Search Results for author:
Found 28 papers, 8 papers with code
Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors
This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance.
XAI-Based Detection of Adversarial Attacks on Deepfake Detectors
Furthermore, this approach does not change the performance of the deepfake detector.
Genetic Programming Theory and Practice: A Fifteen-Year Trajectory
The GPTP workshop series, which began in 2003, has served over the years as a focal meeting for genetic programming (GP) researchers.
Coevolving Artistic Images Using OMNIREP
We have recently developed OMNIREP, a coevolutionary algorithm to discover both a representation and an interpreter that solve a particular problem of interest.
New Pathways in Coevolutionary Computation
The simultaneous evolution of two or more species with coupled fitness -- coevolution -- has been put to good use in the field of evolutionary computation.
Task and Explanation Network
Explainability in deep networks has gained increased importance in recent years.
Fitness Approximation through Machine Learning
We present a novel approach to performing fitness approximation in genetic algorithms (GAs) using machine-learning (ML) models, focusing on evolutionary agents in Gymnasium (game) simulators -- where fitness computation is costly.
Open Sesame! Universal Black Box Jailbreaking of Large Language Models
The GA attack works by optimizing a universal adversarial prompt that -- when combined with a user's query -- disrupts the attacked model's alignment, resulting in unintended and potentially harmful outputs.
I See Dead People: Gray-Box Adversarial Attack on Image-To-Text Models
Through experiments conducted on the ViT-GPT2 model, which is the most-used image-to-text model in Hugging Face, and the Flickr30k dataset, we demonstrate that our proposed attack successfully generates visually similar adversarial examples, both with untargeted and targeted captions.
A Melting Pot of Evolution and Learning
We survey eight recent works by our group, involving the successful blending of evolutionary algorithms with machine learning and deep learning: 1.
Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectors
To our knowledge this is the first and only method that performs black-box physical attacks directly on object-detection models, which results with a model-agnostic attack.
Classy Ensemble: A Novel Ensemble Algorithm for Classification
We present Classy Ensemble, a novel ensemble-generation algorithm for classification tasks, which aggregates models through a weighted combination of per-class accuracy.
Foiling Explanations in Deep Neural Networks
Our novel algorithm, AttaXAI, a model-agnostic, adversarial attack on XAI algorithms, only requires access to the output logits of a classifier and to the explanation map; these weak assumptions render our approach highly useful where real-world models and data are concerned.
Adaptive Combination of a Genetic Algorithm and Novelty Search for Deep Neuroevolution
To that end, Novelty Search (NS) has been shown to be able to outperform gradient-following optimizers in some cases, while under-performing in others.
An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks
Deep neural networks (DNNs) are sensitive to adversarial data in a variety of scenarios, including the black-box scenario, where the attacker is only allowed to query the trained model and receive an output.
EC-KitY: Evolutionary Computation Tool Kit in Python with Seamless Machine Learning Integration
EC-KitY is a comprehensive Python library for doing evolutionary computation (EC), licensed under the BSD 3-Clause License, and compatible with scikit-learn.
High Per Parameter: A Large-Scale Study of Hyperparameter Tuning for Machine Learning Algorithms
Hyperparameters in machine learning (ML) have received a fair amount of attention, and hyperparameter tuning has come to be regarded as an important step in the ML pipeline.
Combining Deep Learning with Good Old-Fashioned Machine Learning
We present a comprehensive, stacking-based framework for combining deep learning with good old-fashioned machine learning, called Deep GOld.
Automatically Balancing Model Accuracy and Complexity using Solution and Fitness Evolution (SAFE)
When seeking a predictive model in biomedical data, one often has more than a single objective in mind, e. g., attaining both high accuracy and low complexity (to promote interpretability).
Solution and Fitness Evolution (SAFE): A Study of Multiobjective Problems
We have recently presented SAFE -- Solution And Fitness Evolution -- a commensalistic coevolutionary algorithm that maintains two coevolving populations: a population of candidate solutions and a population of candidate objective functions.
Solution and Fitness Evolution (SAFE): Coevolving Solutions and Their Objective Functions
We recently highlighted a fundamental problem recognized to confound algorithmic optimization, namely, \textit{conflating} the objective with the objective function.
Binary and Multinomial Classification through Evolutionary Symbolic Regression
We present three evolutionary symbolic regression-based classification algorithms for binary and multinomial datasets: GPLearnClf, CartesianClf, and ClaSyCo.
Evolution of Activation Functions for Deep Learning-Based Image Classification
Studying both standard fully connected neural networks (FCNs) and convolutional neural networks (CNNs), we propose a novel, three-population, coevolutionary algorithm to evolve AFs, and compare it to four other methods, both evolutionary and non-evolutionary.
Symbolic-Regression Boosting
Modifying standard gradient boosting by replacing the embedded weak learner in favor of a strong(er) one, we present SyRBo: Symbolic-Regression Boosting.
Neural Networks with A La Carte Selection of Activation Functions
Activation functions (AFs), which are pivotal to the success (or failure) of a neural network, have received increased attention in recent years, with researchers seeking to design novel AFs that improve some aspect of network performance.
EBIC: an evolutionary-based parallel biclustering algorithm for pattern discover
In this paper a novel biclustering algorithm based on artificial intelligence (AI) is introduced.
Investigating the Parameter Space of Evolutionary Algorithms
The practice of evolutionary algorithms involves the tuning of many parameters.
A System for Accessible Artificial Intelligence
While artificial intelligence (AI) has become widespread, many commercial AI systems are not yet accessible to individual researchers nor the general public due to the deep knowledge of the systems required to use them.
