ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
Abstract
Safety is critical to the usage of large language models (LLMs)
Security
Security is the practice of safeguarding computer systems, networks, and data from various threats and risks. It involves implementing measures and protocols to protect against unauthorized access, data breaches, cyberattacks, and other vulnerabilities. Its primary goal is to ensure the confidentiality, integrity, and availability of information and resources, reducing the potential for harm or unauthorized disruption.
Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation
Abstract
Despite efforts to align large language models to produce harmless responses,
Host your own VPN with WireGuard
You might have already heard of Virtual Private Networks or short VPNs.
LLM Hacking with Gandalf
Since ChatGPT was published in 2022 many organisations use Large Language Models