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

January 31, 2023

January 30, 2023

January 28, 2023

Master's Thesis: Out-of-distribution Detection with Energy-based Models
Sven Elflein
Deep Learning Adversarial Example Distribution Detection Deep Network Expert Knowledge Energy Based Model Electronic Thesis Training Data Distribution Energy Based Prior

January 27, 2023

January 17, 2023

Denoising Diffusion Probabilistic Models as a Defense against Adversarial Attacks
Lars Lien Ankile, Anna Midgley, Sebastian Weisshaar
Diffusion Model Adversarial Attack Adversarial Example Denoising Diffusion Probabilistic Model

January 13, 2023

On the feasibility of attacking Thai LPR systems with adversarial examples
Chissanupong Jiamsuchon, Jakapan Suaboot, Norrathep Rattanavipanon
Adversarial Attack Adversarial Example Optical Character Recognition Character Recognition Task Feasibility License Plate

January 7, 2023

January 1, 2023

Generalizable Black-Box Adversarial Attack with Meta Learning
Fei Yin, Yong Zhang, Baoyuan Wu, Yan Feng, Jingyi Zhang, Yanbo Fan, Yujiu Yang
Adversarial Attack Adversarial Example Adversarial Perturbation Black Box Attack Black Box Adversarial Attack

December 31, 2022

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence
Han Fang, Jiyi Zhang, Yupeng Qiu, Ke Xu, Chengfang Fang, Ee-Chien Chang
Adversarial Attack Adversarial Example Visual Creation Forensic Analysis Noise Robust Loss

December 20, 2022

December 19, 2022

December 18, 2022

Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks
Anqi Zhao, Tong Chu, Yahao Liu, Wen Li, Jingjing Li, Lixin Duan
Adversarial Example Black Box Black Box Model New Attack Distribution Discrepancy Optimal Discrepancy

December 16, 2022

Adversarial Example Defense via Perturbation Grading Strategy
Shaowei Zhu, Wanli Lyu, Bin Li, Zhaoxia Yin, Bin Luo
Deep Neural Network Adversarial Example Adversarial Perturbation DNN Framework

Adversarial Example

Papers

Reverse engineering adversarial attacks with fingerprints from adversarial examples

RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion

Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification

Improving Adversarial Transferability with Scheduled Step Size and Dual Example

Master's Thesis: Out-of-distribution Detection with Energy-based Models

Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers

Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks

Denoising Diffusion Probabilistic Models as a Defense against Adversarial Attacks

On the feasibility of attacking Thai LPR systems with adversarial examples

REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service

Adversarial training with informed data selection

Generalizable Black-Box Adversarial Attack with Meta Learning

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence

Unleashing the Power of Visual Prompting At the Pixel Level

In and Out-of-Domain Text Adversarial Robustness via Label Smoothing

Multi-head Uncertainty Inference for Adversarial Attack Detection

TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization

Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition

Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks

Adversarial Example Defense via Perturbation Grading Strategy