Adversarial Attack Detection
14 papers with code • 0 benchmarks • 0 datasets
The detection of adversarial attacks.
Benchmarks
These leaderboards are used to track progress in Adversarial Attack Detection
Latest papers
OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples
Experiments in the domain of student essays show that the proposed detector improves the detection performance on the attacker-generated texts by up to +41. 3 points F1-score.
Graph-based methods coupled with specific distributional distances for adversarial attack detection
We introduce a novel approach of detection and interpretation of adversarial attacks from a graph perspective.
Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks.
Detecting Adversarial Examples in Batches -- a geometrical approach
Many deep learning methods have successfully solved complex tasks in computer vision and speech recognition applications.
Residue-Based Natural Language Adversarial Attack Detection
Many popular image adversarial detection approaches are able to identify adversarial examples from embedding feature spaces, whilst in the NLP domain existing state of the art detection approaches solely focus on input text features, without consideration of model embedding spaces.
Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection
In addition, we design a robust shape completion algorithm, which is guaranteed to remove the entire patch from the images if the outputs of the patch segmenter are within a certain Hamming distance of the ground-truth patch masks.
Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
In its most commonly reported sub-task, RobustBench evaluates and ranks the adversarial robustness of trained neural networks on CIFAR10 under AutoAttack (Croce and Hein 2020b) with l-inf perturbations limited to eps = 8/255.
Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency
To this end, Argos first amplifies the discrepancies between the visual content of an image and its misclassified label induced by the attack using a set of regeneration mechanisms and then identifies an image as adversarial if the reproduced views deviate to a preset degree.
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
However, it has been shown that the MMD test is unaware of adversarial attacks -- the MMD test failed to detect the discrepancy between natural and adversarial data.
Towards Feature Space Adversarial Attack
We propose a new adversarial attack to Deep Neural Networks for image classification.