Cisco is proud to mark a significant milestone in its AI journey. Our newly launched Basis AI group—fashioned to carry world-class, domain-specific AI infrastructure to the cybersecurity area—is proud to introduce its first launch: Llama-3.1-FoundationAI-SecurityLLM-base-8B (Basis-sec-8b), an 8-billion parameter, open-weight Giant Language Mannequin (LLM) purpose-built for safety.
This mannequin combines deep area experience with the pliability and management wanted for safe, real-world deployment. With Basis-sec-8B, groups can construct, fine-tune, and deploy AI-native workflows throughout the safety lifecycle. This mannequin is designed to assist safety groups suppose sooner, act with precision, and scale operations with out compromise.
Cybersecurity Functions Require Objective-Constructed, open, Small Fashions
Safety groups right this moment face unprecedented strain. Threats are rising sooner, assaults are extra advanced, and conventional instruments aren’t sufficient. AI is rising as a important pressure multiplier—however general-purpose fashions usually fall quick for real-world safety workflows.
Prompting and retrieval pipelines can’t meet the precision, consistency, and high quality calls for of safety operations. Nice-tuning closed fashions brings its personal challenges: excessive prices, restricted management, and deployment limitations—particularly the place information privateness, regulatory compliance, and in-environment internet hosting are non-negotiable. In the meantime, most open fashions lack the domain-specific information safety groups want.
“Basis-sec-8b is a foundational step towards constructing AI-native safety methods—instruments that don’t simply course of information however really perceive the safety area. This mannequin offers safety groups all over the place a robust constructing block to speed up protection, scale back fatigue, and acquire readability in advanced risk environments.”
Jeetu Patel, Chief Product Officer, Cisco
A Objective-Constructed Mannequin for Safety
Basis-sec-8b isn’t a general-purpose mannequin retrofitted for safety. It was designed from the bottom as much as perceive the language, logic, and workflows of cybersecurity.
Constructed with Llama, utilizing the Llama 3.1 8B framework, foundation-sec-8b has been pre-trained on a dataset meticulously constructed in-house by Cisco Basis AI. This dataset was curated particularly to seize the real-world information and context that safety professionals work with every single day. It consists of, however is just not restricted to:
- Vulnerability databases and risk conduct mappings (e.g., CVEs, CWEs, MITRE ATT&CK)
- Menace intelligence reviews, crimson crew playbooks, and real-world incident summaries
- Safety tooling documentation throughout cloud, identification, and infrastructure domains
- Compliance references and safe growth practices (e.g., NIST, OWASP, safe coding guides)
This area alignment makes foundation-sec-8b instantly efficient throughout analyst workflows—delivering deeper insights, fewer hallucinations, and dramatically decrease response occasions in comparison with generalist fashions.
Efficiency That Punches Above Its Weight
Regardless of its 8B parameter measurement, foundation-sec-8b outcomes are comparable with fashions practically 10x bigger. On core cybersecurity benchmarks, it outperforms Llama 3.1 8B and even matches or exceeds Llama 3.1 70B, providing highly effective inference at a fraction of the associated fee and infrastructure burden.
| Benchmark | Mannequin Basis-sec-8b |
Mannequin Llama-3.1-8b |
Mannequin Llama-3.1 70B |
|---|---|---|---|
| CTI-MCQA | 67.39 | 64.14 | 68.23 |
| CTI-RCM | 75.26 | 66.43 | 72.66 |
Importantly, foundation-sec-8b maintains sturdy normal language efficiency, staying on par with Llama fashions on MMLU benchmarks. This implies it could possibly fluidly clarify risk conduct, assist long-form investigation narratives, and reply naturally in chat-based workflows—with out compromising its safety focus.
Its benefits develop much more obvious with fine-tuning. In downstream safety duties—equivalent to extracting MITRE ATT&CK strategies from unstructured risk reviews—a fine-tuned foundation-sec-8b mannequin considerably outperformed fine-tuning the same-sized Llama mannequin. This reinforces the worth of foundation-sec-8b as each a foundational mannequin and a high-impact part for embedded safety workflows.
Sensible Functions—and Constructed to Match Your Surroundings
Basis-sec-8b isn’t simply performant—it’s versatile. Being open-weight and constructed on the Llama framework makes it simple to fine-tune or lengthen with your personal telemetry, detection guidelines, or risk intel. Whether or not you’re embedding it into present instruments or constructing fully new workflows, foundation-sec-8b adapts to your group’s distinctive wants.
Safety groups can apply foundation-sec-8b throughout the safety lifecycle:
- SOC acceleration – Automate alert triage, summarize incidents, and help with investigations
- Proactive risk protection – Simulate assaults, prioritize vulnerabilities, and mannequin threats tailor-made to your infrastructure
- Engineering enablement – Ship AI-assisted code evaluations, validate configurations, and assess compliance proof with context out of your surroundings
- Customized integration – Nice-tune the mannequin to mirror your safety posture, language, and detection methods—guaranteeing precision in real-world deployments
“We’ve been working with the Cisco Basis AI crew exploring learn how to embed foundation-sec-8b throughout Cisco’s inside safety stack. We’re very excited in regards to the capabilities of an AI mannequin that really understands our area and might scale throughout use instances.”
Omar Santos, Distinguished Engineer, Cisco Safety & Belief Group (S&TO)
From powering agentic assistant workflows to helping builders in writing secure-by-default code, foundation-sec-8b is a basis you’ll be able to construct on.
Publicly Accessible, With Privateness and Management in Thoughts
In cybersecurity, belief is non-negotiable. That’s why foundation-sec-8b is open-weight, with weights and tokenizer launched beneath a permissive license.
This offers organizations:
- Full management over deployment – Run the mannequin on-prem, in air-gapped environments, or inside safe cloud enclaves
- Compliance confidence – Hold delicate information native; no compelled inference APIs or third-party sharing
- Customization freedom – Adapt and lengthen the mannequin structure or coaching pipeline to satisfy distinctive safety and privateness wants
Basis-sec-8b is now out there for obtain on Hugging Face.
It’s also possible to learn the complete technical particulars in our analysis paper.
Within the close to future, we additionally plan to open supply the coaching pipeline used to construct the mannequin. For extra on the info building and coaching course of, confer with the analysis paper.
Simply the Starting
Basis-sec-8b is the first launch from Cisco Basis AI, a devoted group constructing the infrastructure that may drive the subsequent decade of cybersecurity innovation. This mannequin lays the groundwork for a future the place AI isn’t only a bolt-on function—however a foundational functionality embedded throughout the whole safety lifecycle.
And we’re simply getting began.
Over the approaching months, Cisco Basis AI will probably be releasing:
- A cybersecurity reasoning mannequin that brings explainability and deeper evaluation to advanced safety workflows
- A brand new benchmark suite designed to guage AI fashions on real-world, practitioner-defined safety duties
- Extra instruments and parts that assist groups fine-tune, operationalize, and embed AI safely and successfully into their safety stacks
Basis-sec-8b opens the door. What comes subsequent will reshape how defenders construct, reply, and lead with AI.
Basis-sec-8b is stay. It’s open. And it’s able to defend.
Discover the mannequin, be a part of the neighborhood, and assist form the subsequent era of AI-powered cybersecurity.
We’d love to listen to what you suppose. Ask a Query, Remark Beneath, and Keep Related with Cisco Safety on social!
Cisco Safety Social Handles
Share:
