# Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks

arXiv: https://arxiv.org/abs/2410.12076 · HTML: https://mlsanity.com/paper/2410.12076/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Knockoff Nets: Stealing Functionality of Black-Box Models](https://mlsanity.com/paper/1812.02766/) (2018)
- [Adversarial Machine Learning -- Industry Perspectives](https://mlsanity.com/paper/2002.05646/) (2020)
- [Stateful Detection of Black-Box Adversarial Attacks](https://mlsanity.com/paper/1907.05587/) (2019)
- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks](https://mlsanity.com/paper/2110.06904/) (2021)
- [Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks](https://mlsanity.com/paper/2006.14042/) (2020)
- [Towards more Practical Threat Models in Artificial Intelligence Security](https://mlsanity.com/paper/2311.09994/) (2023)
- [A Methodology for Creating AI FactSheets](https://mlsanity.com/paper/2006.13796/) (2020)
- [Evading Black-box Classifiers Without Breaking Eggs](https://mlsanity.com/paper/2306.02895/) (2023)

## Built on by (most cited first, 1 of 1)

- [Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk Assessment](https://mlsanity.com/paper/2508.08629/) (2025)

## Abstract (arXiv)

The vulnerability of machine learning models in adversarial scenarios has garnered significant interest in the academic community over the past decade, resulting in a myriad of attacks and defenses. However, while the community appears to be overtly successful in devising new attacks across new contexts, the development of defenses has stalled. After a decade of research, we appear no closer to securing AI applications beyond additional training. Despite a lack of effective mitigations, AI development and its incorporation into existing systems charge full speed ahead with the rise of generative AI and large language models. Will our ineffectiveness in developing solutions to adversarial threats further extend to these new technologies? In this paper, we argue that overly permissive attack and overly restrictive defensive threat models have hampered defense development in the ML domain. Through the lens of adversarial evasion attacks against neural networks, we critically examine common attack assumptions, such as the ability to bypass any defense not explicitly built into the model. We argue that these flawed assumptions, seen as reasonable by the community based on paper acceptance, have encouraged the development of adversarial attacks that map poorly to real-world scenarios. In turn, new defenses evaluated against these very attacks are inadvertently required to be almost perfect and incorporated as part of the model. But do they need to? In practice, machine learning models are deployed as a small component of a larger system. We analyze adversarial machine learning from a system security perspective rather than an AI perspective and its implications for emerging AI paradigms.