Cisco AI Defense
Cisco AI Defense is a comprehensive security solution designed to enable enterprises to safely develop, deploy, and utilize AI applications. It addresses critical security challenges such as shadow AI—unauthorized use of third-party generative AI apps—and application security by providing full visibility into AI assets and enforcing controls to prevent data leakage and mitigate threats. Key components include AI Access, which offers control over third-party AI applications; AI Model and Application Validation, which conducts automated vulnerability assessments; AI Runtime Protection, which implements real-time guardrails against adversarial attacks; and AI Cloud Visibility, which inventories AI models and data sources across distributed environments. Leveraging Cisco's network-layer visibility and continuous threat intelligence updates, AI Defense ensures robust protection against evolving AI-related risks.
Learn more
Alice
Alice (formerly ActiveFence) is a security, safety, and trust platform built to protect AI systems and online platforms in the GenAI era. Powered by the world’s largest adversarial intelligence dataset, Alice safeguards over 3 billion users across more than 120 languages. Its Rabbit Hole intelligence engine continuously analyzes billions of toxic and manipulative data samples to detect emerging threats in real time. The WonderSuite platform includes tools like WonderBuild for pre-launch stress testing, WonderFence for runtime guardrails, and WonderCheck for automated red-teaming. By defending against prompt injection, jailbreaks, governance gaps, and harmful AI behavior, Alice enables enterprises and foundation model labs to innovate with confidence.
Learn more
CyCraft XecGuard
XecGuard is CyCraft’s LLM Firewall for trustworthy, agentic AI, designed to protect enterprise AI systems from prompt injection, jailbreak, prompt extraction, data leakage, unsafe outputs, and agentic workflow risks. Built on CyCraft’s red teaming and blue teaming experience across government, finance, and high-tech manufacturing, XecGuard goes beyond model-level defenses by combining AI guardrails, cybersecurity controls, compliance protection, and risk response strategies for real-world enterprise AI adoption. It is positioned as a plug-and-play LoRA security module that can strengthen LLM defenses without requiring changes to the underlying model architecture, helping teams add protection quickly while preserving performance. XecGuard is built on proprietary security datasets and multi-stage fine-tuning techniques, enabling LLMs to better resist adversarial prompts, malicious manipulation, and attempts to extract protected instructions or sensitive information.
Learn more
LLM Guard
By offering sanitization, detection of harmful language, prevention of data leakage, and resistance against prompt injection attacks, LLM Guard ensures that your interactions with LLMs remain safe and secure. LLM Guard is designed for easy integration and deployment in production environments. While it's ready to use out-of-the-box, please be informed that we're constantly improving and updating the repository. Base functionality requires a limited number of libraries, as you explore more advanced features, necessary libraries will be automatically installed. We are committed to a transparent development process and highly appreciate any contributions. Whether you are helping us fix bugs, propose new features, improve our documentation, or spread the word, we would love to have you as part of our community.
Learn more