paper-with-me

홈 › Papers

Visualizing Representations of Adversarially Perturbed Inputs

2021-05-28 · Daniel Steinberg, Paul Munro

It has been shown that deep learning models are vulnerable to adversarial attacks. We seek to further understand the consequence of such attacks on the intermediate activations of neural networks. We present an evaluation metric, POP-N, which scores the effectiveness of projecting data to N dimensions under the context of visualizing representations of adversarially perturbed inputs. We conduct experiments on CIFAR-10 to compare the POP-2 score of several dimensionality reduction algorithms across various adversarial attacks. Finally, we utilize the 2D data corresponding to high POP-2 scores to generate example visualizations.

📄 PDF Abstract BibTeX arXiv:2105.14116

Code (1)

dstein64/vrapi 공식 구현 pytorch

Tasks

Dimensionality Reduction

Similar Papers 제목 키워드 기반

On the Robustness of Malware Detectors to Adversarial Samples

2024-08-05 · Muhammad Salman, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Muhammad Ikram 외

Adversarial examples add imperceptible alterations to inputs with the objective to induce misclassification in machine learning models. They have been demonstrated to pose significant challenges in domains like image cla…

image-classificationImage ClassificationMalware Analysis

Targeted Visualization of the Backbone of Encoder LLMs

2024-03-26 · Isaac Roberts, Alexander Schulz, Luca Hermes, Barbara Hammer

Attention based Large Language Models (LLMs) are the state-of-the-art in natural language processing (NLP). The two most common architectures are encoders such as BERT, and decoders like the GPT models. Despite the succe…

Dimensionality Reductionimage-classificationImage Classification

Stratified Adversarial Robustness with Rejection

2023-05-02 · Jiefeng Chen, Jayaram Raghuram, Jihye Choi, Xi Wu 외

Recently, there is an emerging interest in adversarially training a classifier with a rejection option (also known as a selective classifier) for boosting adversarial robustness. While rejection can incur a cost in many …

Adversarial RobustnessRobust classification

On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars

2021-09-19 · Chun Tao, Deboleena Roy, Indranil Chakraborty, Kaushik Roy

Applications based on Deep Neural Networks (DNNs) have grown exponentially in the past decade. To match their increasing computational needs, several Non-Volatile Memory (NVM) crossbar based accelerators have been propos…

Exploiting Safe Spots in Neural Networks for Preemptive Robustness and Out-of-Distribution Detection

2021-01-01 · Seungyong Moon, Gaon An, Hyun Oh Song

Recent advances on adversarial defense mainly focus on improving the classifier’s robustness against adversarially perturbed inputs. In this paper, we turn our attention from classifiers to inputs and explore if there ex…

Adversarial DefenseOut-of-Distribution Detection