Defend your AI programs with Immediate Shields—a unified API that analyzes inputs to your LLM-based resolution to protect in opposition to direct and oblique threats.
A robust protection in opposition to immediate injection assaults
The AI safety panorama is consistently altering, with immediate injection assaults rising as one of the important threats to generative AI app builders at this time. This happens when an adversary manipulates an LLM’s enter to vary its conduct or entry unauthorized data. In keeping with the Open Worldwide Software Safety Undertaking (OWASP), immediate injection is the highest risk dealing with LLMs at this time1. Assist defend your AI programs in opposition to this rising risk with Azure AI Content material Security, that includes Immediate Shields—a unified API that analyzes inputs to your LLM-based resolution to protect in opposition to direct and oblique threats. These exploits can embody circumventing current security measures, exfiltrating delicate information, or getting AI programs to take unintended actions inside your atmosphere.
Immediate injection assaults
In a immediate injection assault, malicious actors enter misleading prompts to impress unintended or dangerous responses from AI fashions. These assaults might be categorized into two predominant classes—direct and oblique immediate injection assaults.
- Direct immediate injection assaults, together with jailbreak makes an attempt, happen when an finish consumer inputs a malicious immediate designed to bypass safety layers and extract delicate data. As an example, an attacker may immediate an AI mannequin to expose confidential information, similar to social safety numbers or non-public emails.
- Oblique, or cross-prompt injection assaults (XPIA), contain embedding malicious prompts inside seemingly innocuous exterior content material, similar to paperwork or emails. When an AI mannequin processes this content material, it inadvertently executes the embedded directions, probably compromising the system.
Immediate Shields seamlessly integrates with Azure OpenAI content material filters and is obtainable in Azure AI Content material Security. It defends in opposition to many sorts of immediate injection assaults, and new defenses are usually added as new assault sorts are uncovered. By leveraging superior machine studying algorithms and pure language processing, Immediate Shields successfully identifies and mitigates potential threats in consumer prompts and third-party information. This cutting-edge functionality will help the safety and integrity of your AI functions, serving to to safeguard your programs in opposition to malicious makes an attempt at manipulation or exploitation.
Immediate Shields capabilities embody:
- Contextual consciousness: Immediate Shields can discern the context through which prompts are issued, offering a further layer of safety by understanding the intent behind consumer inputs. Contextual consciousness additionally results in fewer false positives as a result of it’s able to distinguishing precise assaults from real consumer prompts.
- Spotlighting: At Microsoft Construct 2025, we introduced Spotlighting, a strong new functionality that enhances Immediate Shields’ skill to detect and block oblique immediate injection assaults. By distinguishing between trusted and untrusted inputs, this innovation empowers builders to higher safe generative AI functions in opposition to adversarial prompts embedded in paperwork, emails, and internet content material.
- Actual-time response: Immediate Shields operates in actual time and is among the first real-time capabilities to be made typically accessible. It may possibly swiftly establish and mitigate threats earlier than they’ll compromise the AI mannequin. This proactive strategy minimizes the chance of knowledge breaches and maintains system integrity.
Finish-to-end strategy
- Threat and security evaluations: Azure AI Foundry affords danger and security evaluations to let customers consider the output of their generative AI utility for content material dangers: hateful and unfair content material, sexual content material, violent content material, self-harm-related content material, direct and oblique jailbreak vulnerability, and guarded materials.
- Pink-teaming agent: Allow automated scans and adversarial probing to establish identified dangers at scale. Assist groups shift left by shifting from reactive incident response to proactive security testing earlier in growth. Security evaluations additionally help crimson teaming by producing adversarial datasets that strengthen testing and speed up situation detection.
- Strong controls and guardrails: Immediate Shields is only one of Azure AI Foundry’s strong content material filters. Azure AI Foundry affords quite a lot of content material filters to detect and mitigate danger and harms, immediate injection assaults, ungrounded output, protected materials, and extra.
- Defender for Cloud integration: Microsoft Defender now integrates instantly into Azure AI Foundry, surfacing AI safety posture suggestions and runtime risk safety alerts inside the growth atmosphere. This integration helps shut the hole between safety and engineering groups, permitting builders to proactively establish and mitigate AI dangers, similar to immediate injection assaults detected by Immediate Shields. Alerts are viewable within the Dangers and Alerts tab, empowering groups to cut back floor space danger and construct safer AI functions from the beginning.
Buyer use circumstances
AI Content material Security Immediate Shields affords quite a few advantages. Along with defending in opposition to jailbreaks, immediate injections, and doc assaults, it may well assist to make sure that LLMs behave as designed, by blocking prompts that explicitly attempt to circumvent guidelines and insurance policies outlined by the developer. The next use circumstances and buyer testimonials spotlight the impression of those capabilities.
AXA: Guaranteeing reliability and safety
AXA, a worldwide chief in insurance coverage, makes use of Azure OpenAI to energy its Safe GPT resolution. By integrating Azure’s content material filtering know-how and including its personal safety layer, AXA prevents immediate injection assaults and helps make sure the reliability of its AI fashions. Safe GPT is predicated on Azure OpenAI in Foundry Fashions, making the most of fashions which have already been fine-tuned utilizing human suggestions reinforcement studying. As well as, AXA may also depend on Azure content material filtering know-how, to which the corporate added its personal safety layer to forestall any jailbreaking of the mannequin utilizing Immediate Shields, making certain an optimum degree of reliability. These layers are usually up to date to keep up superior safeguarding.
Wrtn: Scaling securely with Azure AI Content material Security
Wrtn Applied sciences, a number one enterprise in Korea, depends on Azure AI Content material Security to keep up compliance and safety throughout its merchandise. At its core, Wrtn’s flagship know-how compiles an array of AI use circumstances and companies localized for Korean customers to combine AI into their on a regular basis lives. The platform fuses components of AI-powered search, chat performance, and customizable templates, empowering customers to work together seamlessly with an “Emotional Companion” AI-infused agent. These AI brokers have participating, lifelike personalities, interacting in dialog with their creators. The imaginative and prescient is a extremely interactive private agent that’s distinctive and particular to you, your information, and your reminiscences.
As a result of the product is extremely customizable to particular customers, the built-in skill to toggle content material filters and Immediate Shields is extremely advantageous, permitting Wrtn to effectively customise its safety measures for various finish customers. This lets builders scale merchandise whereas staying compliant, customizable, and attentive to customers throughout Korea.
“It’s not simply in regards to the safety and privateness, but in addition security. By way of Azure, we are able to simply activate or deactivate content material filters. It simply has so many options that add to our product efficiency,” says Dongjae “DJ” Lee, Chief Product Officer.
Combine Immediate Shields into your AI technique
For IT determination makers trying to improve the safety of their AI deployments, integrating Azure’s Immediate Shields is a strategic crucial. Thankfully, enabling Immediate Shields is simple.
Azure’s Immediate Shields and built-in AI security measures supply an unparalleled degree of safety for AI fashions, serving to to make sure that organizations can harness the facility of AI with out compromising on safety. Microsoft is a pacesetter in figuring out and mitigating immediate injection assaults, and makes use of greatest practices developed with many years of analysis, coverage, product engineering, and learnings from constructing AI merchandise at scale, so you possibly can obtain your AI transformation with confidence. By integrating these capabilities into your AI technique, you possibly can assist safeguard your programs from immediate injection assaults and assist keep the belief and confidence of your customers.
Our dedication to Reliable AI
Organizations throughout industries are utilizing Azure AI Foundry and Microsoft 365 Copilot capabilities to drive development, improve productiveness, and create value-added experiences.
We’re dedicated to serving to organizations use and construct AI that’s reliable, that means it’s safe, non-public, and protected. Reliable AI is barely potential once you mix our commitments, similar to our Safe Future Initiative and Accountable AI ideas, with our product capabilities to unlock AI transformation with confidence.
Get began with Azure AI Content material Security