Adaptive Attack

Adaptive attacks, which leverage knowledge of a system's defenses to craft more effective adversarial examples, are a growing concern across various machine learning applications. Current research focuses on developing both stronger adaptive attacks and more robust defenses, often employing techniques like optimization-based methods, ensemble models, and self-supervised learning to improve detection and resilience. This research is crucial for ensuring the security and reliability of machine learning systems in high-stakes domains, such as healthcare, finance, and autonomous systems, where vulnerabilities to adaptive attacks can have significant consequences.

Papers

June 3, 2023

Can Directed Graph Neural Networks be Adversarially Robust?
Zhichao Hou, Xitong Zhang, Wei Wang, Charu C. Aggarwal, Xiaorui Liu
Graph Neural Network Native Robustness Adaptive Attack

April 16, 2023

A Random-patch based Defense Strategy Against Physical Attacks for Face Recognition Systems
JiaHao Xie, Ye Luo, Jianwei Lu
Adaptive Attack Complex Deep Face Recognition System Perturbation Attack Physical Attack

March 4, 2023

Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Thomas Philippon, Christian Gagné
Adversarial Robustness Diverse Ensemble Structured Output Robustness Evaluation Better Robustness Adaptive Attack Ensemble Diversity Neural Network Ensemble

February 23, 2023

A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Boyang Zhang, Xinlei He, Yun Shen, Tianhao Wang, Yang Zhang
Adversarial Example Word List Adaptive Attack Story Plot Model Stealing Attack Attack Model Target Model Shadow Model

January 31, 2023

Are Defenses for Graph Neural Networks Robust?
Felix Mujkanovic, Simon Geisler, Stephan Günnemann, Aleksandar Bojchevski
Graph Neural Network Native Robustness Adaptive Attack

August 31, 2022

Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning
Zhiyuan He, Yijun Yang, Pin-Yu Chen, Qiang Xu, Tsung-Yi Ho
Deep Neural Network Self Supervised Learning Adversarial Example Adversarial Text Thy Neighbor Adaptive Attack Adversarial Example Detection

August 29, 2022

Towards Adversarial Purification using Denoising AutoEncoders
Dvij Kalaria, Aritra Hazra, Partha Pratim Chakrabarti
Adversarial Attack Deep Learning Architecture Denoising Autoencoder Adaptive Attack

July 13, 2022

Game of Trojans: A Submodular Byzantine Approach
Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu, Bo Li, Bhaskar Ramasubramanian, Radha Poovendran
Submodular Maximization Game Content Adaptive Attack Adaptive Adversary

June 25, 2022

Cascading Failures in Smart Grids under Random, Targeted and Adaptive Attacks
Sushmita Ruj, Arindam Pal
Random Node Smart Grid Random Participation Leg Failure Adaptive Attack Targeted Attack

January 24, 2022

What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
Yijun Yang, Ruiyuan Gao, Yu Li, Qiuxia Lai, Qiang Xu
Adversarial Example Adversarial Training Semantic Consistency Adaptive Attack Network Inference Semantic Adversarial

November 22, 2021

Medical Aegis: Robust adversarial protectors for medical images
Qingsong Yao, Zecheng He, S. Kevin Zhou
Adversarial Example Medical Image Adaptive Attack Adversarial Manipulation

November 5, 2021

Sequential Randomized Smoothing for Adversarially Robust Speech Recognition
Raphael Olivier, Bhiksha Raj
Adversarial Attack Automatic Speech Recognition Speech Recognition Randomized Smoothing ASR Model Adaptive Attack Imperceptible Attack