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

August 11, 2023

Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook
Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, Muhammed Shafique
Adversarial Attack Computer Vision Financial Application Attack Strategy Research Challenge Camera Based

August 10, 2023

August 9, 2023

Adversarial ModSecurity: Countering Adversarial SQL Injections with Robust Machine Learning
Biagio Montaruli, Luca Demetrio, Andrea Valenza, Luca Compagna, Davide Ariu, Luca Piras, Davide Balzarotti, Battista Biggio
Adversarial Attack Adversarial Robustness QuEry Based Attack Attack Pattern Web Application Firewall

August 8, 2023

Improving Performance of Semi-Supervised Learning by Adversarial Attacks
Dongyoon Yang, Kunwoong Kim, Yongdai Kim
Adversarial Attack Adversarial Robustness Semi Supervised Learning System Performance Semi Supervision

August 7, 2023

August 6, 2023

SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation
Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, Muhammad Shafique
Adversarial Attack Monocular Depth Estimation Adversarial Patch

August 5, 2023

An AI-Enabled Framework to Defend Ingenious MDT-based Attacks on the Emerging Zero Touch Cellular Networks
Aneeqa Ijaz, Waseem Raza, Hasan Farooq, Marvin Manalastas, Ali Imran
Adversarial Attack New Attack Decomposed Automation Correction AI Based Framework Zero Touch Network

August 4, 2023

Multi-attacks: Many images $+$ the same adversarial attack $\to$ many target labels
Stanislav Fort
Adversarial Attack Adversarial Example Adversarial Perturbation Step Attack Target Class

August 1, 2023

July 31, 2023

Adversarial Attack

Papers

Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook

Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient

Robustifying Point Cloud Networks by Refocusing

Adversarial ModSecurity: Countering Adversarial SQL Injections with Robust Machine Learning

Improving Performance of Semi-Supervised Learning by Adversarial Attacks

Fixed Inter-Neuron Covariability Induces Adversarial Robustness

Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing

Exploring the Physical World Adversarial Robustness of Vehicle Detection

A reading survey on adversarial machine learning: Adversarial attacks and their understanding

Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change

SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation

An AI-Enabled Framework to Defend Ingenious MDT-based Attacks on the Emerging Zero Touch Cellular Networks

Multi-attacks: Many images $+$ the same adversarial attack $\to$ many target labels

Training on Foveated Images Improves Robustness to Adversarial Attacks

Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness

Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches

Doubly Robust Instance-Reweighted Adversarial Training

Adversarially Robust Neural Legal Judgement Systems

A Novel Deep Learning based Model to Defend Network Intrusion Detection System against Adversarial Attacks

Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection