Adversarial Noise

Adversarial noise refers to carefully crafted perturbations added to data to mislead machine learning models, primarily deep neural networks. Current research focuses on detecting and mitigating these attacks across various modalities (images, audio, text), employing techniques like generative models (diffusion models), variational sparsification, and biologically-inspired feature extraction to enhance robustness. This field is crucial for ensuring the reliability and security of AI systems in diverse applications, from facial recognition and autonomous driving to medical image analysis and speech recognition, where vulnerabilities to adversarial manipulation can have significant consequences.

Papers

November 11, 2024

Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
Shuyao Li, Sushrut Karmalkar, Ilias Diakonikolas, Jelena Diakonikolas
Distribution Shift Primal Dual Worst Case Adversarial Noise Real Neuron Adversarial Covariate Shift

October 24, 2024

GADT: Enhancing Transferable Adversarial Attacks through Gradient-guided Adversarial Data Transformation
Yating Ma, Xiaogang Xu, Liming Fang, Zhe Liu
Adversarial Example Adversarial Noise Transferable Attack Transferable Adversarial Attack Adversarial Transformation

October 8, 2024

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
June Suk Choi, Kyungmin Lee, Jongheon Jeong, Saining Xie, Jinwoo Shin, Kimin Lee
Image Editing Adversarial Noise Robust Defense Diffusion Based Image Editing Imperceptible Adversarial

October 7, 2024

AnyAttack: Towards Large-scale Self-supervised Generation of Targeted Adversarial Examples for Vision-Language Models
Jiaming Zhang, Junhong Ye, Xingjun Ma, Yige Li, Yunfan Yang, Jitao Sang, Dit-Yan Yeung
Adversarial Attack Vision Language Model Adversarial Example Adversarial Noise Adversarial Image Unsupervised Generation

September 29, 2024

Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises
Anubhooti Jain, Susim Roy, Kwanit Gupta, Mayank Vatsa, Richa Singh
Adversarial Attack Deep Learning Model Adversarial Perturbation Industrial Disturbing Noise Intent Detection Adversarial Noise Kill Chaos Detection Network

September 27, 2024

Robust Network Learning via Inverse Scale Variational Sparsification
Zhiling Zhou, Zirui Liu, Chengming Xu, Yanwei Fu, Xinwei Sun
Variational Method Adversarial Noise Enhanced Robustness Scale Space Robust Network Sparse Variational

September 24, 2024

Revisiting Acoustic Features for Robust ASR
Muhammad A. Shah, Bhiksha Raj
Automatic Speech Recognition Speech Recognition Adversarial Noise Acoustic Feature

September 17, 2024

Contextual Breach: Assessing the Robustness of Transformer-based QA Models
Asir Saadat, Nahian Ibn Asad, Md Farhan Ishmam
Native Robustness Adversarial Perturbation Adversarial Noise Contextual Integrity

September 15, 2024

GLEAN: Generative Learning for Eliminating Adversarial Noise
Justin Lyu Kim, Kyoungwan Woo
Text to Image Diffusion Model Adversarial Noise Generative Learning Oxide GLASS Digital Art

September 12, 2024

September 11, 2024

A Cost-Aware Approach to Adversarial Robustness in Neural Networks
Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy Löfstedt, Erik Elmroth
Neural Network Adversarial Attack Native Robustness Adversarial Robustness Model Performance Model Robustness Adversarial Noise

August 30, 2024

Efficient Testable Learning of General Halfspaces with Adversarial Label Noise
Ilias Diakonikolas, Daniel M. Kane, Sihan Liu, Nikos Zarifis
Polynomial Time Adversarial Noise Margin Halfspaces Testable Learning

August 9, 2024

XNN: Paradigm Shift in Mitigating Identity Leakage within Cloud-Enabled Deep Learning
Kaixin Liu, Huixin Xiong, Bingyu Duan, Zexuan Cheng, Xinyu Zhou, Wanqian Zhang, Xiangyu Zhang
Adversarial Training Adversarial Noise Paradigm Shift Cloud Based

July 14, 2024

Disrupting Diffusion-based Inpainters with Semantic Digression
Geonho Son, Juhun Lee, Simon S. Woo
Text to Image Diffusion Model Deep Fake Adversarial Noise Disruption Prediction

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

June 16, 2024

Improving Adversarial Robustness via Decoupled Visual Representation Masking
Decheng Liu, Tao Chen, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao
Adversarial Robustness Adversarial DEfense Adversarial Noise Feature Masking

June 7, 2024

Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning
Roman Belaire, Arunesh Sinha, Pradeep Varakantham
Adversarial Attack Deep Reinforcement Learning Adversarial Perturbation Bayesian Perspective Adversarial Noise Adversarial Reinforcement Learning Error Minimizing Noise

June 5, 2024

VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise
Zhixun He, Mukesh Singhal
Adversarial Attack Industrial Disturbing Noise U Net Adversarial Noise Adversarial Prediction

May 30, 2024

BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas, Shujian Yu, Stjepan Picek
Backdoor Defense Adversarial Noise Backdoor Detection Policy Violation Hidden Backdoor Backdoor Inversion

Adversarial Noise

Papers

Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise

GADT: Enhancing Transferable Adversarial Attacks through Gradient-guided Adversarial Data Transformation

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

AnyAttack: Towards Large-scale Self-supervised Generation of Targeted Adversarial Examples for Vision-Language Models

Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises

Robust Network Learning via Inverse Scale Variational Sparsification

Revisiting Acoustic Features for Robust ASR

Contextual Breach: Assessing the Robustness of Transformer-based QA Models

GLEAN: Generative Learning for Eliminating Adversarial Noise

LoRID: Low-Rank Iterative Diffusion for Adversarial Purification

High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis

A Cost-Aware Approach to Adversarial Robustness in Neural Networks

Efficient Testable Learning of General Halfspaces with Adversarial Label Noise

XNN: Paradigm Shift in Mitigating Identity Leakage within Cloud-Enabled Deep Learning

Disrupting Diffusion-based Inpainters with Semantic Digression

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

Improving Adversarial Robustness via Decoupled Visual Representation Masking

Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning

VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise

BAN: Detecting Backdoors Activated by Adversarial Neuron Noise