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 2, 2024

Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models
Xu Han, Linghao Jin, Xuezhe Ma, Xiaofeng Liu
Adversarial Attack Vision Language Adversarial Noise Medical Vision Language Pre Training
EvolBA: Evolutionary Boundary Attack under Hard-label Black Box condition
Ayane Tajima, Satoshi Ono
Deep Neural Network Adversarial Attack Adversarial Example Black Box Covariance Matrix Adaptation Evolution Strategy Boundary Attack
MALT Powers Up Adversarial Attacks
Odelia Melamed, Gilad Yehudai, Adi Shamir
Adversarial Attack Reverse Graph Linearization

July 1, 2024

Formal Verification of Object Detection
Avraham Raviv, Yizhak Y. Elboher, Michelle Aluf-Medina, Yael Leibovich Weiss, Omer Cohen, Roy Assa, Guy Katz, Hillel Kugler
Deep Neural Network Adversarial Attack Object Detection Model Adversarial Input Formal Verification
Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid
Kalibinuer Tiliwalidi, Chengyin Hu, Weiwen Shi
Adversarial Attack Thermal Infrared Infrared Object Adversarial Infrared

June 29, 2024

Query-Efficient Hard-Label Black-Box Attack against Vision Transformers
Chao Zhou, Xiaowen Shi, Yuan-Gen Wang
Adversarial Attack Vision Transformer Deep Convolutional Neural Network Adversarial Perturbation Black Box Attack

June 28, 2024

DiffuseDef: Improved Robustness to Adversarial Attacks
Zhenhao Li, Marek Rei, Lucia Specia
Adversarial Attack Native Robustness Adversarial Training Adversarial Text Adversarial Defense
Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features
Feng Liu, Qing Xu, Qijian Zheng
Adversarial Attack Action Recognition Action Classification Human Skeleton Skeletal Motion
IDT: Dual-Task Adversarial Attacks for Privacy Protection
Pedro Faustini, Shakila Mahjabin Tonni, Annabelle McIver, Qiongkai Xu, Mark Dras
Adversarial Attack Sensitive Attribute Attribute Inference Attack
Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness
Erh-Chung Chen, Pin-Yu Chen, I-Hsin Chung, Che-Rung Lee
Deep Neural Network Adversarial Attack Native Robustness Adversarial Robustness Cost Effective Approach Lipschitz Continuity

June 27, 2024

Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
Zheng Fang, Tao Wang, Lingchen Zhao, Shenyi Zhang, Bowen Li, Yunjie Ge, Qi Li, Chao Shen, Qian Wang
Adversarial Attack Adversarial Example Black Box Speech Recognition System Transfer Based Adversarial Attack MI Attack
Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs
Jie Zhang, Zhongqi Wang, Mengqi Lei, Zheng Yuan, Bei Yan, Shiguang Shan, Xilin Chen
Adversarial Attack New Benchmark Large Scale Large Vision Language Model Synthesized Image

June 26, 2024

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
Jonas Ngnawé, Sabyasachi Sahoo, Yann Pequignot, Frédéric Precioso, Christian Gagné
Adversarial Attack Native Robustness Adversarial Vulnerability Robust Decision Margin Consistency
Artificial Immune System of Secure Face Recognition Against Adversarial Attacks
Min Ren, Yunlong Wang, Yuhao Zhu, Yongzhen Huang, Zhenan Sun, Qi Li, Tieniu Tan
Adversarial Attack Nocturnal Insect Breeding Program Artificial Immune System

June 25, 2024

Diffusion-based Adversarial Purification for Intrusion Detection
Mohamed Amine Merzouk, Erwan Beurier, Reda Yaich, Nora Boulahia-Cuppens, Frédéric Cuppens
Diffusion Model Adversarial Attack Adversarial Example Adversarial Robustness Intrusion Detection Adversarial Purification
Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
Vaclav Voracek
Adversarial Attack Adversarial Robustness Parameter Estimation Randomized Smoothing Accurate Treatment Estimation Problem
Detection of Synthetic Face Images: Accuracy, Robustness, Generalization
Nela Petrzelkova, Jan Cech
Adversarial Attack Native Robustness Strong Generalization Data Detection Synthetic Image Synthetic Face Diffusion Based Image Generation Face Generator
CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems
Zhen Chen, Yong Liao, Youpeng Zhao, Zipeng Dai, Jian Zhao
Adversarial Attack Constructive Approach Cooperative Multi Agent Reinforcement Learning Malicious Agent Cooperative Multi Agent System Adversarial Markov Decision Process CUDA Implementation Realistic Adversarial Adversarial Capability

June 24, 2024

Automated Adversarial Discovery for Safety Classifiers
Yash Kumar Lal, Preethi Lahoti, Aradhana Sinha, Yao Qin, Ananth Balashankar
Adversarial Attack Successful Adversarial Attack Safety Classifier
UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification
Alvaro Lopez Pellicer, Kittipos Giatgong, Yi Li, Neeraj Suri, Plamen Angelov
Adversarial Attack Unified Framework Adversarial DEfense Unseen Class Novel Class Discovery Adversarial Scenario Noise Reduction Attack Detection

Adversarial Attack

Papers

Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models

EvolBA: Evolutionary Boundary Attack under Hard-label Black Box condition

MALT Powers Up Adversarial Attacks

Formal Verification of Object Detection

Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid

Query-Efficient Hard-Label Black-Box Attack against Vision Transformers

DiffuseDef: Improved Robustness to Adversarial Attacks

Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features

IDT: Dual-Task Adversarial Attacks for Privacy Protection

Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness

Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems

Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers

Artificial Immune System of Secure Face Recognition Against Adversarial Attacks

Diffusion-based Adversarial Purification for Intrusion Detection

Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness

Detection of Synthetic Face Images: Accuracy, Robustness, Generalization

CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems

Automated Adversarial Discovery for Safety Classifiers

UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification