Imperceptible Attack

Imperceptible attacks exploit vulnerabilities in machine learning models by introducing subtle, human-undetectable perturbations to input data, causing misclassifications or biased outputs. Current research focuses on developing increasingly effective attacks across various modalities (images, text, audio) and model types (image classifiers, LLMs, speech recognition systems), often employing optimization algorithms like Frank-Wolfe or distributionally robust optimization to craft these perturbations. This research is crucial for evaluating the robustness of AI systems and informing the development of more secure and reliable models, with implications for applications ranging from facial recognition to autonomous systems.

Papers

January 9, 2025

On Measuring Unnoticeability of Graph Adversarial Attacks: Observations, New Measure, and Applications
Hyeonsoo Jo, Hyunjin Hwang, Fanchen Bu, Soo Yong Lee, Chanyoung Park, Kijung Shin
Adversarial Attack Financial Application Evolving Observation New Measure Imperceptible Attack Graph Adversarial Attack Graph Poisoning Attack Noticeable Difference

December 15, 2024

PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks
Jin Li, Zitong Yu, Ziqiang He, Z. Jane Wang, Xiangui Kang
Adversarial Perturbation Dual System Imperceptible Pattern Imperceptible Attack Imperceptible Adversarial Unlocking Potential Optimal Attack

July 11, 2024

Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systems
Yuxin Cao, Yumeng Zhu, Derui Wang, Sheng Wen, Minhui Xue, Jin Lu, Hao Ge
Adversarial Attack Adversarial Example Threat Word Accessibility Issue Imperceptible Attack Facial Region

June 7, 2024

LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses
Weiran Lin, Anna Gerchanovsky, Omer Akgul, Lujo Bauer, Matt Fredrikson, Zifan Wang
Large Language Model Complex Prompt Recommendation Task Imperceptible Attack Pre Sale Dialogue

April 9, 2024

Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning
Emre Ozfatura, Kerem Ozfatura, Alptekin Kupcu, Deniz Gunduz
Network Pruning Byzantine Attack Imperceptible Pattern Imperceptible Attack Byzantine Failure

February 14, 2024

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
Jessica Quaye, Alicia Parrish, Oana Inel, Charvi Rastogi, Hannah Rose Kirk, Minsuk Kahng, Erin van Liemt, Max Bartolo, Jess Tsang, Justin White, Nathan Clement, Rafael Mosquera, Juan Ciro, Vijay Janapa Reddi, Lora Aroyo
Text to Image Generation Generative AI Model Adversarial Prompt Red Teaming Potential Harm Unsafe Image Imperceptible Attack Adversarial Challenge

November 27, 2023

Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights
Ryoya Nara, Yusuke Matsui
Adversarial Attack Adversarial Example DCU Insight AQ Imperceptible Attack Adversarial Challenge

October 12, 2023

Invisible Threats: Backdoor Attack in OCR Systems
Mauro Conti, Nicola Farronato, Stefanos Koffas, Luca Pajola, Stjepan Picek
Backdoor Attack Optical Character Recognition Imperceptible Attack

July 25, 2023

Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation
Junbin Fang, Canjian Jiang, You Jiang, Puxi Lin, Zhaojie Chen, Yujing Sun, Siu-Ming Yiu, Zoe L. Jiang
Adversarial Attack Face Recognition Fast Adversarial Training Imperceptible Attack Implant Position Illumination Modulation

June 1, 2023

Reconstruction Distortion of Learned Image Compression with Imperceptible Perturbations
Yang Sui, Zhuohang Li, Ding Ding, Xiang Pan, Xiaozhong Xu, Shan Liu, Zhenzhong Chen
Adversarial Example Learned Image Compression Image Transmission Imperceptible Pattern Imperceptible Attack Imperceptible Perturbation Lens Flare

December 14, 2022

SAIF: Sparse Adversarial and Imperceptible Attack Framework
Tooba Imtiaz, Morgan Kohler, Jared Miller, Zifeng Wang, Mario Sznaier, Octavia Camps, Jennifer Dy
Adversarial Attack Imperceptible Attack Sparse Attack Sparse Adversarial Attack

October 15, 2022

Dynamics-aware Adversarial Attack of Adaptive Neural Networks
An Tao, Yueqi Duan, Yingqi Wang, Jiwen Lu, Jie Zhou
Adversarial Attack Imperceptible Attack Adaptive Neural Learning Based Attack

July 20, 2022

Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks
Tim Franzmeyer, Stephen McAleer, João F. Henriques, Jakob N. Foerster, Philip H. S. Torr, Adel Bibi, Christian Schroeder de Witt
Adversarial Attack Information Theoretic Detectability Imperceptible Attack Space Attack

July 17, 2022

Threat Model-Agnostic Adversarial Defense using Diffusion Models
Tsachi Blau, Roy Ganz, Bahjat Kawar, Alex Bronstein, Michael Elad
Diffusion Model Adversarial Attack Adversarial Training Adversarial Perturbation Threat Word Imperceptible Attack Agnostic Adversarial

June 4, 2022

Saliency Attack: Towards Imperceptible Black-box Adversarial Attack
Zeyu Dai, Shengcai Liu, Ke Tang, Qing Li
Adversarial Attack Adversarial Example Saliency Detection Imperceptible Pattern Imperceptible Attack

March 17, 2022

PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks
Yue Wang, Wenqing Li, Esha Sarkar, Muhammad Shafique, Michail Maniatakos, Saif Eddin Jabari
Deep Neural Network Backdoor Attack Faulty Negative Mitigation Backdoor Detection Coherence Modeling Imperceptible Attack

March 3, 2022

Why adversarial training can hurt robust accuracy
Jacob Clarysse, Julia Hörrmann, Fanny Yang
Adversarial Attack Adversarial Training Robust Generalization Imperceptible Attack

November 30, 2021

Human Imperceptible Attacks and Applications to Improve Fairness
Xinru Hua, Huanzhong Xu, Jose Blanchet, Viet Nguyen
Financial Application Procedural Fairness Image Quality Assessment Distributionally Robust Optimization Imperceptible Attack Well Trained

November 5, 2021

Sequential Randomized Smoothing for Adversarially Robust Speech Recognition
Raphael Olivier, Bhiksha Raj
Adversarial Attack Automatic Speech Recognition Speech Recognition Randomized Smoothing ASR Model Adaptive Attack Imperceptible Attack

Imperceptible Attack

Papers

On Measuring Unnoticeability of Graph Adversarial Attacks: Observations, New Measure, and Applications

PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks

Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systems

LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses

Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation

Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights

Invisible Threats: Backdoor Attack in OCR Systems

Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation

Reconstruction Distortion of Learned Image Compression with Imperceptible Perturbations

SAIF: Sparse Adversarial and Imperceptible Attack Framework

Dynamics-aware Adversarial Attack of Adaptive Neural Networks

Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks

Threat Model-Agnostic Adversarial Defense using Diffusion Models

Saliency Attack: Towards Imperceptible Black-box Adversarial Attack

PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks

Why adversarial training can hurt robust accuracy

Human Imperceptible Attacks and Applications to Improve Fairness

Sequential Randomized Smoothing for Adversarially Robust Speech Recognition