial intelligence to enhance molecular fingerprinting of exosomes. Machine learning and deep learning techniques improve spectral interpretation, enabling accurate classification of ...
Munevver Akdeniz, Zakarya Al‐Shaebi, Omer Aydin   +2 more
wiley   +1 more source

Application of Neural Networks for Advanced Ir Spectroscopy Characterization of Ceria Catalysts Surfaces

Advanced Intelligent Discovery, EarlyView.
A novel convolutional neural network architecture enables rapid, unsupervised analysis of IR spectroscopic data from DRIFTS and IRRAS. By combining synthetic data generation with parallel convolutional layers and advanced regularization, the model accurately resolves spectral features of adsorbed CO, offering real‐time insights into ceria surface ...
Mehrdad Jalali, Lachlan Caulfield, Eric Sauter, Alexei Nefedov, Chengwu Yang, Christof Wöll   +5 more
wiley   +1 more source