Ibrahim Saud
@tektrixIndiaCompletionist
2 followers18,457 downloads7,054 copies47 likes38,395 views
11,679 detections
Filters
Last updated
All Time
Detection languages
3,760
1,874
1,586
966
944
Categories
4,878
3,246
1,529
1,303
1,122
Platforms
7,678
1,824
1,066
999
986
Products / Services
2,963
1,768
1,278
953
798
MITRE Techniques
3,615
3,555
2,488
1,474
1,186
CVEs
36
27
26
25
23
IDS Classtypes
360
113
38
24
24
IDS Protocols
315
114
93
47
10
This rule detects unauthorized or malicious agentic AI behavior where prompt injection or poisoned content causes an AI agent to execute excessive tool calls or enter an infinite loop of tool invocations. This behavior can lead to compute resource exhaustion, increased operational costs, and potential data exfiltration via excessive querying.
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 external reconnaissance activity targeting AI backend services. Adversaries scan for known AI infrastructure ports (such as TensorFlow Serving, Triton, or Ray) and common API paths (e.g., /v1/models, /predict) to identify potential targets. The detection utilizes proxy logs to correlate these suspicious network attributes, high request rates, or known scanning user agents.
Detects potential remote code execution triggered by loading untrusted AI model files (e.g., pickle, .pt, .pth, .ckpt) in Python-based environments. The rule identifies suspicious child process execution or the presence of known dangerous deserialization/payload indicators (like os.system, subprocess, or socket) within the command line of common model-loading applications, suggesting a model-based supply chain compromise.
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 the execution of 'rnpkeys.exe' originating from the 'C:\ProgramData\keyroll' directory, which is a non-standard location for executable files and may indicate malicious activity.
Page 104 of 1168