Adversarial Perturbation

Adversarial perturbation research focuses on developing and mitigating the vulnerability of machine learning models to maliciously crafted inputs designed to cause misclassification or other errors. Current research emphasizes improving the robustness of various model architectures, including deep convolutional neural networks, vision transformers, and graph neural networks, often employing techniques like adversarial training, vector quantization, and optimal transport methods. This field is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and face recognition to robotics and natural language processing, by identifying and addressing vulnerabilities to attacks.

Papers

May 14, 2024

SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models
Raghuveer Peri, Sai Muralidhar Jayanthi, Srikanth Ronanki, Anshu Bhatia, Karel Mundnich, Saket Dingliwal, Nilaksh Das, Zejiang Hou, Goeric Huybrechts, Srikanth Vishnubhotla, Daniel Garcia-Romero, Sundararajan Srinivasan, Kyu J Han, Katrin Kirchhoff
Adversarial Attack Adversarial Example Adversarial Robustness Multimodal Large Language Model Adversarial Perturbation

May 10, 2024

PUMA: margin-based data pruning
Javier Maroto, Pascal Frossard
Native Robustness Adversarial Training Adversarial Perturbation Data Pruning Accuracy Robustness

May 9, 2024

Universal Adversarial Perturbations for Vision-Language Pre-trained Models
Peng-Fei Zhang, Zi Huang, Guangdong Bai
Full Model Adversarial Robustness Adversarial Perturbation Transferable Adversarial Attack Universal Adversarial

May 8, 2024

Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations
Xuyang Zhong, Yixiao Huang, Chen Liu
Global Evaluation Adversarial Perturbation Efficient Training Robust Model Sparse Attack Sparse Perturbation Box Attack

May 7, 2024

Effective and Robust Adversarial Training against Data and Label Corruptions
Peng-Fei Zhang, Zi Huang, Xin-Shun Xu, Guangdong Bai
Adversarial Training Raw Data Adversarial Perturbation Data Perturbation Label Corruption Robust Adversarial Training

May 4, 2024

Assessing Adversarial Robustness of Large Language Models: An Empirical Study
Zeyu Yang, Zhao Meng, Xiaochen Zheng, Roger Wattenhofer
Adversarial Attack Adversarial Robustness Adversarial Perturbation Empirical Study White Box LLM Robustness

April 30, 2024

Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment
Lei Wang, Desen Yuan
Adversarial Perturbation Image Quality Assessment Causal Representation Learning Imperceptible Adversarial Perturbation Causal Machine

April 27, 2024

Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks
Yunzhen Feng, Tim G. J. Rudner, Nikolaos Tsilivis, Julia Kempe
Adversarial Attack Adversarial Example Adversarial Robustness Adversarial Perturbation Bayesian Neural Network Bayes Rule

April 25, 2024

April 22, 2024

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
Yiming Liu, Kezhao Liu, Yao Xiao, Ziyi Dong, Xiaogang Xu, Pengxu Wei, Liang Lin
Adversarial Attack Adversarial Perturbation Denoising Diffusion Adversarial Purification Diffusion Purification

April 20, 2024

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think
Haotian Xue, Yongxin Chen
Diffusion Model Adversarial Attack Adversarial Example Adversarial Perturbation Adversarial Sample Tetromino Pixel Knowledge Barrier Adversarial Pattern

April 18, 2024

Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang
Large Language Model Adversarial Attack Native Robustness Adversarial Training Adversarial Perturbation Self Supervised Denoising Smoothing Factor

April 16, 2024

Towards a Novel Perspective on Adversarial Examples Driven by Frequency
Zhun Zhang, Yi Zeng, Qihe Liu, Shijie Zhou
Adversarial Example Adversarial Perturbation High Frequency Attack Performance Novel View

April 9, 2024

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
Jianlang Chen, Xuhong Ren, Qing Guo, Felix Juefei-Xu, Di Lin, Wei Feng, Lei Ma, Jianjun Zhao
Adversarial Perturbation Visual Object Tracking Adversarial Data Spatio Temporal Representation

April 8, 2024

Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing
Chengyan Fu, Wenjie Wang
Neural Network Adversarial Perturbation Denoising Diffusion Parameter Efficient Randomized Smoothing

April 1, 2024

The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness
Xuran Li, Peng Wu, Yanting Chen, Xingjun Ma, Zhen Zhang, Kaixiang Dong
Adversarial Perturbation Input Perturbation Adversarial Instance Robust Fairness Adversarial Bias

March 28, 2024

March 25, 2024

The Anatomy of Adversarial Attacks: Concept-based XAI Dissection
Georgii Mikriukov, Gesina Schwalbe, Franz Motzkus, Korinna Bade
Deep Neural Network Adversarial Attack Adversarial Perturbation Interpretable Deep Learning Adversarial Threat XAI Based

Adversarial Perturbation

Papers

SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models

PUMA: margin-based data pruning

Universal Adversarial Perturbations for Vision-Language Pre-trained Models

Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations

Effective and Robust Adversarial Training against Data and Label Corruptions

Assessing Adversarial Robustness of Large Language Models: An Empirical Study

Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment

Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks

Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach

Boosting Model Resilience via Implicit Adversarial Data Augmentation

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think

Advancing the Robustness of Large Language Models through Self-Denoised Smoothing

Towards a Novel Perspective on Adversarial Examples Driven by Frequency

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing

The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness

Imperceptible Protection against Style Imitation from Diffusion Models

Towards Understanding Dual BN In Hybrid Adversarial Training

The Anatomy of Adversarial Attacks: Concept-based XAI Dissection