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 24, 2023

Boosting Model Inversion Attacks with Adversarial Examples
Shuai Zhou, Tianqing Zhu, Dayong Ye, Xin Yu, Wanlei Zhou
Generative Adversarial Network Adversarial Example Model Inversion Attack

June 23, 2023

Creating Valid Adversarial Examples of Malware
Matouš Kozák, Martin Jureček, Mark Stamp, Fabio Di Troia
Adversarial Attack Adversarial Example Malware Attack Malware Analysis Adversarial Malware

June 22, 2023

June 14, 2023

June 12, 2023

June 11, 2023

Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework
Minglei Yin, Bin Liu, Neil Zhenqiang Gong, Xin Li
Adversarial Attack Adversarial Example Man in the Middle Attack

June 8, 2023

June 7, 2023

PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts
Xiangjue Dong, Yun He, Ziwei Zhu, James Caverlee
Adversarial Example Adversarial Training Adversarial Prompt Prompt Attack Dialogue State

June 6, 2023

Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters
Xingxing Wei, Shiji Zhao, Bo li
Adversarial Attack Native Robustness Adversarial Example Adversarial Robustness Adversarial Text Max Filter Weight Distribution Adversarial Traffic

June 5, 2023

Evading Black-box Classifiers Without Breaking Eggs
Edoardo Debenedetti, Nicholas Carlini, Florian Tramèr
Adversarial Example Black Box Evasion Attack Decision Based Chicken Egg

June 3, 2023

Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method
Yifei Gao, Zhiyu Lin, Yunfan Yang, Jitao Sang
Adversarial Example Raw Data Practical Method Adversarial Example Detection