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

January 26, 2023

January 25, 2023

January 23, 2023

January 22, 2023

Provable Unrestricted Adversarial Training without Compromise with Generalizability
Lilin Zhang, Ning Yang, Yanchao Sun, Philip S. Yu
Adversarial Attack Adversarial Training Adversarial Robustness Stronger Generalizability Unrestricted Adversarial Compromise Decision

January 19, 2023

RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation
Utkarsh Nath, Yancheng Wang, Yingzhen Yang
Adversarial Attack Neural Architecture Search Robust Neural Architecture Robust Neural Architecture Search

January 17, 2023

January 16, 2023

Meta Generative Attack on Person Reidentification
A V Subramanyam
Adversarial Attack Person Re Identification Cross Dataset Generative Attack

January 13, 2023

On the feasibility of attacking Thai LPR systems with adversarial examples
Chissanupong Jiamsuchon, Jakapan Suaboot, Norrathep Rattanavipanon
Adversarial Attack Adversarial Example Optical Character Recognition Character Recognition Task Feasibility License Plate

January 12, 2023

Security-Aware Approximate Spiking Neural Networks
Syed Tihaam Ahmad, Ayesha Siddique, Khaza Anuarul Hoque
Neural Network Adversarial Attack Neuromorphic Computing Full Precision Secure Deep

January 10, 2023

January 9, 2023

On the Susceptibility and Robustness of Time Series Models through Adversarial Attack and Defense
Asadullah Hill Galib, Bidhan Bashyal
Adversarial Attack Native Robustness Backdoor Attack Adversarial DEfense Time Series Model

January 8, 2023

RobArch: Designing Robust Architectures against Adversarial Attacks
ShengYun Peng, Weilin Xu, Cory Cornelius, Kevin Li, Rahul Duggal, Duen Horng Chau, Jason Martin
Adversarial Attack Native Robustness Adversarial Training Robust Architecture

January 5, 2023

Enhancement attacks in biomedical machine learning
Matthew Rosenblatt, Javid Dadashkarimi, Dustin Scheinost
Machine Learning Adversarial Attack Enhancement Attack Better Data

January 4, 2023

Adversarial Attack

Papers

Attacking Important Pixels for Anchor-free Detectors

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

RobustPdM: Designing Robust Predictive Maintenance against Adversarial Attacks

On the Adversarial Robustness of Camera-based 3D Object Detection

DODEM: DOuble DEfense Mechanism Against Adversarial Attacks Towards Secure Industrial Internet of Things Analytics

Practical Adversarial Attacks Against AI-Driven Power Allocation in a Distributed MIMO Network

Provable Unrestricted Adversarial Training without Compromise with Generalizability

RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation

Denoising Diffusion Probabilistic Models as a Defense against Adversarial Attacks

Adversarial AI in Insurance: Pervasiveness and Resilience

Meta Generative Attack on Person Reidentification

On the feasibility of attacking Thai LPR systems with adversarial examples

Security-Aware Approximate Spiking Neural Networks

User-Centered Security in Natural Language Processing

AdvBiom: Adversarial Attacks on Biometric Matchers

On the Susceptibility and Robustness of Time Series Models through Adversarial Attack and Defense

RobArch: Designing Robust Architectures against Adversarial Attacks

Enhancement attacks in biomedical machine learning

Availability Adversarial Attack and Countermeasures for Deep Learning-based Load Forecasting

GUAP: Graph Universal Attack Through Adversarial Patching