Fetching the paper…

Reading the bibliography…

2024

GPT in Sheep's Clothing: The Risk of Customized GPTs

Antebi, Sagiv, Azulay, Noam, Habler, Edan et al.

Original
PDF
Post on X

Understand

In November 2023, OpenAI introduced a new service allowing users to create custom versions of ChatGPT (GPTs) by using specific instructions and knowledge to guide the model's behavior.

We aim to raise awareness of the fact that GPTs can be used maliciously, posing privacy and security risks to their users.

GPT in Sheep's Clothing: The Risk of Customized GPTs · Around

Built on

“Typosquatting and combosquatting attacks on the python ecosystem”
Duc-Ly Vu et al · 2020
Earlier work this paper cites.
“Defending against alignment-breaking attacks via robustly aligned llm”
Original
Bochuan Cao, Yuanpu Cao, Lu Lin and Jinghui Chen · 2023
Earlier work this paper cites.
“A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt”
Original
Yihan Cao et al · 2023
Earlier work this paper cites.
“Investigating the Impact of User Trust on the Adoption and Use of ChatGPT: Survey Analysis”
Avishek Choudhury and Hamid Shamszare · 2023
Earlier work this paper cites.
“Prompt engineering for ChatGPT: A quick guide to techniques, tips, and best practices”
Sabit Ekin · 2023
Earlier work this paper cites.

Similar

“GenAI against humanity: Nefarious applications of generative artificial intelligence and large language models”
Original
Emilio Ferrara · 2023
Cited alongside, same era.
“From chatgpt to threatgpt: Impact of generative ai in cybersecurity and privacy”
Maanak Gupta et al · 2023
Cited alongside, same era.
“Llm self defense: By self examination, llms know they are being tricked”
Original
Alec Helbling, Mansi Phute, Matthew Hull and Duen Chau · 2023
Cited alongside, same era.
“Exploring ChatGPT Capabilities and Limitations: A Survey”
Anis Koubaa et al · 2023
Cited alongside, same era.

Then

“Public Perception of Generative AI on Twitter: An Empirical Study Based on Occupation and Usage”
Original
Kunihiro Miyazaki et al · 2023
Later among the works it cites.
“Self-Guard: Empower the LLM to Safeguard Itself”
Original
Zezhong Wang et al · 2023
Later among the works it cites.
“A prompt pattern catalog to enhance prompt engineering with chatgpt”
Original
Jules White et al · 2023
Later among the works it cites.
“Large Language Model (LLM) Market Size to Grow USD 40.8 Billion By 2029 at a CAGR of 21.4% – Valuates Reports” Accessed: December 2023, 2023
PR Newswire · 2029
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…