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

July 31, 2023

Transferable Attack for Semantic Segmentation
Mengqi He, Jing Zhang, Zhaoyuan Yang, Mingyi He, Nick Barnes, Yuchao Dai
Adversarial Attack Semantic Segmentation Adversarial Example Transferable Attack

July 30, 2023

On Neural Network approximation of ideal adversarial attack and convergence of adversarial training
Rajdeep Haldar, Qifan Song
Adversarial Attack Adversarial Training Early Stage Convergence Adversarial Loss Learned Function Neural Network Approximation Optimal Attack

July 28, 2023

Adversarial training for tabular data with attack propagation
Tiago Leon Melo, João Bravo, Marco O. P. Sampaio, Paolo Romano, Hugo Ferreira, João Tiago Ascensão, Pedro Bizarro
Machine Learning Adversarial Attack Machine Learning Model Adversarial Training Tabular Data Credit Card Fraud Detection

July 27, 2023

July 26, 2023

Characterizing Data Point Vulnerability via Average-Case Robustness
Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
Adversarial Attack Native Robustness Adversarial Robustness Software Vulnerability Robustness Bias Average Case Robustness

July 25, 2023

July 24, 2023

July 23, 2023

Towards Generic and Controllable Attacks Against Object Detection
Guopeng Li, Yue Xu, Jian Ding, Gui-Song Xia
Adversarial Attack Adversarial Example Object Detection Model Social Generic Image Attack

July 21, 2023

Adversarial Attack

Papers

Transferable Attack for Semantic Segmentation

On Neural Network approximation of ideal adversarial attack and convergence of adversarial training

Adversarial training for tabular data with attack propagation

Universal and Transferable Adversarial Attacks on Aligned Language Models

NSA: Naturalistic Support Artifact to Boost Network Confidence

When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-$k$ Multi-Label Learning

Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World

Characterizing Data Point Vulnerability via Average-Case Robustness

On the unreasonable vulnerability of transformers for image restoration -- and an easy fix

Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation

Why Don't You Clean Your Glasses? Perception Attacks with Dynamic Optical Perturbations

An Estimator for the Sensitivity to Perturbations of Deep Neural Networks

Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

Towards Generic and Controllable Attacks Against Object Detection

Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks

Robust Feature Inference: A Test-time Defense Strategy using Spectral Projections

Adversarial attacks for mixtures of classifiers

A Holistic Assessment of the Reliability of Machine Learning Systems

FACADE: A Framework for Adversarial Circuit Anomaly Detection and Evaluation