paper-with-me

Papers

RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Words

2024-06-11 · Alessio Buscemi, Daniele Proverbio

The ethical implications and potentials for misuse of Generative Artificial Intelligence are increasingly worrying topics. This paper explores how easily the default ethical guardrails of ChatGPT, using its latest customization features, can be bypassed by simple prompts and fine-tuning, that can be effortlessly accessed by the broad public. This malevolently altered version of ChatGPT, nicknamed "RogueGPT", responded with worrying behaviours, beyond those triggered by jailbreak prompts. We conduct an empirical study of RogueGPT responses, assessing its flexibility in answering questions pertaining to what should be disallowed usage. Our findings raise significant concerns about the model's knowledge about topics like illegal drug production, torture methods and terrorism. The ease of driving ChatGPT astray, coupled with its global accessibility, highlights severe issues regarding the data quality used for training the foundational model and the implementation of ethical safeguards. We thus underline the responsibilities and dangers of user-driven modifications, and the broader effects that these may have on the design of safeguarding and ethical modules implemented by AI programmers.

📄 PDF Abstract BibTeX arXiv:2407.15009

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Unveiling Security, Privacy, and Ethical Concerns of ChatGPT

2023-07-26 · Xiaodong Wu, Ran Duan, Jianbing Ni

This paper delves into the realm of ChatGPT, an AI-powered chatbot that utilizes topic modeling and reinforcement learning to generate natural responses. Although ChatGPT holds immense promise across various industries, …

ChatbotEthics

AI Ethics and Social Norms: Exploring ChatGPT's Capabilities From What to How

2025-04-25 · Omid Veisi, Sasan Bahrami, Roman Englert, Claudia Müller

Using LLMs in healthcare, Computer-Supported Cooperative Work, and Social Computing requires the examination of ethical and social norms to ensure safe incorporation into human life. We conducted a mixed-method study, in…

Ethics

Ethical ChatGPT: Concerns, Challenges, and Commandments

2023-05-18 · Jianlong Zhou, Heimo Müller, Andreas Holzinger, Fang Chen

Large language models, e.g. ChatGPT are currently contributing enormously to make artificial intelligence even more popular, especially among the general population. However, such chatbot models were developed as tools t…

Chatbot

All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks

2024-01-18 · Kazuhiro Takemoto

Large Language Models (LLMs), such as ChatGPT, encounter `jailbreak' challenges, wherein safeguards are circumvented to generate ethically harmful prompts. This study introduces a straightforward black-box method for eff…

All

Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity

2023-01-30 · Terry Yue Zhuo, Yujin Huang, Chunyang Chen, Zhenchang Xing

Recent breakthroughs in natural language processing (NLP) have permitted the synthesis and comprehension of coherent text in an open-ended way, therefore translating the theoretical algorithms into practical applications…

EthicsLanguage ModellingRed Teaming