# Universal, transferable and targeted adversarial attacks

arXiv: https://arxiv.org/abs/1908.11332 · HTML: https://mlsanity.com/paper/1908.11332/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2019.

## Built on by (most cited first, 7 of 7)

- [MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformer](https://mlsanity.com/paper/2301.11798/) (2023)
- [Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Series](https://mlsanity.com/paper/2101.05639/) (2021)
- [Opinions Vary? Diagnosis First!](https://mlsanity.com/paper/2202.06505/) (2022)
- [Calibrate the inter-observer segmentation uncertainty via diagnosis-first principle](https://mlsanity.com/paper/2208.03016/) (2022)
- [On Distinctive Properties of Universal Perturbations](https://mlsanity.com/paper/2112.15329/) (2021)
- [An Efficient Person Clustering Algorithm for Open Checkout-free Groceries](https://mlsanity.com/paper/2208.02973/) (2022)
- [Evo: Autoregressive-Diffusion Large Language Models with Evolving Balance](https://mlsanity.com/paper/2603.06617/) (2026)

## Abstract (arXiv)

Deep Neural Networks have been found vulnerable re-cently. A kind of well-designed inputs, which called adver-sarial examples, can lead the networks to make incorrectpredictions. Depending on the different scenarios, goalsand capabilities, the difficulties of the attacks are different.For example, a targeted attack is more difficult than a non-targeted attack, a universal attack is more difficult than anon-universal attack, a transferable attack is more difficultthan a nontransferable one. The question is: Is there existan attack that can meet all these requirements? In this pa-per, we answer this question by producing a kind of attacksunder these conditions. We learn a universal mapping tomap the sources to the adversarial examples. These exam-ples can fool classification networks to classify all of theminto one targeted class, and also have strong transferability.Our code is released at: xxxxx.