Evaluation empirique de la sécurisation et de l'alignement de ChatGPT et Gemini: analyse comparative des vulnérabilités par expérimentations de jailbreaks
Rafaël Nouailles
Abstract
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.
Related Papers
Making Language Model a Hierarchical Classifier and Generator2025-07-17SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks2025-07-17Leveraging Pre-Trained Visual Models for AI-Generated Video Detection2025-07-17Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management2025-07-17From Roots to Rewards: Dynamic Tree Reasoning with RL2025-07-17HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals2025-07-17A Survey of Context Engineering for Large Language Models2025-07-17MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval2025-07-17