# Adversarial Framing for Image and Video Classification

arXiv: https://arxiv.org/abs/1812.04599 · HTML: https://mlsanity.com/paper/1812.04599/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2018.

## Built on by (most cited first, 15 of 15)

- [Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast](https://mlsanity.com/paper/2402.08567/) (2024)
- [Test-Time Backdoor Attacks on Multimodal Large Language Models](https://mlsanity.com/paper/2402.08577/) (2024)
- [Adversarially Robust One-class Novelty Detection](https://mlsanity.com/paper/2108.11168/) (2021)
- [Adversarial Robustness against Multiple and Single lp-Threat Models via Quick Fine-Tuning of Robust Classifiers](https://mlsanity.com/paper/2105.12508/) (2021)
- [DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networks](https://mlsanity.com/paper/2107.00415/) (2021)
- [StyleFool: Fooling Video Classification Systems via Style Transfer](https://mlsanity.com/paper/2203.16000/) (2022)
- [Parametric Scattering Networks](https://mlsanity.com/paper/2107.09539/) (2021)
- [Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models](https://mlsanity.com/paper/2108.13872/) (2021)
- [Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos](https://mlsanity.com/paper/2504.14921/) (2025)
- [Physical Knowledge Enhanced Deep Neural Network for Sea Surface Temperature Prediction](https://mlsanity.com/paper/2304.09376/) (2023)
- [Thinking Beyond Distributions in Testing Machine Learned Models](https://mlsanity.com/paper/2112.03057/) (2021)
- [On the interplay of adversarial robustness and architecture components: patches, convolution and attention](https://mlsanity.com/paper/2209.06953/) (2022)
- [Adversarial Attack Driven Data Augmentation for Accurate And Robust Medical Image Segmentation](https://mlsanity.com/paper/2105.12106/) (2021)
- [Imperceptible Adversarial Attack on Deep Neural Networks from Image Boundary](https://mlsanity.com/paper/2308.15344/) (2023)
- [Optimizing the AI Development Process by Providing the Best Support Environment](https://mlsanity.com/paper/2305.00136/) (2023)

## Abstract (arXiv)

Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps the image unchanged and only adds an adversarial framing on the border of the image. We show empirically that our method is able to successfully attack state-of-the-art methods on both image and video classification problems. Notably, the proposed method results in a universal attack which is very fast at test time. Source code can be found at https://github.com/zajaczajac/adv_framing .