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 20, 2023

Diversifying the High-level Features for better Adversarial Transferability
Zhiyuan Wang, Zeliang Zhang, Siyuan Liang, Xiaosen Wang
Adversarial Attack Adversarial Example Adversarial Transferability Level Feature

April 19, 2023

GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
Zaitang Li, Pin-Yu Chen, Tsung-Yi Ho
Adversarial Attack Generative Model Generative Adversarial Network Adversarial Robustness Adversarial Perturbation Human Score Global Robustness

April 18, 2023

April 17, 2023

RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networks
Yunruo Zhang, Tianyu Du, Shouling Ji, Peng Tang, Shanqing Guo
Adversarial Attack Native Robustness Recurrent Neural Network Mt RNN Frame Attack

April 14, 2023

April 11, 2023

April 10, 2023

April 7, 2023

Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones
Jiaping Xiao, Mir Feroskhan
Adversarial Attack Deep Reinforcement Learning Various Fast Moving Drone Adversarial Agent Safe Navigation Pursuit Evasion Pursuit Evasion Game

April 6, 2023

Robust Neural Architecture Search
Xunyu Zhu, Jian Li, Yong Liu, Weiping Wang
Adversarial Attack Adversarial Example Neural Architecture Search Robust Neural Architecture Search

April 5, 2023

Adversarial Attack

Papers

Diversifying the High-level Features for better Adversarial Transferability

GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models

Towards the Transferable Audio Adversarial Attack via Ensemble Methods

Masked Language Model Based Textual Adversarial Example Detection

AI Product Security: A Primer for Developers

RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networks

Combining Generators of Adversarial Malware Examples to Increase Evasion Rate

Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense

Overload: Latency Attacks on Object Detection for Edge Devices

Benchmarking the Physical-world Adversarial Robustness of Vehicle Detection

Defense-Prefix for Preventing Typographic Attacks on CLIP

Generating Adversarial Attacks in the Latent Space

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence

RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks

Benchmarking the Robustness of Quantized Models

Robust Deep Learning Models Against Semantic-Preserving Adversarial Attack

Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones

Robust Neural Architecture Search

How to choose your best allies for a transferable attack?

Dynamic Adversarial Resource Allocation: the dDAB Game