mlsanityData to 14 Oct 2026

Evaluating the Semantic-to-Geometric Gap in Adversarial Defenses Against Vision-Language Model-Based Plagiarism

arXiv 2609.26733 ↗First posted 22 Sep 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

The rapidly advancing capabilities of vision-language models (VLMs) present a systemic challenge to academic integrity. VLMs now allow students to bypass meaningful engagement by capturing and submitting graphical problems as singular images, a practice we define as trivial plagiarism. To provide educators with actionable data on VLM limitations, we investigate the efficacy of heuristic adversarial image transformations designed to degrade model performance while remaining human-interpretable. Through a two-phase evaluation of introductory assessments, we manually assess baseline VLM performance on circuit diagrams, followed by an automated large-scale evaluation of topological structures (logic gates) and coordinate geometry (Karnaugh maps). We find that while highly capable VLMs can exhibit appreciable robustness, all models suffer vulnerability to adversarial perturbations. We conclude that while visual perturbations act as a viable near-term stopgap, long-term assessment security requires educators to reapproach assessment design given continually increasing VLM performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 11 of its 26 references that are in the map. First posted on arXiv 22 Sep 2026.

Builds on

11 of 26 references.

References · 11

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2018Generalisation in humans and deep neural networkscited by 237
  3. 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
  4. 2023Testing of Detection Tools for AI-Generated Textcited by 90
  5. 2022How Large Language Models are Transforming Machine-Paraphrased Plagiarismcited by 38
  6. 2025InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Modelscited by 28
  7. 2023Game of Tones: Faculty detection of GPT-4 generated content in university assessmentscited by 16
  8. 2023Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attackcited by 10
  9. 2024Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbationcited by 5
  10. 2025Can AI Recognize Its Own Reflection? Self-Detection Performance of LLMs in Computing Educationcited by 3
  11. 2023Inappropriate Benefits and Identification of ChatGPT Misuse in Programming Tests: A Controlled Experimentcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack
  2. 2024Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
  3. 2026It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at ε≤ 4/255
  4. 2025Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation
  5. 2024Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
  6. 2025Attention! Your Vision Language Model Could Be Maliciously Manipulated
  7. 2025VLM@school -- Evaluation of AI image understanding on German middle school knowledge
  8. 2024ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time