# Unadversarial Examples: Designing Objects for Robust Vision

arXiv: https://arxiv.org/abs/2012.12235 · HTML: https://mlsanity.com/paper/2012.12235/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 30 of 45)

- [Exploring Visual Prompts for Adapting Large-Scale Models](https://mlsanity.com/paper/2203.17274/) (2022)
- [Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets](https://mlsanity.com/paper/2204.00032/) (2022)
- [Understanding and Improving Visual Prompting: A Label-Mapping Perspective](https://mlsanity.com/paper/2211.11635/) (2022)
- [Improved OOD Generalization via Adversarial Training and Pre-training](https://mlsanity.com/paper/2105.11144/) (2021)
- [Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training](https://mlsanity.com/paper/2102.04716/) (2021)
- [Visual Prompting for Adversarial Robustness](https://mlsanity.com/paper/2210.06284/) (2022)
- [A Survey on Physical Adversarial Attack in Computer Vision](https://mlsanity.com/paper/2209.14262/) (2022)
- [The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training](https://mlsanity.com/paper/2211.00525/) (2022)
- ["Adversarial Examples" for Proof-of-Learning](https://mlsanity.com/paper/2108.09454/) (2021)
- [Defensive Patches for Robust Recognition in the Physical World](https://mlsanity.com/paper/2204.06213/) (2022)
- [The Best Defense is a Good Offense: Adversarial Augmentation against Adversarial Attacks](https://mlsanity.com/paper/2305.14188/) (2023)
- [Evolution of Neural Tangent Kernels under Benign and Adversarial Training](https://mlsanity.com/paper/2210.12030/) (2022)
- [Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond](https://mlsanity.com/paper/2306.00419/) (2023)
- [Can Adversarial Training Be Manipulated By Non-Robust Features?](https://mlsanity.com/paper/2201.13329/) (2022)
- [Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization](https://mlsanity.com/paper/2410.07018/) (2024)
- [Simulated Adversarial Testing of Face Recognition Models](https://mlsanity.com/paper/2106.04569/) (2021)
- [Squeeze Training for Adversarial Robustness](https://mlsanity.com/paper/2205.11156/) (2022)
- [Adversarial Examples in the Physical World: A Survey](https://mlsanity.com/paper/2311.01473/) (2023)
- [Task Bias in Vision-Language Models](https://mlsanity.com/paper/2212.04412/) (2022)
- [Breaking Correlation Shift via Conditional Invariant Regularizer](https://mlsanity.com/paper/2207.06687/) (2022)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [Physical Passive Patch Adversarial Attacks on Visual Odometry Systems](https://mlsanity.com/paper/2207.05729/) (2022)
- [Adversarial Machine Learning for Social Good: Reframing the Adversary as an Ally](https://mlsanity.com/paper/2310.03614/) (2023)
- [Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment](https://mlsanity.com/paper/2408.06079/) (2024)
- [Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks](https://mlsanity.com/paper/2112.05634/) (2021)
- [ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models](https://mlsanity.com/paper/2510.26096/) (2025)
- [Amicable Aid: Perturbing Images to Improve Classification Performance](https://mlsanity.com/paper/2112.04720/) (2021)
- [Model Monitoring and Robustness of In-Use Machine Learning Models: Quantifying Data Distribution Shifts Using Population Stability Index](https://mlsanity.com/paper/2302.00775/) (2023)
- [A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications](https://mlsanity.com/paper/2304.10679/) (2023)
- [Uncovering the Hidden Cost of Model Compression](https://mlsanity.com/paper/2308.14969/) (2023)

## Abstract (arXiv)

We study a class of realistic computer vision settings wherein one can influence the design of the objects being recognized. We develop a framework that leverages this capability to significantly improve vision models' performance and robustness. This framework exploits the sensitivity of modern machine learning algorithms to input perturbations in order to design "robust objects," i.e., objects that are explicitly optimized to be confidently detected or classified. We demonstrate the efficacy of the framework on a wide variety of vision-based tasks ranging from standard benchmarks, to (in-simulation) robotics, to real-world experiments. Our code can be found at https://git.io/unadversarial .