Search Results for author:
Found 16 papers, 6 papers with code
AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer
Combining LiDAR and camera data has shown potential in enhancing short-distance object detection in autonomous driving systems.
OrthoSeisnet: Seismic Inversion through Orthogonal Multi-scale Frequency Domain U-Net for Geophysical Exploration
However, the detection of sparse thin layers within seismic datasets presents a significant challenge due to the ill-posed nature and poor non-linearity of the problem.
Knowledge from Uncertainty in Evidential Deep Learning
In this paper, we empirically investigate the correlations between misclassification and evaluated uncertainty, and show that EDL's `evidential signal' is due to misclassification bias.
On the amplification of security and privacy risks by post-hoc explanations in machine learning models
A variety of explanation methods have been proposed in recent years to help users gain insights into the results returned by neural networks, which are otherwise complex and opaque black-boxes.
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices.
Adversarial training in communication constrained federated learning
We observe a significant drop in both natural and adversarial accuracies when AT is used in the federated setting as opposed to centralized training.
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume.
Explaining Motion Relevance for Activity Recognition in Video Deep Learning Models
Our results show that the selective relevance method can not only provide insight on the role played by motion in the model's decision -- in effect, revealing and quantifying the model's spatial bias -- but the method also simplifies the resulting explanations for human consumption.
SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing
This leads to a significant improvement in both clean accuracy and robustness compared to AT, TRADES, and other baselines.
Sanity Checks for Saliency Metrics
Despite a proliferation of such methods, little effort has been made to quantify how good these saliency maps are at capturing the true relevance of the pixels to the classifier output (i. e. their "fidelity").
Analyzing Federated Learning through an Adversarial Lens
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server.
Stakeholders in Explainable AI
There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable.
Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems
Several researchers have argued that a machine learning system's interpretability should be defined in relation to a specific agent or task: we should not ask if the system is interpretable, but to whom is it interpretable.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
Our experiments on different datasets (MNIST, CIFAR-10, and ImageNet) show that GenAttack can successfully generate visually imperceptible adversarial examples against state-of-the-art image recognition models with orders of magnitude fewer queries than previous approaches.
SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation
second, we use another LSTM network based discriminator model for distinguishing between the true and the synthesized data.
Get More With Less: Near Real-Time Image Clustering on Mobile Phones
In this paper, we show that by combining the computing power distributed over a number of phones, judicious optimization choices, and contextual information it is possible to execute the end-to-end pipeline entirely on the phones at the edge of the network, efficiently.
