Avoiding Dirty RAGs: Retrieval-Augmented Generation with Ollama and LangChain
RAG connects pre-trained LLMs with current data sources. Moreover, a RAG system can use many data sources.
RAG connects pre-trained LLMs with current data sources. Moreover, a RAG system can use many data sources.
Many people have heard of ChatGPT, Gemini, Bart, Claude, Llama, or other artificial intelligence (AI) assistants at this point. These are all implementations of what are known as large language […]
Brian Fehrman // Many of you have likely heard of Domain Fronting. Domain Fronting is a technique that can allow your C2 traffic to blend in with a target’s traffic […]
Brian Fehrman// Microsoft Lync servers have been a staple of my external engagements for the past six months or so. I have found a Lync server on all of those […]
Brian Fehrman // In a previous post, titled PowerShell without PowerShell, we showed you how you can bypass Application Whitelisting Software (AWS), PowerShell restrictions/monitoring, and Command Prompt restrictions. In some […]
Brian Fehrman // Privilege escalation is a common goal for threat actors after they have compromised a system. Having elevated permissions can allow for tasks such as: extracting local password-hashes, […]
Derek Banks, Beau Bullock, & Brian Fehrman // Our clients often ask how they could have detected and prevented the post-exploitation activities we used in their environment to gain elevated […]
Brian Fehrman // Running into environments where the use of PowerShell is being monitored or is just flat-out disabled? Have you tried out the fantastic PowerOps framework but are wishing […]
Brian Fehrman // You’ve sent your phishing ruse, the target has run the Meterpreter payload, and you have shell on their system. Now what? If you follow our blogs, you […]