A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models

• URL: http://arxiv.org/abs/2503.15205v1
• Date: Wed, 19 Mar 2025 13:47:28 GMT
• Title: A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models
• Authors: Don Hickerson, Mike Perkins,
• Abstract summary: We discuss how Internet-sourced training data introduces unintended biases and misinformation into AI systems.<n>We argue that step-around prompting serves a vital role in identifying potential vulnerabilities while acknowledging its dual nature as both a research tool and a security threat.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This research examines the emerging technique of step-around prompt engineering in GenAI research, a method that deliberately bypasses AI safety measures to expose underlying biases and vulnerabilities in GenAI models. We discuss how Internet-sourced training data introduces unintended biases and misinformation into AI systems, which can be revealed through the careful application of step-around techniques. Drawing parallels with red teaming in cybersecurity, we argue that step-around prompting serves a vital role in identifying and addressing potential vulnerabilities while acknowledging its dual nature as both a research tool and a potential security threat. Our findings highlight three key implications: (1) the persistence of Internet-derived biases in AI training data despite content filtering, (2) the effectiveness of step-around techniques in exposing these biases when used responsibly, and (3) the need for robust safeguards against malicious applications of these methods. We conclude by proposing an ethical framework for using step-around prompting in AI research and development, emphasizing the importance of balancing system improvements with security considerations.

Related papers

• Computational Safety for Generative AI: A Signal Processing Perspective [65.268245109828]
  computational safety is a mathematical framework that enables the quantitative assessment, formulation, and study of safety challenges in GenAI.<n>We show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts.<n>We discuss key open research challenges, opportunities, and the essential role of signal processing in computational AI safety.
  arXiv  Detail & Related papers  (2025-02-18T02:26:50Z)
• Open Problems in Machine Unlearning for AI Safety [61.43515658834902]
  Machine unlearning -- the ability to selectively forget or suppress specific types of knowledge -- has shown promise for privacy and data removal tasks.<n>In this paper, we identify key limitations that prevent unlearning from serving as a comprehensive solution for AI safety.
  arXiv  Detail & Related papers  (2025-01-09T03:59:10Z)
• SoK: Watermarking for AI-Generated Content [112.9218881276487]
  Watermarking schemes embed hidden signals within AI-generated content to enable reliable detection.<n>Watermarks can play a crucial role in enhancing AI safety and trustworthiness by combating misinformation and deception.<n>This work aims to guide researchers in advancing watermarking methods and applications, and support policymakers in addressing the broader implications of GenAI.
  arXiv  Detail & Related papers  (2024-11-27T16:22:33Z)
• AI-Augmented Ethical Hacking: A Practical Examination of Manual Exploitation and Privilege Escalation in Linux Environments [2.3020018305241337]
  This study explores the application of generative AI (GenAI) within manual exploitation and privilege escalation tasks in Linux-based penetration testing environments. Our findings demonstrate that GenAI can streamline processes, such as identifying potential attack vectors and parsing complex outputs for sensitive data during privilege escalation.
  arXiv  Detail & Related papers  (2024-11-26T15:55:15Z)
• Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI [52.138044013005]
  generative AI, particularly large language models (LLMs), become increasingly integrated into production applications. New attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems. Red-teaming has gained importance in proactively identifying weaknesses in these systems, while blue-teaming works to protect against such adversarial attacks. This work aims to bridge the gap between academic insights and practical security measures for the protection of generative AI systems.
  arXiv  Detail & Related papers  (2024-09-23T10:18:10Z)
• Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? [59.96471873997733]
  We propose an empirical foundation for developing more meaningful safety metrics and define AI safety in a machine learning research context.<n>We aim to provide a more rigorous framework for AI safety research, advancing the science of safety evaluations and clarifying the path towards measurable progress.
  arXiv  Detail & Related papers  (2024-07-31T17:59:24Z)
• Artificial Intelligence as the New Hacker: Developing Agents for Offensive Security [0.0]
  This paper explores the integration of Artificial Intelligence (AI) into offensive cybersecurity. It develops an autonomous AI agent, ReaperAI, designed to simulate and execute cyberattacks. ReaperAI demonstrates the potential to identify, exploit, and analyze security vulnerabilities autonomously.
  arXiv  Detail & Related papers  (2024-05-09T18:15:12Z)
• Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness [53.91018508439669]
  The study explores the complexities of integrating Artificial Intelligence into Autonomous Vehicles (AVs) It examines the challenges introduced by AI components and the impact on testing procedures. The paper identifies significant challenges and suggests future directions for research and development of AI in AV technology.
  arXiv  Detail & Related papers  (2024-02-21T08:29:42Z)
• A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research [23.273934717819795]
  This paper presents a systematic literature review of approaches that aim to improve the explainability of AI models within the context of Software Engineering.<n>We aim to summarize the SE tasks where XAI techniques have shown success to date; (2) classify and analyze different XAI techniques; and (3) investigate existing evaluation approaches.
  arXiv  Detail & Related papers  (2024-01-26T03:20:40Z)
• Deepfakes, Misinformation, and Disinformation in the Era of Frontier AI, Generative AI, and Large AI Models [7.835719708227145]
  Deepfakes and the spread of m/disinformation have emerged as formidable threats to the integrity of information ecosystems worldwide. We highlight the mechanisms through which generative AI based on large models (LM-based GenAI) craft seemingly convincing yet fabricated contents. We introduce an integrated framework that combines advanced detection algorithms, cross-platform collaboration, and policy-driven initiatives.
  arXiv  Detail & Related papers  (2023-11-29T06:47:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.