Adversarial Robustness

Adversarial robustness focuses on developing machine learning models resistant to adversarial attacks—small, carefully crafted input perturbations designed to cause misclassification. Current research investigates diverse defense mechanisms, including adversarial training, data purification using diffusion models, and biologically-inspired regularizers, often applied to convolutional neural networks (CNNs), transformers, and spiking neural networks (SNNs). This field is crucial for ensuring the reliability and safety of AI systems in real-world applications, particularly in safety-critical domains like autonomous driving and healthcare, where model failures can have severe consequences.

Papers

January 7, 2025

An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised Learning
Fatemeh Ghofrani, Pooyan Jamshidi
Self Supervised Learning Training Data High Efficiency Adversarial Training Adversarial Robustness Empirical Study Accuracy Robustness

January 6, 2025

On the Adversarial Robustness of Benjamini Hochberg
Louis L Chen, Roberto Szechtman, Matan Seri
Data Detection Adversarial Robustness Outlier Detection

January 5, 2025

Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks
Yang Wang, Chenghua Lin
Adversarial Attack Deep Learning Model New Benchmark Adversarial Robustness Natural Language Inference AI Model Textual Adversarial Attack Four Bar

January 3, 2025

Rerouting LLM Routers
Avital Shafran, Roei Schuster, Thomas Ristenpart, Vitaly Shmatikov
Native Robustness Adversarial Robustness Adversarial Input LLM Safety

December 30, 2024

RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses
Mohamed Djilani, Salah Ghamizi, Maxime Cordy
Adversarial Robustness White Box Black Box Attack Black Box Adversarial Attack Truly Robust Case Provable Defense

December 29, 2024

On Adversarial Robustness of Language Models in Transfer Learning
Bohdan Turbal, Anastasiia Mazur, Jiaxu Zhao, Mykola Pechenizkiy
Language Model Adversarial Attack Native Robustness Transfer Learning Adversarial Robustness

December 28, 2024

December 27, 2024

December 26, 2024

Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field
Keke Tang, Weiyao Ke, Weilong Peng, Xiaofei Wang, Ziyong Du, Zhize Wu, Peican Zhu, Zhihong Tian
Adversarial Attack Point Cloud Adversarial Robustness Adversarial Perturbation 3D Point Cloud Object Surface Explicit Surface Imperceptible Adversarial

December 25, 2024

Evaluating the Adversarial Robustness of Detection Transformers
Amirhossein Nazeri, Chunheng Zhao, Pierluigi Pisu
Adversarial Attack Adversarial Robustness Detection Transformer Robust Object Detection Black Box Adversarial Attack Transformer Based Detector CNN Based Detector

December 24, 2024

December 20, 2024

Adversarial Robustness through Dynamic Ensemble Learning
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial Attack Adversarial Training Adversarial Robustness Adversarial Scenario Adversarial Pattern Ensemble Selection

December 19, 2024

December 16, 2024

Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation
Svetlana Pavlitska, Enrico Eisen, J. Marius Zöllner
Adversarial Attack Semantic Segmentation Adversarial Robustness Mixture of Expert Adversarial Vulnerability Architecture Perspective Gating Mechanism Transfer Attack

December 15, 2024

Learning Robust and Privacy-Preserving Representations via Information Theory
Binghui Zhang, Sayedeh Leila Noorbakhsh, Yun Dong, Yuan Hong, Binghui Wang
Adversarial Robustness Theoretical Understanding Full Information Robust Learning Attribute Inference Attack Multi Step Adversarial Attack Privacy Preserving Representation Attribute Privacy

December 14, 2024

Improving Graph Neural Networks via Adversarial Robustness Evaluation
Yongyu Wang
Graph Neural Network Adversarial Robustness Nearest Neighbor Graph

Adversarial Robustness

Papers

An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised Learning

On the Adversarial Robustness of Benjamini Hochberg

Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks

Rerouting LLM Routers

RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses

On Adversarial Robustness of Language Models in Transfer Learning

A Robust Adversarial Ensemble with Causal (Feature Interaction) Interpretations for Image Classification

Adversarial Robustness for Deep Learning-based Wildfire Prediction Models

Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness

Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning

Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field

Evaluating the Adversarial Robustness of Detection Transformers

On the Local Complexity of Linear Regions in Deep ReLU Networks

Efficient Contrastive Explanations on Demand

Adversarial Robustness through Dynamic Ensemble Learning

Boosting Graph Neural Network Training by Focusing on Non-Robust Samples from the Training Set

Holistic Adversarially Robust Pruning

Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation

Learning Robust and Privacy-Preserving Representations via Information Theory

Improving Graph Neural Networks via Adversarial Robustness Evaluation