# Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shift

arXiv: https://arxiv.org/abs/2407.13700 · HTML: https://mlsanity.com/paper/2407.13700/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 30 of 32)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [Enhancing the Transferability of Adversarial Attacks through Variance Tuning](https://mlsanity.com/paper/2103.15571/) (2021)
- [Frequency Domain Model Augmentation for Adversarial Attack](https://mlsanity.com/paper/2207.05382/) (2022)
- [Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World](https://mlsanity.com/paper/2103.01050/) (2021)
- [Robustness of classifiers: from adversarial to random noise](https://mlsanity.com/paper/1608.08967/) (2016)
- [Analysis of classifiers' robustness to adversarial perturbations](https://mlsanity.com/paper/1502.02590/) (2015)
- [Fast Feature Fool: A data independent approach to universal adversarial perturbations](https://mlsanity.com/paper/1707.05572/) (2017)
- [Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations](https://mlsanity.com/paper/2202.08602/) (2022)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction](https://mlsanity.com/paper/1911.11616/) (2019)
- [Cross-Modality Perturbation Synergy Attack for Person Re-identification](https://mlsanity.com/paper/2401.10090/) (2024)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions](https://mlsanity.com/paper/1808.01153/) (2018)
- [Exploring Color Invariance through Image-Level Ensemble Learning](https://mlsanity.com/paper/2401.10512/) (2024)
- [Transfer Learning based Dynamic Multiobjective Optimization Algorithms](https://mlsanity.com/paper/1612.06093/) (2016)

## Built on by (most cited first, 9 of 9)

- [Phy124: Fast Physics-Driven 4D Content Generation from a Single Image](https://mlsanity.com/paper/2409.07179/) (2024)
- [RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions](https://mlsanity.com/paper/2508.03077/) (2025)
- [StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance](https://mlsanity.com/paper/2510.06635/) (2025)
- [Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation](https://mlsanity.com/paper/2505.15191/) (2025)
- [One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models](https://mlsanity.com/paper/2507.07709/) (2025)
- [On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning](https://mlsanity.com/paper/2505.12681/) (2025)
- [GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation](https://mlsanity.com/paper/2505.15194/) (2025)
- [Disentangled Geometric Alignment with Adaptive Contrastive Perturbation for Reliable Domain Transfer](https://mlsanity.com/paper/2505.15241/) (2025)
- [Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction](https://mlsanity.com/paper/2606.10571/) (2026)

## Abstract (arXiv)

Studying adversarial attacks on artificial intelligence (AI) systems helps discover model shortcomings, enabling the construction of a more robust system. Most existing adversarial attack methods only concentrate on single-task single-model or single-task cross-model scenarios, overlooking the multi-task characteristic of artificial intelligence systems. As a result, most of the existing attacks do not pose a practical threat to a comprehensive and collaborative AI system. However, implementing cross-task attacks is highly demanding and challenging due to the difficulty in obtaining the real labels of different tasks for the same picture and harmonizing the loss functions across different tasks. To address this issue, we propose a self-supervised Cross-Task Attack framework (CTA), which utilizes co-attention and anti-attention maps to generate cross-task adversarial perturbation. Specifically, the co-attention map reflects the area to which different visual task models pay attention, while the anti-attention map reflects the area that different visual task models neglect. CTA generates cross-task perturbations by shifting the attention area of samples away from the co-attention map and closer to the anti-attention map. We conduct extensive experiments on multiple vision tasks and the experimental results confirm the effectiveness of the proposed design for adversarial attacks.