Results 1 to 10 of about 2,394,947 (118)
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective [PDF]
IEEE Data Engineering Bulletin, 2023 ChatGPT is a recent chatbot service released by OpenAI and is receiving increasing attention over the past few months. While evaluations of various aspects of ChatGPT have been done, its robustness, i.e., the performance to unexpected inputs, is still ...
Jindong Wang +12 more
semanticscholar +1 more source
Understanding The Robustness in Vision Transformers [PDF]
International Conference on Machine Learning, 2022 Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic understanding.
Daquan Zhou +6 more
semanticscholar +1 more source
Understanding Robustness of Transformers for Image Classification [PDF]
IEEE International Conference on Computer Vision, 2021 Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (ViT) have matched or even surpassed ResNets for image classification ...
Srinadh Bhojanapalli +5 more
semanticscholar +1 more source
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization [PDF]
IEEE International Conference on Computer Vision, 2020 We introduce four new real-world distribution shift datasets consisting of changes in image style, image blurriness, geographic location, camera operation, and more. With our new datasets, we take stock of previously proposed methods for improving out-of-
Dan Hendrycks +12 more
semanticscholar +1 more source
Recent Advances in Adversarial Training for Adversarial Robustness [PDF]
International Joint Conference on Artificial Intelligence, 2021 Adversarial training is one of the most effective approaches for deep learning models to defend against adversarial examples. Unlike other defense strategies, adversarial training aims to enhance the robustness of models intrinsically.
Tao Bai +4 more
semanticscholar +1 more source
Indoor–Outdoor Detection in Mobile Networks Using Quantum Machine Learning Approaches
Computers, 2021 Communication networks are managed more and more by using artificial intelligence. Anomaly detection, network monitoring and user behaviour are areas where machine learning offers advantages over more traditional methods.
Frank Phillipson +2 more
doaj +1 more source
Towards Evaluating the Robustness of Neural Networks [PDF]
IEEE Symposium on Security and Privacy, 2016 Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x' that is ...
Nicholas Carlini, D. Wagner
semanticscholar +1 more source
BMC Medical Informatics and Decision Making, 2022 Background Analysing distributed medical data is challenging because of data sensitivity and various regulations to access and combine data. Some privacy-preserving methods are known for analyzing horizontally-partitioned data, where different ...
Bart Kamphorst +4 more
doaj +1 more source
Pretrained Transformers Improve Out-of-Distribution Robustness [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribution (OOD) generalization for seven NLP datasets by constructing a new ...
Dan Hendrycks +5 more
semanticscholar +1 more source
Constrained MEMS-Based INS/UWB Tightly Coupled System for Accurate UGVs Navigation
Remote Sensing, 2023 To enhance the navigation performance and robustness of navigation system combining ultrawideband (UWB) and inertial navigation systems (INS) under complex indoor environments, an improved navigation method—Allan variance (AV) to assist a modified ...
Jing Mi, Qing Wang, Xiaotao Han
doaj +1 more source