Adversarial training - Open Access .click

Results 61 to 70 of about 217,331 (267)

Decentralized Adversarial Training Over Graphs

IEEE Transactions on Information Theory
arXiv admin note: text overlap with arXiv:2303 ...
Ying Cao +3 more
openaire +2 more sources

Strength-Adaptive Adversarial Training

, 2022
Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness ...
Yu, Chaojian +7 more
openaire +2 more sources

Stable Imitation of Multigait and Bipedal Motions for Quadrupedal Robots Over Uneven Terrains

Advanced Robotics Research, EarlyView.
How are quadrupedal robots empowered to execute complex navigation tasks, including multigait and bipedal motions? Challenges in stability and real‐world adaptation persist, especially with uneven terrains and disturbances. This article presents an imitation learning framework that enhances adaptability and robustness by incorporating long short‐term ...
Erdong Xiao, Yinzhao Dong, Ji Ma, Peng Lu +3 more
wiley +1 more source

Triple Down on Robustness: Understanding the Impact of Adversarial Triplet Compositions on Adversarial Robustness

Machine Learning and Knowledge Extraction
Adversarial training, a widely used technique for fortifying the robustness of machine learning models, has seen its effectiveness further bolstered by modifying loss functions or incorporating additional terms into the training objective.
Sander Joos +4 more
doaj +1 more source

Continual Learning for Multimodal Data Fusion of a Soft Gripper

Advanced Robotics Research, EarlyView.
Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley +1 more source

Phase-shifted Adversarial Training

, 2023
Adversarial training has been considered an imperative component for safely deploying neural network-based applications to the real world. To achieve stronger robustness, existing methods primarily focus on how to generate strong attacks by increasing the number of update steps, regularizing the models with the smoothed loss function, and injecting the
Kim, Yeachan +3 more
openaire +2 more sources

A State‐Adaptive Koopman Control Framework for Real‐Time Deformable Tool Manipulation in Robotic Environmental Swabbing

Advanced Robotics Research, EarlyView.
This work presents a state‐adaptive Koopman linear quadratic regulator framework for real‐time manipulation of a deformable swab tool in robotic environmental sampling. By combining Koopman linearization, tactile sensing, and centroid‐based force regulation, the system maintains stable contact forces and high coverage across flat and inclined surfaces.
Siavash Mahmoudi, Amirreza Davar, Dongyi Wang +2 more
wiley +1 more source

Evaluating the Utilities of Foundation Models in Single‐Cell Data Analysis

Advanced Science, EarlyView.
This study delivers the first systematic, task‐level evaluation of single‐cell foundation models across eight core analytical tasks. By benchmarking 10 leading models with the scEval framework, it reveals where foundation models truly add value, where task‐specific methods still dominate, and provides concrete, reproducible guidelines to steer the next
Tianyu Liu +4 more
wiley +1 more source

High‐Fidelity Synthetic Data Replicates Clinical Prediction Performance in a Million‐Patient Diabetes Cohort

Advanced Science, EarlyView.
This study generates high‐fidelity synthetic longitudinal records for a million‐patient diabetes cohort, successfully replicating clinical predictive performance. However, deeper analysis reveals algorithmic biases and trajectory inconsistencies that escape standard quality metrics. These findings challenge current validation norms, demonstrating why a
Francisco Ortuño +5 more
wiley +1 more source

Adversarial Example Detection and Classification With Asymmetrical Adversarial Training

, 2020
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
Kolouri, Soheil, Rohde, Gustavo K., Yin, Xuwang +2 more
core

adversarial attacks
deep learning
robustness

adversarial robustness
adversarial attack
adversarial examples

data augmentation
deep neural network
adversarial machine learning