In this episode, we talk about ten very important security architecture patterns to protect LLM applications.
Open source guardrails software mentioned during the episode:
<ul>
 <li><a href="https://trustyai-explainability.github.io/trustyai-site/main/main.html" target="_blank" rel="ugc noopener noreferrer">TrustyAI</a></li>
 <li><a href="https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/" target="_blank" rel="ugc noopener noreferrer">Llama Guard</a></li>
 <li><a href="https://github.com/NVIDIA/NeMo-Guardrails" target="_blank" rel="ugc noopener noreferrer">Nemo Guardrails</a></li>
</ul>
Open source model evaluation frameworks mentioned:
<ul>
 <li><a href="https://github.com/EleutherAI/lm-evaluation-harness" target="_blank" rel="ugc noopener noreferrer">lm-evaluation-harness</a></li>
 <li><a href="https://github.com/aiverify-foundation/moonshot" target="_blank" rel="ugc noopener noreferrer">Project Moonshot</a></li>
 <li><a href="https://github.com/Giskard-AI/giskard" target="_blank" rel="ugc noopener noreferrer">Giskard</a></li>
</ul>

In this episode, we talk about ten very important security architecture patterns to protect LLM applications. Open source guardrails software mentioned during the episode: TrustyAI Llama Guard Nemo Guardrails Open source model evaluation frameworks mentioned: lm-evaluation-harness Project Moonshot Giskard

In this episode, we talk about ten very important security architecture patterns to protect LLM applications.
Open source guardrails software mentioned during the episode:
<ul>
 <li><a href="https://trustyai-explainability.github.io/trustyai-site/main/main.html" rel="noopener noreferrer">TrustyAI</a></li>
 <li><a href="https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/" rel="noopener noreferrer">Llama Guard</a></li>
 <li><a href="https://github.com/NVIDIA/NeMo-Guardrails" rel="noopener noreferrer">Nemo Guardrails</a></li>
</ul>
Open source model evaluation frameworks mentioned:
<ul>
 <li><a href="https://github.com/EleutherAI/lm-evaluation-harness" rel="noopener noreferrer">lm-evaluation-harness</a></li>
 <li><a href="https://github.com/aiverify-foundation/moonshot" rel="noopener noreferrer">Project Moonshot</a></li>
 <li><a href="https://github.com/Giskard-AI/giskard" rel="noopener noreferrer">Giskard</a></li>
</ul>

Top 10 Security Architecture Patterns for LLM applications

Join Florencio Cano Gabarda in Mind the Machine, where we dive into the critical intersection of AI security and safety. Explore how to protect AI systems from cyber threats, use AI to enhance IT security, and tackle the ethical challenges of AI safety—covering issues like ethics, bias, and trustworthiness. Tune in to navigate the complexities of building secure and safe AI.

Share Top 10 Security Architecture Patterns for LLM applications

Sign up to save your podcasts

Top 10 Security Architecture Patterns for LLM applications

Top 10 Security Architecture Patterns for LLM applications