mlsanityData to 7 Oct 2026

Generating Robust Adversarial Examples against Online Social Networks (OSNs)

arXiv 2310.12708 ↗First posted 19 Oct 2023cs.MM cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Online Social Networks (OSNs) have blossomed into prevailing transmission channels for images in the modern era. Adversarial examples (AEs) deliberately designed to mislead deep neural networks (DNNs) are found to be fragile against the inevitable lossy operations conducted by OSNs. As a result, the AEs would lose their attack capabilities after being transmitted over OSNs. In this work, we aim to design a new framework for generating robust AEs that can survive the OSN transmission; namely, the AEs before and after the OSN transmission both possess strong attack capabilities. To this end, we first propose a differentiable network termed SImulated OSN (SIO) to simulate the various operations conducted by an OSN. Specifically, the SIO network consists of two modules: 1) a differentiable JPEG layer for approximating the ubiquitous JPEG compression and 2) an encoder-decoder subnetwork for mimicking the remaining operations. Based upon the SIO network, we then formulate an optimization framework to generate robust AEs by enforcing model outputs with and without passing through the SIO to be both misled. Extensive experiments conducted over Facebook, WeChat and QQ demonstrate that our attack methods produce more robust AEs than existing approaches, especially under small distortion constraints; the performance gain in terms of Attack Success Rate (ASR) could be more than 60%. Furthermore, we build a public dataset containing more than 10,000 pairs of AEs processed by Facebook, WeChat or QQ, facilitating future research in the robust AEs generation. The dataset and code are available at https://github.com/csjunjun/RobustOSNAttack.git.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 33 of its 63 references that are in the map. First posted on arXiv 19 Oct 2023.

Builds on

33 of 63 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  11. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  12. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
21 more
  1. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  2. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  3. 2018Noiseprint: a CNN-based camera model fingerprintcited by 114
  4. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
  5. 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 104
  6. 2018Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examplescited by 98
  7. 2021Invertible Image Signal Processingcited by 94
  8. 2018Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blockscited by 75
  9. 2018Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networkscited by 38
  10. 2017Binary Classification from Positive-Confidence Datacited by 23
  11. 2018MRI Reconstruction via Cascaded Channel-wise Attention Networkcited by 20
  12. 2019Walking on the Edge: Fast, Low-Distortion Adversarial Examplescited by 18
  13. 2019SESF-Fuse: An Unsupervised Deep Model for Multi-Focus Image Fusioncited by 13
  14. 2015Predicting popularity of online videos using Support Vector Regressioncited by 7
  15. 2019Eyenet: Attention based Convolutional Encoder-Decoder Network for Eye Region Segmentationcited by 7
  16. 2021Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attackscited by 7
  17. 2022Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networkscited by 6
  18. 2021Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchycited by 4
  19. 2022Low-Mid Adversarial Perturbation against Unauthorized Face Recognition Systemcited by 4
  20. 2019SkeletonNet: Shape Pixel to Skeleton Pixelcited by 3
  21. 2022Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generationcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networkscited by 6
  2. 2025FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font Knowledgecited by 3
  3. 2024DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domaincited by 2
  4. 2025Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreakingcited by 2