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 8, 2024

Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness
Xiaojing Fan, Chunliang Tao
Large Language Model Adversarial Attack High Efficiency Adversarial Robustness System Performance Adversarial Sample Tiny Refinement Elicit Resilience
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness
Stanislav Fort, Balaji Lakshminarayanan
Adversarial Attack Adversarial Example Adversarial Training Adversarial Robustness Multi Scale Diverse Ensemble
Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
Duanyi Yao, Songze Li, Ye Xue, Jin Liu
Adversarial Attack Adversarial Example Multi Armed Bandit Vertical Federated Learning Adversarial Corruption Optimal Attack
EdgeShield: A Universal and Efficient Edge Computing Framework for Robust AI
Duo Zhong, Bojing Li, Xiang Chen, Chenchen Liu
Adversarial Attack Real Time Edge Computing Universal Image Adversarial Detection Efficient Detection Robust AI Edge Offloading

August 7, 2024

LaFA: Latent Feature Attacks on Non-negative Matrix Factorization
Minh Vu, Ben Nebgen, Erik Skau, Geigh Zollicoffer, Juan Castorena, Kim Rasmussen, Boian Alexandrov, Manish Bhattarai
Adversarial Attack Adversarial Loss Non Negative Matrix Factorization Latent Ensemble Attack
Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks
Keiichiro Yamamura, Issa Oe, Hiroki Ishikura, Katsuki Fujisawa
Adversarial Attack Adversarial Example Conjugate Gradient Attack Performance

August 5, 2024

Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services
Shaopeng Fu, Xuexue Sun, Ke Qing, Tianhang Zheng, Di Wang
Machine Learning Adversarial Attack Pre Trained Downstream Policy Learning
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
Muxi Diao, Rumei Li, Shiyang Liu, Guogang Liao, Jingang Wang, Xunliang Cai, Weiran Xu
Large Language Model Adversarial Attack Adversarial Prompt Upper Ocean Adversarial Machine Learning Adversarial Optimization
On the Robustness of Malware Detectors to Adversarial Samples
Muhammad Salman, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Muhammad Ikram, Sidharth Kaushik, Mohamed Ali Kaafar
Adversarial Attack Native Robustness Adversarial Example Adversarial Sample Adversarial Malware Sensitive Hashing

August 4, 2024

AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning
Xin Wang, Kai Chen, Xingjun Ma, Zhineng Chen, Jingjing Chen, Yu-Gang Jiang
Adversarial Attack Adversarial Example Prompt Tuning QuEry Based Attack
Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification
Honglin Gao, Gaoxi Xiao
Graph Neural Network Adversarial Attack Graph Learning Heterogeneous Graph
A Survey and Evaluation of Adversarial Attacks for Object Detection
Khoi Nguyen Tiet Nguyen, Wenyu Zhang, Kangkang Lu, Yuhuan Wu, Xingjian Zheng, Hui Li Tan, Liangli Zhen
Timely Survey Adversarial Attack Global Evaluation Adversarial Robustness Object Detection

August 3, 2024

ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features
Peng Cheng, Yuwei Wang, Peng Huang, Zhongjie Ba, Xiaodong Lin, Feng Lin, Li Lu, Kui Ren
Adversarial Attack Adversarial Example Linguistic Feature Black Box Language Model Adversarial Audio
Joint Universal Adversarial Perturbations with Interpretations
Liang-bo Ning, Zeyu Dai, Wenqi Fan, Jingran Su, Chao Pan, Luning Wang, Qing Li
Adversarial Attack Adversarial Example
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
Weijie Zheng, Xingjun Ma, Hanxun Huang, Zuxuan Wu, Yu-Gang Jiang
Adversarial Attack Adversarial Example Pre Trained Vision Transformer Adversarial Vulnerability Pre Trained ViT Downstream Model Transfer Based Attack

August 2, 2024

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics
Alexander Gushchin, Khaled Abud, Georgii Bychkov, Ekaterina Shumitskaya, Anna Chistyakova, Sergey Lavrushkin, Bader Rasheed, Kirill Malyshev, Dmitriy Vatolin, Anastasia Antsiferova
Adversarial Attack Adversarial Robustness Image Quality Image Quality Assessment Image Quality Metric
Assessing Robustness of Machine Learning Models using Covariate Perturbations
Arun Prakash R, Anwesha Bhattacharyya, Joel Vaughan, Vijayan N. Nair
Adversarial Attack Native Robustness Machine Learning Model Model Robustness Noise Covariance Local Robustness

Adversarial Attack

Papers

Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness

Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness

Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit

EdgeShield: A Universal and Efficient Edge Computing Framework for Robust AI

LaFA: Latent Feature Attacks on Non-negative Matrix Factorization

Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks

Simple Perturbations Subvert Ethereum Phishing Transactions Detection: An Empirical Analysis

Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey

Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models

Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services

SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models

On the Robustness of Malware Detectors to Adversarial Samples

AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning

Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification

A Survey and Evaluation of Adversarial Attacks for Object Detection

ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features

Joint Universal Adversarial Perturbations with Interpretations

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics

Assessing Robustness of Machine Learning Models using Covariate Perturbations