Detections
Explore public detection logic contributed by the community across SIEM and rule languages.
1,733 detections
Filters
Last updated
All Time
Detection languages
909
387
164
127
68
Contributors
479
417
201
177
61
Categories
20,443
11,831
5,875
5,151
4,864
1,733
Platforms
822
436
329
274
206
Products / Services
498
378
118
96
79
MITRE Techniques
433
327
225
196
196
CVEs
12
12
10
10
6
IDS Classtypes
1
1
IDS Protocols
2
Detects adversarial AI cost harvesting (AML.T0034.000) by identifying anomalous volumes of low-complexity queries against an AI inference API that result in a significant, unexplained spike in billed costs. This behavior mimics denial-of-service tactics aimed at exhausting compute capacity and financial resources.
Detects ingestion of documents containing potential LLM prompt injection payloads (using zero-width characters or HTML comments to hide imperative instructions) into a RAG system, followed by anomalous LLM behavior such as unauthorized tool execution or unintended data disclosure.
Detects ingestion of documents containing potential LLM prompt injection payloads (using zero-width characters or HTML comments to hide imperative instructions) into a RAG system, followed by anomalous LLM behavior such as unauthorized tool execution or unintended data disclosure.
Detects ingestion of documents containing potential LLM prompt injection payloads (using zero-width characters or HTML comments to hide imperative instructions) into a RAG system, followed by anomalous LLM behavior such as unauthorized tool execution or unintended data disclosure.
Detects anomalous AI model inference activity where a caller submits a high volume of near-duplicate queries while frequently requesting raw confidence scores. This behavior is indicative of a membership-inference privacy attack, where an adversary attempts to determine if specific data points were included in the model's training set by analyzing query response patterns.
Detects LLM jailbreak attempts using a 'crescendo' multi-turn strategy. The rule monitors for sequences where an initial prompt contains known jailbreak-intent keywords leading to an AI refusal, followed shortly by a compliant AI response to a rephrased request within the same conversation session.
Detects adversaries attempting to override LLM system instructions by submitting crafted prompts containing known injection patterns (e.g., 'ignore previous instructions', role-override). The rule tracks anomalous interaction patterns identified by multiple occurrences or a variety of override phrases within a short timeframe.
Detects the ingestion of documents into production RAG (Retrieval-Augmented Generation) indexes from untrusted or external-facing sources, which may indicate an attempt to perform RAG poisoning attacks.
This rule detects potential cost harvesting or service abuse against AI gateway endpoints. It establishes a baseline of typical user activity over a 30-day period and flags anomalies where current request volume (in the last 1 hour or 24 hours) significantly exceeds the user's established P95 baseline. To reduce noise, it specifically identifies scenarios where these high-frequency requests are associated with low-complexity, short prompts, which are indicative of automated probing or resource-intensive scraping rather than legitimate high-utility usage.
This rule detects anomalous behavior in AI agent tool invocations, specifically monitoring for high volumes of tool calls, high costs associated with token consumption, or suspicious tool interactions following a flagged indirect prompt injection. This behavior is indicative of potential resource exhaustion (denial of service) or abusive agent behavior as defined by the MITRE ATLAS framework for AI security.
Detects suspicious AI agent behavior by identifying two primary scenarios: 1) The invocation of sensitive tools (e.g., code execution, file deletion) within a short timeframe following a flagged prompt injection or jailbreak attempt in the same conversation; or 2) The invocation of a tool by an AI agent that is not explicitly defined in its allowed tool list for the given workflow.
This rule detects potential Denial of Service (DoS) attacks against AI inference endpoints. It monitors for sustained high latency and high error rates combined with a high volume of 'heavy' requests (those exceeding a token/character count threshold) from specific source IPs. This pattern suggests an attempt to exhaust system resources by forcing the processing of complex or overly large prompts.
This rule detects potential Denial of Service (DoS) attacks against AI inference endpoints. It monitors for sustained high latency and high error rates combined with a high volume of 'heavy' requests (those exceeding a token/character count threshold) from specific source IPs. This pattern suggests an attempt to exhaust system resources by forcing the processing of complex or overly large prompts.
This rule monitors package installation logs for indicators of packages potentially generated or suggested by AI tools (e.g., Copilot, code assistants) being installed in a target environment. It specifically looks for a low volume of installations (<=3) for packages that have been published within the last 14 days, which is a pattern often associated with the 'Publish Hallucinated Entities' technique in AI systems, where malicious or hallucinated code packages are introduced into the supply chain.
Detects suspicious modifications or registrations of AI agent tools within the registry. The rule identifies three core indicators of compromise: usage of an unverified or external registry source, unauthorized tool definition modifications (hash mismatch against baseline), and a suspicious 'update chain' where a non-standard maintainer pushes a tool update that simultaneously increases requested operational scopes.
Detects attempts to bypass LLM safety alignment by utilizing roleplay or hypothetical framing (e.g., DAN mode) alongside evidence of prompt iteration, identified by repeated moderation blocks within the same session.
Detects potential passkey phishing follow-on activity by monitoring for successful sign-ins from unmanaged or non-compliant devices to OfficeHome or via device code flow, followed within 30 minutes by access to self-service account-management applications, accompanied by specific authentication errors (50074 or 50140).
Detects anomalous GitHub audit log activity indicative of a potential supply-chain compromise. The rule identifies workflows or automated entities (Bot/App) that access sensitive Action secrets followed by the publishing of packages to public registries like PyPI or npm. This activity can represent the precursor steps of token-theft-driven malicious package injection.
This rule detects the creation of a new Azure AD (Entra ID) application with a name containing AI-related keywords (e.g., 'ai', 'copilot', 'gpt') that is subsequently granted high-privilege Microsoft Graph API permissions within a 24-hour window. This behavior is often associated with attackers setting up seemingly benign-looking applications to conduct OAuth-based persistent access or data exfiltration.
Detects potential command injection attempts or unauthorized access attempts directed at WatchGuard Access Point management interfaces, identified by suspicious strings typically used in exploitation payloads within device logs.
Detects potential command injection attempts or unauthorized access attempts directed at WatchGuard Access Point management interfaces, identified by suspicious strings typically used in exploitation payloads within device logs.
Page 9 of 83