Search Results for author:
Found 21 papers, 7 papers with code
Deep neural network loses attention to adversarial images
We also analyse how different adversarial samples distort the attention of the neural network compared to original samples.
Perceptual Deep Neural Networks: Adversarial Robustness through Input Recreation
Thus, $\varphi$DNNs reveal that input recreation has strong benefits for artificial neural networks similar to biological ones, shedding light into the importance of purposely corrupting the input as well as pioneering an area of perception models based on GANs and autoencoders for robust recognition in artificial intelligence.
Continual General Chunking Problem and SyncMap
Here, we propose a continual generalization of the chunking problem (an unsupervised problem), encompassing fixed and probabilistic chunks, discovery of temporal and causal structures and their continual variations.
Representation Quality Explain Adversarial Attacks
The main idea lies in the fact that some features are present on unknown classes and that unknown classes can be defined as a combination of previous learned features without representation bias (a bias towards representation that maps only current set of input-outputs and their boundary).
Evolving Robust Neural Architectures to Defend from Adversarial Attacks
By creating a novel neural architecture search with options for dense layers to connect with convolution layers and vice-versa as well as the addition of concatenation layers in the search, we were able to evolve an architecture that is inherently accurate on adversarial samples.
Representation Quality Of Neural Networks Links To Adversarial Attacks and Defences
A crucial step to understanding the rationale for this lack of robustness is to assess the potential of the neural networks' representation to encode the existing features.
Adversarial Robustness Assessment: Why both $L_0$ and $L_\infty$ Attacks Are Necessary
There exists a vast number of adversarial attacks and defences for machine learning algorithms of various types which makes assessing the robustness of algorithms a daunting task.
Self Training Autonomous Driving Agent
Intrinsically, driving is a Markov Decision Process which suits well the reinforcement learning paradigm.
Batch Tournament Selection for Genetic Programming
Lexicase selection achieves very good solution quality by introducing ordered test cases.
Tackling Unit Commitment and Load Dispatch Problems Considering All Constraints with Evolutionary Computation
In this paper, both problems are solved together without approximations or simplifications.
Understanding the One-Pixel Attack: Propagation Maps and Locality Analysis
Deep neural networks were shown to be vulnerable to single pixel modifications.
Universal Rules for Fooling Deep Neural Networks based Text Classification
Here, we go beyond attacks to investigate, for the first time, universal rules, i. e., rules that are sample agnostic and therefore could turn any text sample in an adversarial one.
Spectrum-Diverse Neuroevolution with Unified Neural Models
The combination of Spectrum Diversity with a unified neuron representation enables the algorithm to either surpass or equal NeuroEvolution of Augmenting Topologies (NEAT) on all of the five classes of problems tested.
General Subpopulation Framework and Taming the Conflict Inside Populations
Structured evolutionary algorithms have been investigated for some time.
Self Organizing Classifiers: First Steps in Structured Evolutionary Machine Learning
Here, a variation of the first algorithm is proposed which uses a parameterless self organizing map (SOM).
Self Organizing Classifiers and Niched Fitness
In fact, the proposed algorithm possesses a dynamical population structure that self-organizes itself to better project the input space into a map.
Contingency Training
Experiments are conducted with the contingency training applied to neural networks over traditional datasets as well as datasets with additional irrelevant variables.
Novelty-organizing team of classifiers in noisy and dynamic environments
Moreover, NOTC is compared with NeuroEvolution of Augmenting Topologies (NEAT) in these problems, revealing a trade-off between the approaches.
Attacking Convolutional Neural Network using Differential Evolution
The attack only requires modifying 5 pixels with 20. 44, 14. 76 and 22. 98 pixel values distortion.
Lightweight Classification of IoT Malware based on Image Recognition
The Internet of Things (IoT) is an extension of the traditional Internet, which allows a very large number of smart devices, such as home appliances, network cameras, sensors and controllers to connect to one another to share information and improve user experiences.
One pixel attack for fooling deep neural networks
The results show that 67. 97% of the natural images in Kaggle CIFAR-10 test dataset and 16. 04% of the ImageNet (ILSVRC 2012) test images can be perturbed to at least one target class by modifying just one pixel with 74. 03% and 22. 91% confidence on average.
