mlsanityData to 7 Oct 2026

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks

arXiv 2407.10179 ↗First posted 14 Jul 2024cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios. Recent studies have introduced textitsingle-target generative attacks that train a generator for each target class to generate highly transferable perturbations, resulting in substantial computational overhead when handling multiple classes. textitMulti-target attacks address this by training only one class-conditional generator for multiple classes. However, the generator simply uses class labels as conditions, failing to leverage the rich semantic information of the target class. To this end, we design a CLIP-guided Generative Network with Cross-attention modules (CGNC) to enhance multi-target attacks by incorporating textual knowledge of CLIP into the generator. Extensive experiments demonstrate that CGNC yields significant improvements over previous multi-target generative attacks, e.g., a 21.46% improvement in success rate from ResNet-152 to DenseNet-121. Moreover, we propose a masked fine-tuning mechanism to further strengthen our method in attacking a single class, which surpasses existing single-target methods.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 55 of its 71 references that are in the map. First posted on arXiv 14 Jul 2024.

Builds on

55 of 71 references.

References · 55

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  11. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  12. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
38 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  2. 2016Adversarial Machine Learning at Scalecited by 934
  3. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  4. 2016Universal adversarial perturbationscited by 774
  5. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  6. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  7. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  8. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  9. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  10. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 309
  11. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  12. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  13. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  14. 2017Generative Adversarial Perturbationscited by 153
  15. 2019Cross-Domain Transferability of Adversarial Perturbationscited by 92
  16. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
  17. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  18. 2023GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesiscited by 84
  19. 2019PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Drivingcited by 72
  20. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  21. 2024Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagescited by 69
  22. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 67
  23. 2021On Generating Transferable Targeted Perturbationscited by 65
  24. 2020Understanding Adversarial Examples from the Mutual Influence of Images and Perturbationscited by 59
  25. 2020Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferabilitycited by 57
  26. 2019Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reductioncited by 47
  27. 2023GIFD: A Generative Gradient Inversion Method with Feature Domain Optimizationcited by 45
  28. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  29. 2023A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidancecited by 40
  30. 2021Image-Based CLIP-Guided Essence Transfercited by 39
  31. 2024One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Modelscited by 39
  32. 2020Yet Another Intermediate-Level Attackcited by 35
  33. 2019Query-efficient Meta Attack to Deep Neural Networkscited by 33
  34. 2018Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressionscited by 31
  35. 2021Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networkscited by 31
  36. 2022Enhancing the Self-Universality for Transferable Targeted Attackscited by 30
  37. 2024Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defensescited by 30
  38. 2024Adversarial Robustness for Visual Grounding of Multimodal Large Language Modelscited by 23

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 13; 2026: 5.

19 papers.

Sort:

By area:

  1. 2025Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMscited by 16
  2. 2025Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputscited by 7
  3. 2025Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Modelscited by 5
  4. 2025Protecting Your Video Content: Disrupting Automated Video-based LLM Annotationscited by 5
  5. 2024Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editingcited by 3
  6. 2025Superplatforms Have to Attack AI Agentscited by 3
  7. 2026Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanizationcited by 3
  8. 2025TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Modelscited by 2
  9. 2026Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimizationcited by 2
  10. 2026Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimizationcited by 2
  11. 2025Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimizationcited by 1
  12. 2025Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIPcited by 0
7 more
  1. 2025Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approachcited by 0
  2. 2025Towards Cross-Domain Multi-Targeted Adversarial Attackscited by 0
  3. 2025Improving Black-Box Generative Attacks via Generator Semantic Consistencycited by 0
  4. 2025Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimizationcited by 0
  5. 2025Improving Sustainability of Adversarial Examples in Class-Incremental Learningcited by 0
  6. 2026DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Modelscited by 0
  7. 2026T-VSS: Test-Time Visual Subspace Steering for Adversarial Robustness of Vision-Language Modelscited by 0