Copertina

Evaluation empirique de la sécurisation et de l'alignement de ChatGPT et Gemini: analyse comparative des vulnérabilités par expérimentations de jailbreaks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Nouailles, Rafaël
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Comparative Analysis Based on DeepSeek, ChatGPT, and Google Gemini: Features, Techniques, Performance, Future Prospects
di: Rahman, Anichur, et al.
Pubblicazione: (2025)

AuditGPT: Auditing Smart Contracts with ChatGPT
di: Xia, Shihao, et al.
Pubblicazione: (2024)

Exploring ChatGPT's Capabilities on Vulnerability Management
di: Liu, Peiyu, et al.
Pubblicazione: (2023)

Exfiltration of personal information from ChatGPT via prompt injection
di: Schwartzman, Gregory
Pubblicazione: (2024)

LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins
di: Iqbal, Umar, et al.
Pubblicazione: (2023)

On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing
di: Liu, Zeyan, et al.
Pubblicazione: (2023)

From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude
di: Roy, Sayak Saha, et al.
Pubblicazione: (2023)

ChatGPT's Potential in Cryptography Misuse Detection: A Comparative Analysis with Static Analysis Tools
di: Firouzi, Ehsan, et al.
Pubblicazione: (2024)

Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments
di: Mukherjee, Kunal, et al.
Pubblicazione: (2026)

Detecting Phishing Sites Using ChatGPT
di: Koide, Takashi, et al.
Pubblicazione: (2023)

How Secure is Code Generated by ChatGPT?
di: Khoury, Raphaël, et al.
Pubblicazione: (2023)

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
di: Yi, Xin, et al.
Pubblicazione: (2025)

Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics
di: Jia, Shan, et al.
Pubblicazione: (2024)

Security Analysis of ChatGPT: Threats and Privacy Risks
di: Xiang, Yushan, et al.
Pubblicazione: (2025)

Digital Forensic Investigation of the ChatGPT Windows Application
di: Kankanamge, Malithi Wanniarachchi, et al.
Pubblicazione: (2025)

Recursive language models for jailbreak detection: a procedural defense for tool-augmented agents
di: Shavit, Doron
Pubblicazione: (2026)

A Qualitative Study on Using ChatGPT for Software Security: Perception vs. Practicality
di: Kholoosi, M. Mehdi, et al.
Pubblicazione: (2024)

EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection
di: Liu, Shigang, et al.
Pubblicazione: (2024)

Evaluation of ChatGPT's Smart Contract Auditing Capabilities Based on Chain of Thought
di: Du, Yuying, et al.
Pubblicazione: (2024)

Are aligned neural networks adversarially aligned?
di: Carlini, Nicholas, et al.
Pubblicazione: (2023)

Exploring Backdoor Vulnerabilities of Chat Models
di: Hao, Yunzhuo, et al.
Pubblicazione: (2024)

Time to Separate from StackOverflow and Match with ChatGPT for Encryption
di: Firouzi, Ehsan, et al.
Pubblicazione: (2024)

Can ChatGPT Perform Image Splicing Detection? A Preliminary Study
di: Nath, Souradip
Pubblicazione: (2025)

Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers
di: Hamer, Sivana, et al.
Pubblicazione: (2024)

ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected
di: Gharami, Kanchon, et al.
Pubblicazione: (2025)

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
di: Wang, Boxin, et al.
Pubblicazione: (2023)

Confused ChatGPT: Cross-App Context Poisoning via First-Party APIs
di: Wang, Chao, et al.
Pubblicazione: (2026)

WildCode: An Empirical Analysis of Code Generated by ChatGPT
di: Khanmohammadi, Kobra, et al.
Pubblicazione: (2025)

GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation
di: Ramesh, Govind, et al.
Pubblicazione: (2024)

ChatGPT, is this real? The influence of generative AI on writing style in top-tier cybersecurity papers
di: Vansteenhuyse, Daan
Pubblicazione: (2026)

AbuseGPT: Abuse of Generative AI ChatBots to Create Smishing Campaigns
di: Shibli, Ashfak Md, et al.
Pubblicazione: (2024)

Enhancing Android Malware Detection: The Influence of ChatGPT on Decision-centric Task
di: Li, Yao, et al.
Pubblicazione: (2024)

ChatGPT and Other Large Language Models for Cybersecurity of Smart Grid Applications
di: Zaboli, Aydin, et al.
Pubblicazione: (2023)

From static to adaptive: immune memory-based jailbreak detection for large language models
di: Leng, Jun, et al.
Pubblicazione: (2025)

Low-Resource Languages Jailbreak GPT-4
di: Yong, Zheng-Xin, et al.
Pubblicazione: (2023)

Using Hallucinations to Bypass GPT4's Filter
di: Lemkin, Benjamin
Pubblicazione: (2024)

Generative AI like ChatGPT in Blockchain Federated Learning: use cases, opportunities and future
di: Puppala, Sai, et al.
Pubblicazione: (2024)

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection
di: Chang, Xiangyu, et al.
Pubblicazione: (2025)

AVISE: Framework for Evaluating the Security of AI Systems
di: Lempinen, Mikko, et al.
Pubblicazione: (2026)

TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations
di: Chen, Xiuyuan, et al.
Pubblicazione: (2025)