Deviations in Representations Induced by Adversarial Attacks
Deep learning has been a popular topic and has achieved success in many areas. It has drawn the attention of researchers and machine learning practitioners alike, with developed models deployed to a variety of settings. Along with its achievements, research has shown that deep learning models are vulnerable to adversarial attacks. This finding brought about a new direction in research, whereby algorithms were developed to attack and defend vulnerable networks. Our interest is in understanding how these attacks effect change on the intermediate representations of deep learning models. We present a method for measuring and analyzing the deviations in representations induced by adversarial attacks, progressively across a selected set of layers. Experiments are conducted using an assortment of attack algorithms, on the CIFAR-10 dataset, with plots created to visualize the impact of adversarial attacks across different layers in a network.
Code (1)
Tasks
Deep LearningSimilar Papers 제목 키워드 기반
Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
Although deep neural networks have shown promising performances on various tasks, they are susceptible to incorrect predictions induced by imperceptibly small perturbations in inputs. A large number of previous works pro…
GeoDetect: Geometric Adversarial Detection for VLPs
Vision-language pre-trained models (VLPs) are widely used in real-world applications. However, they remain vulnerable to adversarial attacks. Although adversarial detection methods have demonstrated success in single-mod…
Batchnorm Allows Unsupervised Radial Attacks
The construction of adversarial examples usually requires the existence of soft or hard labels for each instance, with respect to which a loss gradient provides the signal for construction of the example. We show that fo…
Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field
Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Traditional solutions strictly limit point displacement during attacks, making it challen…
Adversarial RobustnessAttributeDenoisingBadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts
Recent knowledge graph (KG)-enhanced large language models (LLMs) move beyond purely textual knowledge augmentation by encoding retrieved subgraphs into continuous soft prompts via graph neural networks, introducing a gr…