Adversarial Attack

Adversarial attacks aim to deceive machine learning models by subtly altering input data, causing misclassifications or other erroneous outputs. Current research focuses on developing more robust models and detection methods, exploring various attack strategies across different model architectures (including vision transformers, recurrent neural networks, and graph neural networks) and data types (images, text, signals, and tabular data). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of AI systems in diverse applications, from autonomous vehicles to medical diagnosis and cybersecurity.

Papers

February 1, 2023

Effectiveness of Moving Target Defenses for Adversarial Attacks in ML-based Malware Detection
Aqib Rashid, Jose Such
Adversarial Attack Attack Strategy Adversarial Machine Learning Based Malware Detection Moving Target Defense
Exploring Semantic Perturbations on Grover
Pranav Kulkarni, Ziqing Ji, Yan Xu, Marko Neskovic, Kevin Nolan
Adversarial Attack Fake News Fake News Detection Semantic Perturbation Grover Search Algorithm

January 31, 2023

The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models
Son Quoc Tran, Phong Nguyen-Thuan Do, Uyen Le, Matt Kretchmar
Adversarial Attack Native Robustness Language Understanding Pretrained Language Model Reading Comprehension Impact Assessment Unanswerable Question
Reverse engineering adversarial attacks with fingerprints from adversarial examples
David Aaron Nicholson, Vincent Emanuele
Adversarial Attack Adversarial Example Reverse Engineering Attack Algorithm Reverse Noise
Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond
Meyer Scetbon, Elvis Dohmatob
Adversarial Attack Native Robustness Robust Model Robust Regression Early Stopping Adversarial Risk
Inference Time Evidences of Adversarial Attacks for Forensic on Transformers
Hugo Lemarchant, Liangzi Li, Yiming Qian, Yuta Nakashima, Hajime Nagahara
Adversarial Attack Vision Transformer Transformer Megatron Decepticons Adversarial Perturbation Adversarial Sample Latent Vector Forensic Analysis
Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning
Chaoxi Niu, Guansong Pang, Ling Chen
Adversarial Attack Self Supervised Contrastive Learning Hard Negative Mining

January 30, 2023

Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification
João Vitorino, Isabel Praça, Eva Maia
Adversarial Attack Adversarial Example Classification Code Robust Learning IoT Intrusion Detection Adversarial Evasion Attack Realistic Adversarial
Language-Driven Anchors for Zero-Shot Adversarial Robustness
Xiao Li, Wei Zhang, Yining Liu, Zhanhao Hu, Bo Zhang, Xiaolin Hu
Adversarial Attack Adversarial Training Adversarial Robustness Zero Shot Adversarial Robustness
On the Efficacy of Metrics to Describe Adversarial Attacks
Tommaso Puccetti, Tommaso Zoppi, Andrea Ceccarelli
Adversarial Attack Metric Library Adversarial DEfense Adversarial Image Attack Dataset
Improving Adversarial Transferability with Scheduled Step Size and Dual Example
Zeliang Zhang, Peihan Liu, Xiaosen Wang, Chenliang Xu
Adversarial Attack Adversarial Example Exemplar Image Adversarial Transferability
Identifying Adversarially Attackable and Robust Samples
Vyas Raina, Mark Gales
Adversarial Attack Robust Statistic Deep Attack
Adversarial Attacks on Adversarial Bandits
Yuzhe Ma, Zhijin Zhou
Adversarial Attack Bandit Algorithm Adversarial Bandit Adversarial Multi Armed Bandit

January 28, 2023

Node Injection for Class-specific Network Poisoning
Ansh Kumar Sharma, Rahul Kukreja, Mayank Kharbanda, Tanmoy Chakraborty
Graph Neural Network Adversarial Attack Poisoning Attack Node Injection
Selecting Models based on the Risk of Damage Caused by Adversarial Attacks
Jona Klemenc, Holger Trittenbach
Artificial Intelligence Adversarial Attack High Quality Risk Description Adversary Agent
Semantic Adversarial Attacks on Face Recognition through Significant Attributes
Yasmeen M. Khedr, Yifeng Xiong, Kun He
Adversarial Attack Face Recognition Rich Attribute Semantic Adversarial Adversarial Face

January 27, 2023

Certified Invertibility in Neural Networks via Mixed-Integer Programming
Tianqi Cui, Thomas Bertalan, George J. Pappas, Manfred Morari, Ioannis G. Kevrekidis, Mahyar Fazlyab
Neural Network Adversarial Attack Mixed Integer Discrete Time Imperceptible Perturbation Restricted Approximate Invertibility
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
Sungmin Cha, Sungjun Cho, Dasol Hwang, Honglak Lee, Taesup Moon, Moontae Lee
LeArning Abstract Adversarial Attack Adversarial Example Pre Trained Model Pre Trained Classifier Level Unlearning
Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks
Wei Tao, Lei Bao, Sheng Long, Gaowei Wu, Qing Tao
Adversarial Attack Adversarial Example NCD Method Gradient Method Unified View Step Size Adaptive Gradient Gradient Based Adversarial
Targeted Attacks on Timeseries Forecasting
Yuvaraj Govindarajulu, Avinash Amballa, Pavan Kulkarni, Manojkumar Parmar
Adversarial Attack Time Series Time Series Forecasting Adversarial Input Targeted Attack Projected Gradient Descent Attack

Adversarial Attack

Papers

Effectiveness of Moving Target Defenses for Adversarial Attacks in ML-based Malware Detection

Exploring Semantic Perturbations on Grover

The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models

Reverse engineering adversarial attacks with fingerprints from adversarial examples

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond

Inference Time Evidences of Adversarial Attacks for Forensic on Transformers

Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning

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

Language-Driven Anchors for Zero-Shot Adversarial Robustness

On the Efficacy of Metrics to Describe Adversarial Attacks

Improving Adversarial Transferability with Scheduled Step Size and Dual Example

Identifying Adversarially Attackable and Robust Samples

Adversarial Attacks on Adversarial Bandits

Node Injection for Class-specific Network Poisoning

Selecting Models based on the Risk of Damage Caused by Adversarial Attacks

Semantic Adversarial Attacks on Face Recognition through Significant Attributes

Certified Invertibility in Neural Networks via Mixed-Integer Programming

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

Targeted Attacks on Timeseries Forecasting