Search Results for author:
Found 22 papers, 6 papers with code
Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience
Specifically, we first identify three key problems: (1) How to capture the inherent confidence of the LLM?
Large Language Model Can Continue Evolving From Mistakes
Continual Learning (CL) is a commonly used method to address this issue.
Small Language Model Can Self-correct
In this paper, we introduce the \underline{I}ntrinsic \underline{S}elf-\underline{C}orrection (ISC) in generative language models, aiming to correct the initial output of LMs in a self-triggered manner, even for those small LMs with 6 billion parameters.
TransCORALNet: A Two-Stream Transformer CORAL Networks for Supply Chain Credit Assessment Cold Start
Thanks to the domain adaptation capability of the proposed model, the domain shift between the source and target domain is minimized.
DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
Our experiments validate the effectiveness of DragNUWA, demonstrating its superior performance in fine-grained control in video generation.
DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder
Our work proposes a VQ-VAE architecture model with a diffusion decoder (DiVAE) to work as the reconstructing component in image synthesis.
Causality-based Neural Network Repair
Results also show that thanks to the causality-based fault localization, CARE's repair focuses on the misbehavior and preserves the accuracy of the neural networks.
Repairing Adversarial Texts through Perturbation
Furthermore, such attacks are impossible to eliminate, i. e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training.
Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.
A Unified Game-Theoretic Interpretation of Adversarial Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i. e.} the view of multi-order interactions between input variables of DNNs.
Backdoor Pre-trained Models Can Transfer to All
However, a pre-trained model with backdoor can be a severe threat to the applications.
Thief, Beware of What Get You There: Towards Understanding Model Extraction Attack
We find the effectiveness of existing techniques significantly affected by the absence of pre-trained models.
A-FMI: Learning Attributions from Deep Networks via Feature Map Importance
Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs).
A Unified Game-Theoretic Interpretation of Adversarial Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.
DAFAR: Defending against Adversaries by Feedback-Autoencoder Reconstruction
We propose DAFAR, a feedback framework that allows deep learning models to detect/purify adversarial examples in high effectiveness and universality, with low area and time overhead.
Rethinking Natural Adversarial Examples for Classification Models
A detection model based on the classification model EfficientNet-B7 achieved a top-1 accuracy of 53. 95%, surpassing previous state-of-the-art classification models trained on ImageNet, suggesting that accurate localization information can significantly boost the performance of classification models on ImageNet-A.
Power System Event Identification based on Deep Neural Network with Information Loading
Online power system event identification and classification is crucial to enhancing the reliability of transmission systems.
Where Does the Robustness Come from? A Study of the Transformation-based Ensemble Defence
This paper aims to provide a thorough study on the effectiveness of the transformation-based ensemble defence for image classification and its reasons.
Rotation-Equivariant Neural Networks for Privacy Protection
Compared to the traditional neural network, the RENN uses d-ary vectors/tensors as features, in which each element is a d-ary number.
Deep Quaternion Features for Privacy Protection
We propose a method to revise the neural network to construct the quaternion-valued neural network (QNN), in order to prevent intermediate-layer features from leaking input information.
Information Losses in Neural Classifiers from Sampling
It then bounds this expected total variation as a function of the size of randomly sampled datasets in a fairly general setting, and without bringing in any additional dependence on model complexity.
Shape Analysis With Hyperbolic Wasserstein Distance
Experimental results demonstrate that our method may be used as an effective shape index, which outperforms some other standard shape measures in our AD versus healthy control classification study.
