Sparse Attack

Sparse attacks, a subfield of adversarial machine learning, focus on crafting minimally-perturbed inputs—modifying only a few features—to fool machine learning models. Current research emphasizes developing efficient algorithms for generating these attacks (e.g., variations of projected gradient descent and Bayesian methods) across various model architectures, including convolutional neural networks and vision transformers, and for different data types (images, graphs). This research is crucial for evaluating the robustness of deployed machine learning systems, particularly in safety-critical applications, and for developing more resilient models.

Papers

May 23, 2024

Certified Robustness against Sparse Adversarial Perturbations via Data Localization
Ambar Pal, René Vidal, Jeremias Sulam
Native Robustness Adversarial Robustness Adversarial Perturbation Localization Focus Robustness Guarantee Robust Classifier Sparse Attack Sparse Perturbation

May 8, 2024

Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations
Xuyang Zhong, Yixiao Huang, Chen Liu
Global Evaluation Adversarial Perturbation Efficient Training Robust Model Sparse Attack Sparse Perturbation Box Attack

April 8, 2024

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe
Adversarial Example Adversarial Sample QuEry Based Attack Sparse Attack Sparse Perturbation

February 2, 2024

$σ$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
Antonio Emanuele Cinà, Francesco Villani, Maura Pintor, Lea Schönherr, Battista Biggio, Marcello Pelillo
Adversarial Example Optimization Purpose Adversarial Robustness Norm Attack Sparse Attack \Ell_1$ Norm

November 29, 2023

GSE: Group-wise Sparse and Explainable Adversarial Attacks
Shpresim Sadiku, Moritz Wagner, Sebastian Pokutta
Adversarial Attack Learning Problem Structural Regularization Group Sparsity Sparse Attack Sparse Adversarial Attack

March 1, 2023

To Make Yourself Invisible with Adversarial Semantic Contours
Yichi Zhang, Zijian Zhu, Hang Su, Jun Zhu, Shibao Zheng, Yuan He, Hui Xue
Adversarial Example Sparse Attack

December 14, 2022

SAIF: Sparse Adversarial and Imperceptible Attack Framework
Tooba Imtiaz, Morgan Kohler, Jared Miller, Zifeng Wang, Mario Sznaier, Octavia Camps, Jennifer Dy
Adversarial Attack Imperceptible Attack Sparse Attack Sparse Adversarial Attack

September 20, 2022

Sparse Vicious Attacks on Graph Neural Networks
Giovanni Trappolini, Valentino Maiorca, Silvio Severino, Emanuele Rodolà, Fabrizio Silvestri, Gabriele Tolomei
Graph Neural Network Adversarial Attack Link Prediction Malicious Node Sparse Attack

January 31, 2022

Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Models
Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe
Adversarial Perturbation Black Box Black Box Model Efficient Query Sparse Attack

January 23, 2022

Efficient and Robust Classification for Sparse Attacks
Mark Beliaev, Payam Delgosha, Hamed Hassani, Ramtin Pedarsani
High Efficiency Adversarial Training Defense Method Robust Classification Sparse Attack \Ell_1$ Norm