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

April 29, 2024

Certification of Speaker Recognition Models to Additive Perturbations
Dmitrii Korzh, Elvir Karimov, Mikhail Pautov, Oleg Y. Rogov, Ivan Oseledets
Adversarial Attack Speaker Recognition Additive Perturbation Speaker Recognition System Voice Authentication Speaker Recognition Model
Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots
Xi Xin, Giles Hooker, Fei Huang
Machine Learning Adversarial Attack Black Box Model Model Interpretability Adversarial Framework Partial Dependence Plot Dependence Shift
Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection
Konstantinos Tsigos, Evlampios Apostolidis, Spyridon Baxevanakis, Symeon Papadopoulos, Vasileios Mezaris
Adversarial Attack Deepfake Detection Deepfake Detector Explainable Artificial Intelligence Method Quantitative Evaluation Face Image Datasets
A Systematic Evaluation of Adversarial Attacks against Speech Emotion Recognition Models
Nicolas Facchinetti, Federico Simonetta, Stavros Ntalampiras
Adversarial Attack Adversarial Example Long Short Term Memory Speech Emotion Recognition

April 27, 2024

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
Yassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer, Michalis Vazirgiannis, Henrik Boström
Graph Neural Network Adversarial Attack Native Robustness Adversarial Robustness General Bound Node Injection
Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks
Yunzhen Feng, Tim G. J. Rudner, Nikolaos Tsilivis, Julia Kempe
Adversarial Attack Adversarial Example Adversarial Robustness Adversarial Perturbation Bayesian Neural Network Bayes Rule

April 26, 2024

Defending Spiking Neural Networks against Adversarial Attacks through Image Purification
Weiran Chen, Qi Sun, Qi Xu
Adversarial Attack Spiking Neural Network Image Purification Non Blind Denoising

April 25, 2024

Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach
Cristopher McIntyre-Garcia, Adrien Heymans, Beril Borali, Won-Sook Lee, Shiva Nejati
Adversarial Attack Adversarial Perturbation Adaptive Importance Object Detection Model Adversarial Testing
Don't Say No: Jailbreaking LLM by Suppressing Refusal
Yukai Zhou, Zhijie Huang, Feiyang Lu, Zhan Qin, Wenjie Wang
Adversarial Attack Medical LLM Natural Language Inference Jailbreak Attack Refusal Response

April 24, 2024

A Comparative Analysis of Adversarial Robustness for Quantum and Classical Machine Learning Models
Maximilian Wendlinger, Kilian Tscharke, Pascal Debus
Adversarial Attack Adversarial Robustness Comparative Study Quantum Machine Learning Quantum Physic Classical Machine Learning Quantum Model Quantum Network
A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challenges
Melih Yazgan, Thomas Graf, Min Liu, Tobias Fleck, J. Marius Zoellner
Timely Survey Adversarial Attack Autonomous Driving Real World Collaborative Perception Intermediate Fusion
Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks
Erh-Chung Chen, Pin-Yu Chen, I-Hsin Chung, Che-Rung Lee
Adversarial Attack Native Robustness Adversarial Example Black Box Adversarial Attack Ghost Object Latency Attack Efficient Ghost
An Empirical Study of Aegis
Daniel Saragih, Paridhi Goel, Tejas Balaji, Alyssa Li
Adversarial Attack Native Robustness Adversarial Example Empirical Study Training Robustness Bit Flip Attack
MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception
Vidit Khazanchi, Pavan Kulkarni, Yuvaraj Govindarajulu, Manojkumar Parmar
Adversarial Attack Feature Wise Shapley Additive Explanation Evasion Attack

April 23, 2024

Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structure
Tobias Ladner, Michael Eichelbeck, Matthias Althoff
Adversarial Attack Native Robustness Deep Convolutional Neural Network Formal Verification Feature Uncertainty Uncertainty Aware Graph
DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermark
Yunming Zhang, Dengpan Ye, Caiyun Xie, Sipeng Shen, Ziyi Liu, Jiacheng Deng, Long Tang
Adversarial Attack Face Recognition Watermarking Method Privacy Protection Adversarial Watermarking Deep Watermarking

April 22, 2024

Automatic Discovery of Visual Circuits
Achyuta Rajaram, Neil Chowdhury, Antonio Torralba, Jacob Andreas, Sarah Schwettmann
Adversarial Attack Vision Model Deep Vision Model Automatic Discovery Interpretable Algorithm Visual Circuit Computational Graph
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
Yiming Liu, Kezhao Liu, Yao Xiao, Ziyi Dong, Xiaogang Xu, Pengxu Wei, Liang Lin
Adversarial Attack Adversarial Perturbation Denoising Diffusion Adversarial Purification Diffusion Purification

April 20, 2024

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think
Haotian Xue, Yongxin Chen
Diffusion Model Adversarial Attack Adversarial Example Adversarial Perturbation Adversarial Sample Tetromino Pixel Knowledge Barrier Adversarial Pattern
Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives
Chenxi Yang, Yujia Liu, Dingquan Li, Yan Zhong, Tingting Jiang
Adversarial Attack Synthesized View Reference Image Quality Assessment Nr Iqa Rank Correlation

Adversarial Attack

Papers

Certification of Speaker Recognition Models to Additive Perturbations

Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots

Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection

A Systematic Evaluation of Adversarial Attacks against Speech Emotion Recognition Models

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks

Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks

Defending Spiking Neural Networks against Adversarial Attacks through Image Purification

Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach

Don't Say No: Jailbreaking LLM by Suppressing Refusal

A Comparative Analysis of Adversarial Robustness for Quantum and Classical Machine Learning Models

A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challenges

Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks

An Empirical Study of Aegis

MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception

Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structure

DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermark

Automatic Discovery of Visual Circuits

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think

Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives