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 18, 2024

Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shift
Qingyuan Zeng, Yunpeng Gong, Min Jiang
Adversarial Attack Adversarial Perturbation Task Attack
Prover-Verifier Games improve legibility of LLM outputs
Jan Hendrik Kirchner, Yining Chen, Harri Edwards, Jan Leike, Nat McAleese, Yuri Burda
Adversarial Attack Readability Control LLM Output Proof Checker
Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking
Yunpeng Gong, Chuangliang Zhang, Yongjie Hou, Lifei Chen, Min Jiang
Convolutional Neural Network Adversarial Attack Adversarial Robustness Structured Dropout Feature Masking Robust Convolutional Neural Network CNN Framework
Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls
Aras Selvi, Eleonora Kreacic, Mohsen Ghassemi, Vamsi Potluru, Tucker Balch, Manuela Veloso
Adversarial Attack Native Robustness Empirical Risk Minimization Robust Optimization Distributional Assumption Robust Regression Sliced Wasserstein Wasserstein Uncertainty
PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving
Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang, Haijing Guo, Shuyong Gao, Wenqiang Zhang
Adversarial Attack Autonomous Driving Vision Foundation Model Black Box Adversarial Attack Perturbation Attack

July 17, 2024

July 16, 2024

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness
Ryo Hase, Ye Wang, Toshiaki Koike-Akino, Jing Liu, Kieran Parsons
Adversarial Attack Adversarial Robustness Adversarial Perturbation Randomized Smoothing Enhanced Robustness
Relaxing Graph Transformers for Adversarial Attacks
Philipp Foth, Lukas Gosch, Simon Geisler, Leo Schwinn, Stephan Günnemann
Graph Neural Network Adversarial Attack Graph Transformer Node Injection
Enhancing TinyML Security: Study of Adversarial Attack Transferability
Parin Shah, Yuvaraj Govindarajulu, Pavan Kulkarni, Manojkumar Parmar
Adversarial Attack Study Feature TinyML Model Adversarial Vulnerability Embedded System Adversarial Transferability
AEMIM: Adversarial Examples Meet Masked Image Modeling
Wenzhao Xiang, Chang Liu, Hang Su, Hongyang Yu
Adversarial Attack Adversarial Example Supervised ImageNet
Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness
Kai Guo, Zewen Liu, Zhikai Chen, Hongzhi Wen, Wei Jin, Jiliang Tang, Yi Chang
Large Language Model LeArning Abstract Adversarial Attack Graph Drawing Model Robustness Deep Dive Text Attack Text Perturbation
Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysis
Zhipeng He, Chun Ouyang, Laith Alzubaidi, Alistair Barros, Catarina Moreira
Adversarial Attack Tabular Data Empirical Analysis Imperceptible Pattern Imperceptible Perturbation

July 15, 2024

Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
Rishika Bhagwatkar, Shravan Nayak, Reza Bayat, Alexis Roger, Daniel Z Kaplan, Pouya Bashivan, Irina Rish
Adversarial Attack Vision Language Model Adversarial Robustness Adversarial Perturbation DCU Insight AQ Design Choice Image Attack
Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
Quang H. Nguyen, Nguyen Ngoc-Hieu, The-Anh Ta, Thanh Nguyen-Tang, Kok-Seng Wong, Hoang Thanh-Tung, Khoa D. Doan
Adversarial Attack Backdoor Attack Attack Success Rate Clean Label Backdoor Attack Clean Label Attack

July 13, 2024

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu
Adversarial Attack Adversarial Sample Unlabeled Image Untargeted Adversarial Attack

Adversarial Attack

Papers

Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shift

Prover-Verifier Games improve legibility of LLM outputs

Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking

Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls

PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective

Direct Unlearning Optimization for Robust and Safe Text-to-Image Models

Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

Relaxing Graph Transformers for Adversarial Attacks

Enhancing TinyML Security: Study of Adversarial Attack Transferability

AEMIM: Adversarial Examples Meet Masked Image Modeling

Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness

Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysis

Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks

SENTINEL: Securing Indoor Localization against Adversarial Attacks with Capsule Neural Networks

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks

Transferable 3D Adversarial Shape Completion using Diffusion Models

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images