# Fighting Fire with Fire: On the Feasibility of Protecting Exercises Against AI Cheating

arXiv: https://arxiv.org/abs/2608.01112 · HTML: https://mlsanity.com/paper/2608.01112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [Raising the Cost of Malicious AI-Powered Image Editing](https://mlsanity.com/paper/2302.06588/) (2023)
- [Protecting Intellectual Property of Language Generation APIs with Lexical Watermark](https://mlsanity.com/paper/2112.02701/) (2021)
- [On the Learnability of Watermarks for Language Models](https://mlsanity.com/paper/2312.04469/) (2023)
- [Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models](https://mlsanity.com/paper/2310.13828/) (2023)
- [Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment](https://mlsanity.com/paper/2505.21494/) (2025)
- [WatME: Towards Lossless Watermarking Through Lexical Redundancy](https://mlsanity.com/paper/2311.09832/) (2023)
- [EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models](https://mlsanity.com/paper/2311.12066/) (2023)
- [MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation](https://mlsanity.com/paper/2407.00468/) (2024)
- [GenAI Detection Tools, Adversarial Techniques and Implications for Inclusivity in Higher Education](https://mlsanity.com/paper/2403.19148/) (2024)
- [Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption](https://mlsanity.com/paper/2510.18333/) (2025)

## Abstract (arXiv)

The widespread adoption of generative AI enables students to outsource cognitive effort to increasingly capable assistants, creating an illusion of competence while undermining the independent reasoning that education aims to cultivate. We investigate whether adversarial machine learning can be repurposed to protect educational exercises against such corrosive reliance. Our approach uses multimodal multiple-choice questions whose visual components can be protected with subtle visual perturbations that steer AI solvers toward designated incorrect answers. These responses form a statistical fingerprint: students who blindly copy a solver reproduce the induced answer pattern more frequently than genuine students. We study the feasibility of this paradigm under realistic black-box assistant assumptions using three of the most common state-of-the-art multimodal language models: Anthropic's Claude, Google's Gemini, and OpenAI's ChatGPT. By using accessible surrogate models, we optimize adversarial perturbations that induce consistent response patterns. Those patterns enable principled detection through statistical hypothesis testing. These findings establish both the promise and the limitations of fighting machine-assisted reasoning with the vulnerabilities of the machines themselves.