Search Results for author:
Found 27 papers, 9 papers with code
T3-Vis: visual analytic for Training and fine-Tuning Transformers in NLP
Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging.
A Training-Free Plug-and-Play Watermark Framework for Stable Diffusion
We also have validated that our method is generalized to multiple versions of SDs, even without retraining the watermark model.
Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
Backdoor attacks have been shown to impose severe threats to real security-critical scenarios.
Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks
In this study, we formulate the problem of targeted adversarial attack on Stable Diffusion and propose a framework to generate adversarial prompts.
MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition
Consequently, this paper aims to improve the confidence with view selection and hierarchical prompts.
Improving Rumor Detection by Class-based Adversarial Domain Adaptation
This is not in line with the original intention of the rumor detection task.
T2IW: Joint Text to Image & Watermark Generation
Furthermore, we strengthen the watermark robustness of our approach by subjecting the compound image to various post-processing attacks, with minimal pixel distortion observed in the revealed watermark.
IPProtect: protecting the intellectual property of visual datasets during data valuation
Data trading is essential to accelerate the development of data-driven machine learning pipelines.
GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning
Federated learning (FL) is an effective technique to directly involve edge devices in machine learning training while preserving client privacy.
Revealing Unfair Models by Mining Interpretable Evidence
The key idea is to find solid evidence in the form of a group of data instances discriminated most by the model.
Intrinsic Bias Identification on Medical Image Datasets
However, scientists and practitioners are difficult to identify implicit biases in the datasets, which causes lack of reliable unbias test datasets to valid models.
Membership Privacy Protection for Image Translation Models via Adversarial Knowledge Distillation
Image-to-image translation models are shown to be vulnerable to the Membership Inference Attack (MIA), in which the adversary's goal is to identify whether a sample is used to train the model or not.
Targeted Data Poisoning Attack on News Recommendation System by Content Perturbation
To address this, we introduce a notion of the exposure risk and propose a novel problem of attacking a history news dataset by means of perturbations where the goal is to maximize the manipulation of the target news rank while keeping the risk of exposure under a given budget.
Mining Minority-class Examples With Uncertainty Estimates
In the real world, the frequency of occurrence of objects is naturally skewed forming long-tail class distributions, which results in poor performance on the statistically rare classes.
Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation
The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently.
Adversarial Robustness via Adaptive Label Smoothing
We first show both theoretically and empirically that strong smoothing in AT increases local smoothness of the loss surface which is beneficial for robustness but sacrifices the training loss which influences the accuracy of samples near the decision boundary.
FedFair: Training Fair Models In Cross-Silo Federated Learning
In this paper, we first propose a federated estimation method to accurately estimate the fairness of a model without infringing the data privacy of any party.
T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP
Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging.
Auto-Split: A General Framework of Collaborative Edge-Cloud AI
At the same time, large amounts of input data are collected at the edge of cloud.
Finding Representative Interpretations on Convolutional Neural Networks
Interpreting the decision logic behind effective deep convolutional neural networks (CNN) on images complements the success of deep learning models.
Robust Counterfactual Explanations on Graph Neural Networks
Massive deployment of Graph Neural Networks (GNNs) in high-stake applications generates a strong demand for explanations that are robust to noise and align well with human intuition.
A High Precision Pipeline for Financial Knowledge Graph Construction
This pipeline combines multiple information extraction techniques with a financial dictionary that we built, all working together to produce over 342, 000 compact extractions from over 288, 000 financial news articles, with a precision of 78{\%} at the top-100 extractions. The extracted triples are stored in a knowledge graph making them readily available for use in downstream applications.
Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification
White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images.
Personalized Cross-Silo Federated Learning on Non-IID Data
Non-IID data present a tough challenge for federated learning.
Exact and Consistent Interpretation of Piecewise Linear Models Hidden behind APIs: A Closed Form Solution
More and more AI services are provided through APIs on cloud where predictive models are hidden behind APIs.
Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution
Strong intelligent machines powered by deep neural networks are increasingly deployed as black boxes to make decisions in risk-sensitive domains, such as finance and medical.
Characterizing Driving Styles with Deep Learning
Characterizing driving styles of human drivers using vehicle sensor data, e. g., GPS, is an interesting research problem and an important real-world requirement from automotive industries.
