Adversarial Attack

Adversarial attacks aim to deceive machine learning models by subtly altering input data, causing misclassifications or other erroneous outputs. Current research focuses on developing more robust models and detection methods, exploring various attack strategies across different model architectures (including vision transformers, recurrent neural networks, and graph neural networks) and data types (images, text, signals, and tabular data). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of AI systems in diverse applications, from autonomous vehicles to medical diagnosis and cybersecurity.

Papers

March 25, 2024

Ensemble Adversarial Defense via Integration of Multiple Dispersed Low Curvature Models
Kaikang Zhao, Xi Chen, Wei Huang, Liuxin Ding, Xianglong Kong, Fan Zhang
Adversarial Attack Adversarial Robustness Ensemble Diversity Ensemble Adversarial

March 24, 2024

March 23, 2024

Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions
Kaiwen Wang, Yinzhe Shen, Martin Lauer
Adversarial Attack Adversarial DEfense Cross Domain Object Detection Low Visibility

March 22, 2024

Robust optimization for adversarial learning with finite sample complexity guarantees
André Bertolace, Konstatinos Gatsis, Kostas Margellos
Adversarial Attack Native Robustness Adversarial Example Adversarial Learning Sample Complexity Robust Optimization Robust Classifier Classifier Robustness

March 20, 2024

March 18, 2024

March 17, 2024

Adversarial Attack

Papers

Ensemble Adversarial Defense via Integration of Multiple Dispersed Low Curvature Models

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

Robust Diffusion Models for Adversarial Purification

Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions

Robust optimization for adversarial learning with finite sample complexity guarantees

Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking

Adversary-Robust Graph-Based Learning of WSIs

Adversary-Augmented Simulation to evaluate fairness on HyperLedger Fabric

Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process

DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation

ADAPT to Robustify Prompt Tuning Vision Transformers

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory

SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator

Problem space structural adversarial attacks for Network Intrusion Detection Systems based on Graph Neural Networks

LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM

Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization

A Modified Word Saliency-Based Adversarial Attack on Text Classification Models

Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentation