InAIM IntelligencebySejin·Nov 25, 2024The Hidden Threat: Understanding Indirect Prompt Injection in LLMsLarge Language Models (LLMs) are revolutionizing the way we live and work, seamlessly integrating into tasks like information search…
InAIM IntelligencebySejin·Nov 9, 2024Defending Web Agents: Advanced Security Strategies through AdvWeb and BrowserARTThe advancement of web agents, alongside the development of large language models (LLMs) and vision language models (VLMs), plays a crucial…
InAIM IntelligencebySejin·Oct 21, 2024Robust LLM Defenses: Exploring Prompt Perturbation TechniquesAs AI advances to process both text and images simultaneously through multi-modal models, ensuring the safety of these systems has become…
InAIM IntelligencebySejin·Oct 11, 2024Ensuring Safety in Large Language Models: Approaches and ChallengesHello, my name is Sejin Lee, an intern at AIM Intelligence.