Adversarial Perturbation

Adversarial perturbation research focuses on developing and mitigating the vulnerability of machine learning models to maliciously crafted inputs designed to cause misclassification or other errors. Current research emphasizes improving the robustness of various model architectures, including deep convolutional neural networks, vision transformers, and graph neural networks, often employing techniques like adversarial training, vector quantization, and optimal transport methods. This field is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and face recognition to robotics and natural language processing, by identifying and addressing vulnerabilities to attacks.

Papers

March 24, 2024

Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
Rui Zheng, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
Adversarial Attack Adversarial Example Adversarial Perturbation Subspace Learning Clean Speech Subspace Prototype Effective Adversarial

March 18, 2024

March 17, 2024

RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning
Javad Rafiei Asl, Prajwal Panzade, Eduardo Blanco, Daniel Takabi, Zhipeng Cai
Language Model Adversarial Perturbation Document Representation

March 14, 2024

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr
Vision Language Model Adversarial Perturbation Complex Prompt Task Specific Model Adversarial Transferability

March 10, 2024

Attacking Transformers with Feature Diversity Adversarial Perturbation
Chenxing Gao, Hang Zhou, Junqing Yu, YuTeng Ye, Jiale Cai, Junle Wang, Wei Yang
Vision Transformer Transformer Megatron Decepticons Adversarial Perturbation White Box

March 8, 2024

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao
Adversarial Attack Adversarial Perturbation 3D Point Cloud Imperceptible Pattern Physical Adversarial Adversarial Shape Prior

March 6, 2024

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability
Rajdeep Haldar, Yue Xing, Qifan Song
Adversarial Attack Mixed Effect Adversarial Perturbation Adversarial Vulnerability Intrinsic Dimension Manifold Attack

February 28, 2024

Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks
Zhewei Wu, Ruilong Yu, Qihe Liu, Shuying Cheng, Shilin Qiu, Shijie Zhou
Adversarial Attack Adversarial Training Adversarial Perturbation Adversarial Defense Robust Tracking Auxiliary Adversarial

February 27, 2024

Adversarial Perturbations of Physical Signals
Robert L. Bassett, Austin Van Dellen, Anthony P. Austin
Machine Learning Model Adversarial Perturbation Abnormal Signal Catastrophic Interference Signal Classification

February 26, 2024

Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing
Kefu Guo, Fengfan Zhou, Hefei Ling, Ping Li, Hui Liu
Adversarial Attack Adversarial Example Adversarial Perturbation Face Recognition Joint Photographic Expert Group Adversarial Face

February 25, 2024

Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks
Zhiying Jiang, Xingyuan Li, Jinyuan Liu, Xin Fan, Risheng Liu
Adversarial Attack Adversarial Perturbation Adaptive Learning Attack Performance Image Stitching Adaptive Adversarial Training

February 19, 2024

Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overview
Alexander Auras, Kanchana Vaishnavi Gandikota, Hannah Droege, Michael Moeller
Native Robustness Adversarial Perturbation Inverse Problem Environment Exploration Variational Method Numerical Experiment Point Estimate

February 16, 2024

Theoretical Understanding of Learning from Adversarial Perturbations
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
LeArning Abstract Adversarial Example Adversarial Perturbation Theoretical Understanding One Hidden Layer

February 14, 2024

Exploring the Adversarial Capabilities of Large Language Models
Lukas Struppek, Minh Hieu Le, Dominik Hintersdorf, Kristian Kersting
Adversarial Example Adversarial Perturbation Adversarial Behavior Adversarial Capability

February 13, 2024

Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks
Qiyuan An, Christos Sevastopoulos, Fillia Makedon
Adversarial Attack Native Robustness Adversarial Perturbation Adversarial Image Hidden Layer Traditional Adversarial Indoor Robot Navigation Free Space Segmentation

February 6, 2024

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
Zhenyu Liu, Garrett Gagnon, Swagath Venkataramani, Liu Liu
Deep Neural Network Adversarial Attack High Efficiency Adversarial Robustness Adversarial Perturbation Industrial Disturbing Noise Noise Injection Critical Neuron

February 5, 2024

January 28, 2024

Intriguing Equivalence Structures of the Embedding Space of Vision Transformers
Shaeke Salman, Md Montasir Bin Shams, Xiuwen Liu
Vision Transformer Adversarial Perturbation Meaningful Representation Deep Space Representation Space Model Equivalence

Adversarial Perturbation

Papers

Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals

Diffusion Denoising as a Certified Defense against Clean-label Poisoning

LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model

RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models

Attacking Transformers with Feature Diversity Adversarial Perturbation

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability

Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks

Adversarial Perturbations of Physical Signals

Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing

Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks

Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overview

Theoretical Understanding of Learning from Adversarial Perturbations

Exploring the Adversarial Capabilities of Large Language Models

Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons

Generalization Properties of Adversarial Training for $\ell_0$-Bounded Adversarial Attacks

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics

Intriguing Equivalence Structures of the Embedding Space of Vision Transformers