Search Results for author:
Found 11 papers, 7 papers with code
Showing Many Labels in Multi-label Classification Models: An Empirical Study of Adversarial Examples
Experimental results indicate that under the "Showing Many Labels", iterative attacks perform significantly better than one-step attacks.
Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense
In the second phase of our method, we leverage several lightweight unlearning methods with the trigger detected by CETF for model repair, which also constructively demonstrate the underlying correlation of the backdoor with Batch Normalization layers.
Benchmark for CEC 2024 Competition on Multiparty Multiobjective Optimization
The competition focuses on Multiparty Multiobjective Optimization Problems (MPMOPs), where multiple decision makers have conflicting objectives, as seen in applications like UAV path planning.
EDOLAB: An Open-Source Platform for Education and Experimentation with Evolutionary Dynamic Optimization Algorithms
Evolutionary Dynamic Optimization Algorithms (EDOAs) are designed to address these challenges effectively.
Evolutionary Multiparty Distance Minimization
In the field of evolutionary multiobjective optimization, the decision maker (DM) concerns conflicting objectives.
Defending Adversarial Examples by Negative Correlation Ensemble
The security issues in DNNs, such as adversarial examples, have attracted much attention.
Privacy-Preserving Distributed Machine Learning Made Faster
So machine learning tasks need to be spread across multiple servers, turning the centralized machine learning into a distributed one.
Benchmark Functions for CEC 2022 Competition on Seeking Multiple Optima in Dynamic Environments
This is very helpful for the decision makers, especially when facing changing environments.
Competition on Dynamic Optimization Problems Generated by Generalized Moving Peaks Benchmark (GMPB)
The Generalized Moving Peaks Benchmark (GMPB) is a tool for generating continuous dynamic optimization problem instances with controllable dynamic and morphological characteristics.
Random Directional Attack for Fooling Deep Neural Networks
Unfortunately, as the model is nonlinear in most cases, the addition of perturbations in the gradient direction does not necessarily increase loss.
Community-based 3-SAT Formulas with a Predefined Solution
Although some generating algorithms have been proposed to generate SAT formulas with predefined solutions, community structures of SAT formulas are not considered.
