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

October 7, 2023

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
Ziyi Yin, Muchao Ye, Tianrong Zhang, Tianyu Du, Jinguo Zhu, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma
Adversarial Attack Adversarial Robustness Pre Trained Model Vision Language Image Text Pair Adversarial Sample Vision Language Task Modal Attack

October 1, 2023

Counterfactual Image Generation for adversarially robust and interpretable Classifiers
Rafael Bischof, Florian Scheidegger, Michael A. Kraus, A. Cristiano I. Malossi
Adversarial Attack Generative Adversarial Network Adversarial Sample Counterfactual Image Interpretable Classifier

September 29, 2023

Intrinsic Biologically Plausible Adversarial Robustness
Matilde Tristany Farinha, Thomas Ortner, Giorgia Dellaferrera, Benjamin Grewe, Angeliki Pantazi
Adversarial Attack Adversarial Example Adversarial Robustness Adversarial Sample Natural Adversarial

September 25, 2023

On the Effectiveness of Adversarial Samples against Ensemble Learning-based Windows PE Malware Detectors
Trong-Nghia To, Danh Le Kim, Do Thi Thu Hien, Nghi Hoang Khoa, Hien Do Hoang, Phan The Duy, Van-Hau Pham
Adversarial Attack Diverse Ensemble Adversarial Sample Malware Detection Malware Analysis Based Malware Metamorphic Malware

September 20, 2023

PRAT: PRofiling Adversarial aTtacks
Rahul Ambati, Naveed Akhtar, Ajmal Mian, Yogesh Singh Rawat
Adversarial Attack Adversarial Example Adversarial Sample Adversarial Datasets

September 13, 2023

Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments
Simon Queyrut, Valerio Schiavoni, Pascal Felber
Adversarial Attack Adversarial Example Self Attention Adversarial Sample Adversarial Image Trusted Execution Environment White Box Adversarial

September 7, 2023

Adversarially Robust Deep Learning with Optimal-Transport-Regularized Divergences
Jeremiah Birrell, Mohammadreza Ebrahimi
Adversarial Attack Adversarial Training Adversarial Robustness Optimal Transport Adversarial Sample Robust Deep

August 29, 2023

Advancing Adversarial Robustness Through Adversarial Logit Update
Hao Xuan, Peican Zhu, Xingyu Li
Adversarial Attack Adversarial Training Adversarial Robustness Adversarial Sample Adversarial Purification Successful Adversarial Attack

August 15, 2023

A Review of Adversarial Attacks in Computer Vision
Yutong Zhang, Yao Li, Yin Li, Zhichang Guo
Adversarial Attack Computer Vision Adversarial Sample White Box Deep Neural Network Classifier

July 19, 2023

Towards Building More Robust Models with Frequency Bias
Qingwen Bu, Dong Huang, Heming Cui
Adversarial Training Adversarial Learning Adversarial Sample Adversarial Framework Frequency Bias

July 15, 2023

Why Does Little Robustness Help? Understanding and Improving Adversarial Transferability from Surrogate Training
Yechao Zhang, Shengshan Hu, Leo Yu Zhang, Junyu Shi, Minghui Li, Xiaogeng Liu, Wei Wan, Hai Jin
Adversarial Example Adversarial Training Adversarial Sample Robustness Problem Surrogate Model Training

July 13, 2023

Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems
Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo, Eric Chan-Tin, Tamer Abuhmed
Deep Learning Model Adversarial Example Adversarial Sample Black Box Attack Interpretable Deep Learning

July 12, 2023

Single-Class Target-Specific Attack against Interpretable Deep Learning Systems
Eldor Abdukhamidov, Mohammed Abuhamad, George K. Thiruvathukal, Hyoungshick Kim, Tamer Abuhmed
Adversarial Attack Adversarial Sample Adversarial Loss Interpretable Deep Learning Targeted Attack

July 5, 2023

GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations
Julia Lust, Alexandru P. Condurache
Deep Neural Network Adversarial Attack Strong Generalization High Uncertainty Anticipation Distribution Data Adversarial Sample Generalization Error Transformation Invariance

June 27, 2023

June 20, 2023

Comparative Evaluation of Recent Universal Adversarial Perturbations in Image Classification
Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li
Convolutional Neural Network Image Classification Adversarial Sample Comparative Evaluation Universal Adversarial Universal Adversarial Perturbation

June 7, 2023

Adversarial Sample Detection Through Neural Network Transport Dynamics
Skander Karkar, Patrick Gallinari, Alain Rakotomamonjy
Neural Network Adversarial Sample Vector Field Adversarial Detection Invisible Attack

May 25, 2023

Adversarial Sample

Papers

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Counterfactual Image Generation for adversarially robust and interpretable Classifiers

Intrinsic Biologically Plausible Adversarial Robustness

On the Effectiveness of Adversarial Samples against Ensemble Learning-based Windows PE Malware Detectors

PRAT: PRofiling Adversarial aTtacks

Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments

Adversarially Robust Deep Learning with Optimal-Transport-Regularized Divergences

Advancing Adversarial Robustness Through Adversarial Logit Update

A Review of Adversarial Attacks in Computer Vision

Towards Building More Robust Models with Frequency Bias

Why Does Little Robustness Help? Understanding and Improving Adversarial Transferability from Surrogate Training

Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems

Single-Class Target-Specific Attack against Interpretable Deep Learning Systems

GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations

Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability

On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection

Comparative Evaluation of Recent Universal Adversarial Perturbations in Image Classification

Adversarial Sample Detection Through Neural Network Transport Dynamics

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score