Adversarial Example

Adversarial examples are subtly altered inputs designed to fool machine learning models, primarily deep neural networks (DNNs), into making incorrect predictions. Current research focuses on improving model robustness against these attacks, exploring techniques like ensemble methods, multi-objective representation learning, and adversarial training, often applied to architectures such as ResNets and Vision Transformers. Understanding and mitigating the threat of adversarial examples is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and natural language processing to malware detection and autonomous driving. The development of robust defenses and effective attack detection methods remains a significant area of ongoing investigation.

Papers

June 18, 2024

Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial Example Textual Adversarial Attack Traditional Adversarial Word Saliency

June 15, 2024

Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networks
Nasrin Alipour, Seyyed Ali SeyyedSalehi
Neural Network Adversarial Attack Adversarial Example Image Classification Distribution Detection Distribution Data Adversarial Sample Robust Classification New Attractor

June 14, 2024

June 13, 2024

Improving Adversarial Robustness via Feature Pattern Consistency Constraint
Jiacong Hu, Jingwen Ye, Zunlei Feng, Jiazhen Yang, Shunyu Liu, Xiaotian Yu, Lingxiang Jia, Mingli Song
Adversarial Attack Adversarial Example Adversarial Robustness Adversarial Perturbation Feature Consistency

June 12, 2024

Adversarial Evasion Attack Efficiency against Large Language Models
João Vitorino, Eva Maia, Isabel Praça
Adversarial Attack Adversarial Example Adversarial Defense Word Level Attack Adversarial Evasion Attack

June 9, 2024

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
Sajjad Amini, Mohammadreza Teymoorianfard, Shiqing Ma, Amir Houmansadr
Convolutional Neural Network Native Robustness Adversarial Example Adversarial Perturbation Document Parsing Sparse Feature Robustness Enhancement

June 8, 2024

Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization
Jiancong Xiao, Ruoyu Sun, Qi Long, Weijie J. Su
Adversarial Example Robust Version Robust Loss Rademacher Complexity Test Time Adversarial

June 7, 2024

ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks
Feiyang Wang, Xingquan Zuo, Hai Huang, Gang Chen
Adversarial Attack Adversarial Example Decision Boundary Black Box Adversarial Attack Decision Based dlADMM Algorithm

June 6, 2024

Interpreting the Second-Order Effects of Neurons in CLIP
Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
Adversarial Example Single CLIP Second Order Single Neuron Level Individual Neuron Polysemantic Neuron

June 5, 2024

June 4, 2024

Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation
Yaohua Liu, Jiaxin Gao, Xuan Liu, Xianghao Jiao, Xin Fan, Risheng Liu
Adversarial Example Surrogate Model Bilevel Optimization Pseudo Victim AttackER Transfer Attack Sequence Length Reduction

June 2, 2024

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
Jiacheng Zhang, Feng Liu, Dawei Zhou, Jingfeng Zhang, Tongliang Liu
Adversarial Example Adversarial Training Robust Classification Accuracy Robustness Adversarial Reweighting

May 31, 2024

Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization
Yisu Liu, Jinyang An, Wanqian Zhang, Dayan Wu, Jingzi Gu, Zheng Lin, Weiping Wang
Adversarial Attack Adversarial Example Diffusion Explainer Adversarial Behavior Customization Method

May 30, 2024

May 29, 2024

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
Shuyu Cheng, Yibo Miao, Yinpeng Dong, Xiao Yang, Xiao-Shan Gao, Jun Zhu
Adversarial Attack Adversarial Example Bayesian Optimization Black Box Model Black Box Adversarial Attack Functional Prior

May 28, 2024

Adversarial Example

Papers

Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation

Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networks

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

Improving Adversarial Robustness via Feature Pattern Consistency Constraint

Adversarial Evasion Attack Efficiency against Large Language Models

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification

Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization

ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks

Interpreting the Second-Order Effects of Neurons in CLIP

ZeroPur: Succinct Training-Free Adversarial Purification

DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain

Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training

Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization

Typography Leads Semantic Diversifying: Amplifying Adversarial Transferability across Multimodal Large Language Models

HOLMES: to Detect Adversarial Examples with Multiple Detectors

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models

PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics