# Real-Time Adversarial Attacks

arXiv: https://arxiv.org/abs/1905.13399 · HTML: https://mlsanity.com/paper/1905.13399/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2019.

## Built on by (most cited first, 11 of 11)

- [Real-Time Neural Voice Camouflage](https://mlsanity.com/paper/2112.07076/) (2021)
- [ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints](https://mlsanity.com/paper/2201.01621/) (2022)
- [Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectives](https://mlsanity.com/paper/2307.01390/) (2023)
- [SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems](https://mlsanity.com/paper/2103.10651/) (2021)
- [Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs](https://mlsanity.com/paper/2601.06460/) (2026)
- [Online Adversarial Attacks](https://mlsanity.com/paper/2103.02014/) (2021)
- [LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models](https://mlsanity.com/paper/2604.18803/) (2026)
- [Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future](https://mlsanity.com/paper/2207.09912/) (2022)
- [Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection](https://mlsanity.com/paper/2604.10460/) (2026)
- [INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression](https://mlsanity.com/paper/2604.11928/) (2026)
- [Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks](https://mlsanity.com/paper/2606.06833/) (2026)

## Abstract (arXiv)

In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are very effective, they only focus on scenarios where the target model takes static input, i.e., an attacker can observe the entire original sample and then add a perturbation at any point of the sample. These attack approaches are not applicable to situations where the target model takes streaming input, i.e., an attacker is only able to observe past data points and add perturbations to the remaining (unobserved) data points of the input. In this paper, we propose a real-time adversarial attack scheme for machine learning models with streaming inputs.