Adversarial Example

Adversarial examples are subtly altered inputs designed to fool machine learning models, primarily deep neural networks (DNNs), into making incorrect predictions. Current research focuses on improving model robustness against these attacks, exploring techniques like ensemble methods, multi-objective representation learning, and adversarial training, often applied to architectures such as ResNets and Vision Transformers. Understanding and mitigating the threat of adversarial examples is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and natural language processing to malware detection and autonomous driving. The development of robust defenses and effective attack detection methods remains a significant area of ongoing investigation.

Papers

November 30, 2023

Universal Backdoor Attacks
Benjamin Schneider, Nils Lukas, Florian Kerschbaum
Adversarial Example Backdoor Attack Poisoning Attack Transferable Attack Universal Backdoor

November 28, 2023

November 27, 2023

November 23, 2023

When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence
Benoit Coqueret, Mathieu Carbone, Olivier Sentieys, Gabriel Zaid
Adversarial Attack Adversarial Example Black Box Side Channel Embedded Neural Network

November 22, 2023

November 20, 2023

Generating Valid and Natural Adversarial Examples with Large Language Models
Zimu Wang, Wei Wang, Qi Chen, Qiufeng Wang, Anh Nguyen
Adversarial Attack Adversarial Example Word Level Adversarial

November 18, 2023

November 16, 2023

Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting
Romain Ilbert, Thai V. Hoang, Zonghua Zhang, Themis Palpanas
Adversarial Attack Native Robustness Adversarial Example System Performance Adversarial Training Algorithm Data Perturbation

November 14, 2023

November 13, 2023

November 10, 2023

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
Mingyuan Fan, Xiaodan Li, Cen Chen, Wenmeng Zhou, Yaliang Li
Adversarial Attack Adversarial Example Label Regularization Flatness Aware

November 8, 2023

Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data
Thibault Simonetto, Salah Ghamizi, Antoine Desjardins, Maxime Cordy, Yves Le Traon
Deep Neural Network Adversarial Example Adversarial Robustness Tabular Data Robust Training Adaptive Attack Tabular Deep Learning

November 7, 2023

Unveiling Safety Vulnerabilities of Large Language Models
George Kour, Marcel Zalmanovici, Naama Zwerdling, Esther Goldbraich, Ora Nova Fandina, Ateret Anaby-Tavor, Orna Raz, Eitan Farchi
Large Language Model Adversarial Example Semantic Region Unveiling Vulnerability

Adversarial Example

Papers

Universal Backdoor Attacks

Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model

Rethinking Mixup for Improving the Adversarial Transferability

Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights

RetouchUAA: Unconstrained Adversarial Attack via Image Retouching

When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence

Transfer Attacks and Defenses for Large Language Models on Coding Tasks

A Survey of Adversarial CAPTCHAs on its History, Classification and Generation

Generating Valid and Natural Adversarial Examples with Large Language Models

Boost Adversarial Transferability by Uniform Scale and Mix Mask Method

Improving Adversarial Transferability by Stable Diffusion

Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting

$DA^3$: A Distribution-Aware Adversarial Attack against Language Models

Physical Adversarial Examples for Multi-Camera Systems

On The Relationship Between Universal Adversarial Attacks And Sparse Representations

Parrot-Trained Adversarial Examples: Pushing the Practicality of Black-Box Audio Attacks against Speaker Recognition Models

An Extensive Study on Adversarial Attack against Pre-trained Models of Code

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness

Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data

Unveiling Safety Vulnerabilities of Large Language Models