Evaluation empirique de la s'ecurisation et de l'alignement de ChatGPT et Gemini: analyse comparative des vuln'erabilit'es par exp'erimentations de jailbreaks
On the map: LLM safety and security → Jailbreaking
Abstract (arXiv)
Large Language models (LLMs) are transforming digital usage, particularly in text generation, image creation, information retrieval and code development. ChatGPT, launched by OpenAI in November 2022, quickly became a reference, prompting the emergence of competitors such as Google's Gemini. However, these technological advances raise new cybersecurity challenges, including prompt injection attacks, the circumvention of regulatory measures (jailbreaking), the spread of misinformation (hallucinations) and risks associated with deep fakes. This paper presents a comparative analysis of the security and alignment levels of ChatGPT and Gemini, as well as a taxonomy of jailbreak techniques associated with experiments.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. First posted on arXiv 10 Jun 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Comprehensive Evaluation of ChatGPT Reliability Through Multilingual Inquiries
- 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
- 2025Evaluating Adversarial Vulnerabilities in Modern Large Language Models
- 2024All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
- 2025Jailbreaking Generative AI: Empowering Novices to Conduct Phishing Attacks
- 2024A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
- 2025Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
- 2023Multi-step Jailbreaking Privacy Attacks on ChatGPT