Search Results for author:
Found 9 papers, 1 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.
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.
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.
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.
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.
