Search Results for author:
Found 31 papers, 10 papers with code
Efficient and Robust Continual Graph Learning for Graph Classification in Biology
Graph classification is essential for understanding complex biological systems, where molecular structures and interactions are naturally represented as graphs.
Deep Adversarial Defense Against Multilevel-Lp Attacks
Deep learning models have shown considerable vulnerability to adversarial attacks, particularly as attacker strategies become more sophisticated.
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
PSBD is motivated by an intriguing Prediction Shift (PS) phenomenon, where poisoned models' predictions on clean data often shift away from true labels towards certain other labels with dropout applied during inference, while backdoor samples exhibit less PS.
Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their performance and ethical application.
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
Based on this, we pose the backdoor data identification problem as a hierarchical data splitting optimization problem, leveraging a novel SPC-based loss function as the primary optimization objective.
Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond
Uncertainty estimation is crucial for the reliability of safety-critical human and artificial intelligence (AI) interaction systems, particularly in the domain of healthcare engineering.
PINNs-Based Uncertainty Quantification for Transient Stability Analysis
This paper addresses the challenge of transient stability in power systems with missing parameters and uncertainty propagation in swing equations.
Efficient and Effective Deep Multi-view Subspace Clustering
i) The parameter scale of the FC layer is quadratic to sample numbers, resulting in high time and memory costs that significantly degrade their feasibility in large-scale datasets.
Improving Generalization in Meta-Learning via Meta-Gradient Augmentation
The key idea is to first break the rote memories by network pruning to address memorization overfitting in the inner loop, and then the gradients of pruned sub-networks naturally form the high-quality augmentation of the meta-gradient to alleviate learner overfitting in the outer loop.
Robust Mode Connectivity-Oriented Adversarial Defense: Enhancing Neural Network Robustness Against Diversified $\ell_p$ Attacks
Adversarial robustness is a key concept in measuring the ability of neural networks to defend against adversarial attacks during the inference phase.
MetaViewer: Towards A Unified Multi-View Representation
To overcome them, we propose a novel bi-level-optimization-based multi-view learning framework, where the representation is learned in a uniform-to-specific manner.
Fine-Grained Classification with Noisy Labels
To this end, we propose a novel framework called stochastic noise-tolerated supervised contrastive learning (SNSCL) that confronts label noise by encouraging distinguishable representation.
Towards Understanding How Self-training Tolerates Data Backdoor Poisoning
In this paper, we explore the potential of self-training via additional unlabeled data for mitigating backdoor attacks.
Physics-Constrained Backdoor Attacks on Power System Fault Localization
The advances in deep learning (DL) techniques have the potential to deliver transformative technological breakthroughs to numerous complex tasks in modern power systems that suffer from increasing uncertainty and nonlinearity.
Learnable Distribution Calibration for Few-Shot Class-Incremental Learning
LDC is built upon a parameterized calibration unit (PCU), which initializes biased distributions for all classes based on classifier vectors (memory-free) and a single covariance matrix.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
Multi-Trigger-Key: Towards Multi-Task Privacy Preserving In Deep Learning
Deep learning-based Multi-Task Classification (MTC) is widely used in applications like facial attributes and healthcare that warrant strong privacy guarantees.
Multi-Trigger-Key: Towards Multi-Task Privacy-Preserving In Deep Learning
Deep learning-based Multi-Task Classification (MTC) is widely used in applications like facial attribute and healthcare that warrant strong privacy guarantees.
Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision
In this paper, we propose a method to estimate not only a depth map but an AiF image from a set of images with different focus positions (known as a focal stack).
Deep Adversarially-Enhanced k-Nearest Neighbors
Recent works have theoretically and empirically shown that deep neural networks (DNNs) have an inherent vulnerability to small perturbations.
Immuno-mimetic Deep Neural Networks (Immuno-Net)
This immuno-mimetic model leads to a new computational biology framework for robustification of deep neural networks against adversarial attacks.
ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense
K-Nearest Neighbor (kNN)-based deep learning methods have been applied to many applications due to their simplicity and geometric interpretability.
RAILS: A Robust Adversarial Immune-inspired Learning System
Initializing a population of exemplars that is balanced across classes, RAILS starts from a uniform label distribution that encourages diversity and uses an evolutionary optimization process to adaptively adjust the predictive label distribution in a manner that emulates the way the natural immune system recognizes novel pathogens.
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Despite the generalization power of the meta-model, it remains elusive that how adversarial robustness can be maintained by MAML in few-shot learning.
RAILS: A Robust Adversarial Immune-inspired Learning System
RAILS incorporates an Adaptive Immune System Emulation (AISE), which emulates in silico the biological mechanisms that are used to defend the host against attacks by pathogens.
Explorable Tone Mapping Operators
It aims to preserve visual information of HDR images in a medium with a limited dynamic range.
Singular equivalences induced by bimodules and quadratic monomial algebras
We investigate the problem when the tensor functor by a bimodule yields a singular equivalence.
Representation Theory Rings and Algebras 18G80, 16E45, 16D20, 16G20
Learning Camera-Aware Noise Models
Modeling imaging sensor noise is a fundamental problem for image processing and computer vision applications.
Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
When the training data are maliciously tampered, the predictions of the acquired deep neural network (DNN) can be manipulated by an adversary known as the Trojan attack (or poisoning backdoor attack).
IOCA: High-Speed I/O-Aware LLC Management for Network-Centric Multi-Tenant Platform
In this paper, we argue that besides CPU cores, high-speed network I/O is also important for LLC management.
Hardware Architecture Operating Systems
Tensor Recovery from Noisy and Multi-Level Quantized Measurements
Existing works on tensor recovery have focused on data losses and random noises.
SCG: Spotting Coordinated Groups in Social Media
Recent events have led to a burgeoning awareness on the misuse of social media sites to affect political events, sway public opinion, and confuse the voters.
