GenAI Detection Tools, Adversarial Techniques and Implications for Inclusivity in Higher Education

Abstract

This study investigates the efficacy of six major Generative AI (GenAI) text detectors when confronted with machine-generated content that has been modified using techniques designed to evade detection by these tools (n=805). The results demonstrate that the detectors' already low accuracy rates (39.5%) show major reductions in accuracy (17.4%) when faced with manipulated content, with some techniques proving more effective than others in evading detection. The accuracy limitations and the potential for false accusations demonstrate that these tools cannot currently be recommended for determining whether violations of academic integrity have occurred, underscoring the challenges educators face in maintaining inclusive and fair assessment practices. However, they may have a role in supporting student learning and maintaining academic integrity when used in a non-punitive manner. These results underscore the need for a combined approach to addressing the challenges posed by GenAI in academia to promote the responsible and equitable use of these emerging technologies. The study concludes that the current limitations of AI text detectors require a critical approach for any possible implementation in HE and highlight possible alternatives to AI assessment strategies.

References in corpus (10)

• Testing of Detection Tools for AI-Generated Text
• Release Strategies and the Social Impacts of Language Models
• The AI Assessment Scale (AIAS): A Framework for Ethical Integration of Generative AI in Educational Assessment
• A Survey on Evaluation of Large Language Models
• Game of Tones: Faculty detection of GPT-4 generated content in university assessments
• Can AI-Generated Text be Reliably Detected?
• ChatGPT v Bard v Bing v Claude 2 v Aria v human-expert. How good are AI chatbots at scientific writing?
• Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
• LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models
• The EAP-AIAS: Adapting the AI Assessment Scale for English for Academic Purposes

Cited by in corpus (3)

• Research Integrity and GenAI: A Systematic Analysis of Ethical Challenges Across Research Phases
• GenAI as Digital Plastic: Understanding Synthetic Media Through Critical AI Literacy
• To Deepfake or Not to Deepfake: Higher Education Stakeholders' Perceptions and Intentions towards Synthetic Media