Adversarial Sample

Adversarial samples are inputs designed to intentionally mislead machine learning models, primarily by introducing small, imperceptible perturbations to otherwise correctly classified data. Current research focuses on developing more robust models through techniques like adversarial training, purification methods using generative models (e.g., GANs), and exploring the vulnerabilities of various architectures, including convolutional neural networks, recurrent networks, and large language models. Understanding and mitigating the impact of adversarial samples is crucial for ensuring the reliability and security of machine learning systems across diverse applications, from cybersecurity to medical diagnosis.

Papers

January 14, 2025

DisCoPatch: Batch Statistics Are All You Need For OOD Detection, But Only If You Can Trust Them
Francisco Caetano, Christiaan Viviers, Luis A. Zavala-Mondragón, Peter H. N. de With, Fons van der Sommen
Generative Adversarial Network Distribution Detection Adversarial Sample Covariate Shift Batch Size Adversarial Discriminator

December 11, 2024

Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds
Shuhai Zhang, Jiahao Yang, Hui Luo, Jie Chen, Li Wang, Feng Liu, Bo Han, Mingkui Tan
Adversarial Perturbation Adversarial Sample Data Manifold Adversarial Purification Latent Space Optimization Diffusion Purification DNN Robustness

December 10, 2024

December 8, 2024

December 3, 2024

Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script
Xi Cao, Dolma Dawa, Nuo Qun, Trashi Nyima
Native Robustness Chinese Character Adversarial Sample NLP Model Textual Adversarial Attack Black Box Language Model Chinese Language Model

October 21, 2024

Conflict-Aware Adversarial Training
Zhiyu Xue, Haohan Wang, Yao Qin, Ramtin Pedarsani
Adversarial Training Adversarial Robustness Adversarial Sample Adversarial Loss

October 16, 2024

New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes
Yanyun Wang, Li Liu, Zi Liang, Qingqing Ye, Haibo Hu
Native Robustness Adversarial Example Adversarial Training Adversarial Robustness Adversarial Sample Robust Learning Function Class

October 13, 2024

Understanding Robustness of Parameter-Efficient Tuning for Image Classification
Jiacheng Ruan, Xian Gao, Suncheng Xiang, Mingye Xie, Ting Liu, Yuzhuo Fu
Native Robustness Classification Code Adversarial Sample Parameter Efficient Tuning Learnable Parameter Perturbation Attack Natural Robustness Research

October 9, 2024

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
Han Shen, Pin-Yu Chen, Payel Das, Tianyi Chen
Fine Tuning Bilevel Optimization Adversarial Sample LLM Fine Tuning Seal Generation

September 23, 2024

Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training
Jinpeng Lin, Xulei Yang, Tianrui Li, Xun Xu
Adversarial Attack Adversarial Training Adversarial Robustness Self Training Adversarial Sample Test Time Adversarial Purification Point Cloud Recognition

September 1, 2024

Comprehensive Botnet Detection by Mitigating Adversarial Attacks, Navigating the Subtleties of Perturbation Distances and Fortifying Predictions with Conformal Layers
Rahul Yumlembam, Biju Issac, Seibu Mary Jacob, Longzhi Yang
Adversarial Attack Adversarial Example Adversarial Sample Conformal FRP@TPR95 Metric Botnet Related Malware BotNet Detection

August 20, 2024

MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification
Huafeng Qin, Yuming Fu, Huiyan Zhang, Mounim A. El-Yacoubi, Xinbo Gao, Qun Song, Jun Wang
Adversarial Attack Adversarial Perturbation Multi Scale Memory Trace Adversarial Sample

August 14, 2024

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
Zhibo Jin, Jiayu Zhang, Zhiyu Zhu, Chenyu Zhang, Jiahao Huang, Jianlong Zhou, Fang Chen
Adversarial Attack Adversarial Sample Adversarial Parameter

August 8, 2024

Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness
Xiaojing Fan, Chunliang Tao
Large Language Model Adversarial Attack High Efficiency Adversarial Robustness System Performance Adversarial Sample Tiny Refinement Elicit Resilience

August 6, 2024

Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models
Haonan Zheng, Wen Jiang, Xinyang Deng, Wenrui Li
Adversarial Attack Full Model Adversarial Sample Adversarial Patch Visual Language Task Multimodal Decision

August 5, 2024

On the Robustness of Malware Detectors to Adversarial Samples
Muhammad Salman, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Muhammad Ikram, Sidharth Kaushik, Mohamed Ali Kaafar
Adversarial Attack Native Robustness Adversarial Example Adversarial Sample Adversarial Malware Sensitive Hashing

July 30, 2024

DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers
C. A. Martínez-Mejía, J. Solano, J. Breier, D. Bucko, X. Hou
Adversarial Sample CNN Architecture Neural Network Layer Backdoor Injection Fault Injection Attack Deep Attack

July 29, 2024

DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models
Jing Yang, Runping Xi, Yingxin Lai, Xun Lin, Zitong Yu
Text to Image Diffusion Model Adversarial Sample Personalized Generation Dual Domain Anti Personalization

Adversarial Sample

Papers

DisCoPatch: Batch Statistics Are All You Need For OOD Detection, But Only If You Can Trust Them

Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds

Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency

A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detection

Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling

DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization

Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script

Conflict-Aware Adversarial Training

New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes

Understanding Robustness of Parameter-Efficient Tuning for Image Classification

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection

Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training

Comprehensive Botnet Detection by Mitigating Adversarial Attacks, Navigating the Subtleties of Perturbation Distances and Fortifying Predictions with Conformal Layers

MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack

Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness

Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models

On the Robustness of Malware Detectors to Adversarial Samples

DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers

DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models