Fotie M. Constantblog.fotiecodes.com·Sep 30, 2024How I Hacked Large Language Models(LLMs) Using Prompt Injection (And It Worked)I recently embarked on an exciting research journey to explore the vulnerabilities of large language models (LLMs) like ChatGPT, Anthropic Gemini, and similar models. My goal was to see how hackers could exploit them through prompt injection attacks....Discuss·68 readsllm
jamarirjamarir.hashnode.dev·Sep 12, 2024[CTF] LAKERA - GandalfGandalf prompt injection https://gandalf.lakera.ai/ Your goal is to make Gandalf reveal the secret password for each level. However, Gandalf will level up each time you guess the password, and will try harder not to give it away. Can you beat leve...Discuss·27 readsCTFinfosec
Anshul Tiwaricsanshul.hashnode.dev·Sep 9, 2024Prompt Injection: A Simple ExplanationThis is security vulnerability that targets AI and machine learning system.Here malicious prompt manipulates model's behavior.Its aims to get sensitive information or executing unauthorized instructions. Types of Prompt Injections: Direct Prompt Inj...Discusspromptinjections
Harsh Agarwalharshagarwal29.hashnode.dev·Aug 21, 2024A Beginner's Guide to LLMs: Insights from Andrej Karpathy's TutorialLLMs are currently all the rage in the market. No matter which company you check, you will find that it is developing some kind of AI feature or integration. As such, having a basic grasp on LLM is a necessary skill for software developers. This arti...Discuss·10 likes·135 readsllm-jailbreak
Wilame Limawilame.hashnode.dev·Aug 16, 2024Defending AI: Understanding and Mitigating Prompt Injection AttacksPrompt injection is a type of cybersecurity threat that is becoming increasingly relevant as more industries start using Large Language Models (LLMs) like GPT-3, GPT-4, and others. Essentially, attackers can manipulate AI systems by feeding them care...DiscussAI
Jalel TOUNSIsecondbrain.hashnode.dev·Apr 8, 2024Understanding AI Dynamics: the difference between Prompt Injection and JailbreakingIn the realm of digital creativity, two powerful concepts are reshaping the way we approach innovation: Prompt Injection and Jailbreaking. Let's dive into their essence, with examples that highlight their impact on creativity and problem-solving. Pro...Discuss·10 likes2Articles1Week
Patrick Peng0reg.dev·Feb 21, 2024Injecting customgpt.ai demo: How to jailbreak a strictly prompt-engineered GPT-4 in wild?Starting point Recently a really cool LLM Application really catched my eyes, called https://customgpt.ai/： CustomGPT seemed like a commerical GPT-4 Chatbot allowed user interaction to custom services! seemed like a really innovating application. I...DiscussGPT 4
Gunjan Mehtagunjanmehta01.hashnode.dev·Dec 2, 2023Day 1 of Advent of Cyber 2023!Introduction: Advent of Cyber is basically 25 days of challenge in which the participant will get a task to do on daily basis and the deadline to complete the task is till 25th December. Every task has its own new story related to the Christmas and d...Discussadvent of cyber
Arcturusarcturus.hashnode.dev·Dec 2, 2023TryHackMe | Advent of Cyber 2023 | Day 1Day 1 Machine Learning - Chatbot, tell me, if you're really safe? Welcome to Day 1 of the Advent of Cyber 2023. You must have already read the backstory, and if you haven't, read the exciting story and get to know the puzzle we will be solving this ...Discuss·77 readsAdventOfCyber2023
![[CTF] LAKERA - Gandalf](https://cdn.hashnode.com/res/hashnode/image/upload/v1726175250067/7349e48b-8d2d-4809-9147-a74d76937a6d.jpeg?w=1600&h=840&fit=crop&crop=entropy&auto=compress,format&format=webp)
