Introduction to Lakera Guard

Lakera Guard delivers real-time visibility and control to block threats and govern agents. Our AI-first approach provides the industry’s most accurate AI threat detection while maximizing agent performance. Leading enterprises and fast-growth SaaS companies use Lakera to secure all of their GenAI applications.

Key Features

Through Lakera Guard you can get:

Real Time Visibility

• Confirm agents behave as intended by monitoring user inputs and model outputs
• Flag malicious actors before they become real threats
• Deploy globally with multi-language and multi-modality support

Threat Detection

• Stay secure with the industry’s most up-to-date threat intelligence, updated daily with Lakera threat research, including insights from 100K Gandalf attacks per day
• Block prompt attacks, data leakage, and inappropriate interactions with precision to optimize user experience
• Meet compliance requirements with activity logs, including blocked threats and inappropriate behavior

Centralized Control

• Get started in 5 minutes with a single API call and out-of-the-box policies you can customize
• Maintain policy consistency across applications without code changes
• Optimize user experience with ultra low latency controls and few false positives

Defenses

Lakera Guard will screen LLM interactions and flag for mitigating action if the following threats are detected:

• Prompt attacks - detect prompt injections, jailbreaks or manipulation in user prompts or reference materials to stop LLM behavior being overridden
• Data Leakage - prevent leakage of sensitive information and Personally Identifiable Information (PII) in user prompts or LLM outputs
• Content violations - detect offensive, hateful, sexual, violent and vulgar content in user prompts or LLM outputs
• Malicious links - detect links that are not from an allowed list of domains to prevent phishing and malicious links being shown to users
• Custom threats - create custom controls to apply your own security policies

You can control and customize the defenses applied to your application or use case by setting policies within Guard.

How it works

Lakera Guard is built on top of our continuously evolving security intelligence platform and is designed to form a protective firewall around your generative AI applications, securing LLM interactions in real time.

Integrating with Lakera Guard is straightforward and can be done in minutes:

1. Simply set up a project for each application or system you need to secure.
2. For each project, choose a policy from our catalog or create a custom policy to enforce your bespoke security requirements.
3. Then have your AI gateway or GenAI application(s) make an API request to the Lakera Guard API for each user interaction or agent step, passing the user and external inputs plus the LLM output to Guard.
4. Flexibly choose how your applications respond if guard flags a threat, for example blocking the interaction or logging for investigation.

Guard will now continuously screen for attacks, unwanted AI behavior, and data leakage according to your policies, protecting your GenAI applications in real-time and providing visibility of threats and vulnerabilities.

Once integrated, you can configure and customize Lakera Guard to control application and use-case specific defenses across your organization. Gain centralized oversight and rapidly respond to threats and suspicious users through in-built monitoring, or connect up your own security monitoring setup.

Continuously evolving threat intelligence

Our security intelligence platform combines insights from public sources, data from the LLM developer community, our Lakera Red Team, and the latest LLM security research and techniques.

Our proprietary threat database contains tens of millions of attack data points, and is growing by roughly 100,000 entries per day, so you can gain zero-day protections and stay ahead of constantly arising new threats.

Coverage

Model compatibility

Lakera Guard is completely model-agnostic and works with:

• Any hosted model provider (OpenAI, Anthropic, Cohere, etc.)
• Any open-source model
• Your own custom or fine-tuned models

Language

Lakera detects threats in 100+ languages, including all major global languages, including:

• Major European languages (English, French, German, Spanish, Italian, etc.)
• Asian languages (Chinese, Japanese, Korean, Vietnamese, Thai, etc.)
• Indian languages (Hindi, Bengali, Tamil, etc.)
• Arabic and other Semitic languages
• Russian and other Slavic languages
• African languages (Swahili, Yoruba, etc.)

Modalities

Lakera Guard screens for threats in text, including structured text as well as natural language.

Defense against multi-modal threats in audio and images is coming soon. Please reach out if you want to join our early access betas.

Deployment options

Lakera Guard is available as an enterprise grade Software as a Service (SaaS) cloud-hosted solution or Self-hosted product.

Get started for free in minutes

You can start protecting your LLM applications in minutes by signing up for a free account and following our Quickstart guide.

Learn more

• Understand the AI threats that GenAI applications face and how Lakera defenses secure against them
• Learn more about working with the Lakera Guard API
• Learn more about how to use the Lakera platform to monitor and analyze interactions and threats, as well as customize and configure guard