101 indexed

ATLASATLAS adversarial ML techniques

101 MITRE ATLAS top-level techniques covering the adversarial-ML attack surface, grouped by tactic. Authored by Adam Lundqvist.

101 across 16 categories

Resource Development13

IDTitleSummary
AML.T0002Acquire Public AI ArtifactsAdversaries may search public sources, including cloud storage, public-facing services, and software or data repositories, to identify AI artifacts. These AI a…
AML.T0008Acquire InfrastructureAdversaries may buy, lease, or rent infrastructure for use throughout their operation. A wide variety of infrastructure exists for hosting and orchestrating ad…
AML.T0016Obtain CapabilitiesAdversaries may search for and obtain software capabilities for use in their operations. Capabilities may be specific to AI-based attacks [Adversarial AI Attac…
AML.T0017Develop CapabilitiesAdversaries may develop their own capabilities to support operations. This process encompasses identifying requirements, building solutions, and deploying capa…
AML.T0019Publish Poisoned DatasetsAdversaries may [Poison Training Data](/techniques/AML.T0020) and publish it to a public location. The poisoned dataset may be a novel dataset or a poisoned va…
AML.T0020Poison Training DataAdversaries may attempt to poison datasets used by an AI model by modifying the underlying data or its labels. This allows the adversary to embed vulnerabiliti…
AML.T0021Establish AccountsAdversaries may create accounts with various services for use in targeting, to gain access to resources needed in [AI Attack Staging](/tactics/AML.TA0001), or …
AML.T0058Publish Poisoned ModelsAdversaries may publish a poisoned model to a public location such as a model registry or code repository. The poisoned model may be a novel model or a poisone…
AML.T0060Publish Hallucinated EntitiesAdversaries may create an entity they control, such as a software package, website, or email address to a source hallucinated by an LLM. The hallucinations may…
AML.T0065LLM Prompt CraftingAdversaries may use their acquired knowledge of the target generative AI system to craft prompts that bypass its defenses and allow malicious instructions to b…
AML.T0066Retrieval Content CraftingAdversaries may write content designed to be retrieved by user queries and influence a user of the system in some way. This abuses the trust the user has in th…
AML.T0079Stage CapabilitiesAdversaries may upload, install, or otherwise set up capabilities that can be used during targeting. To support their operations, an adversary may need to take…
AML.T0104Publish Poisoned AI Agent ToolAdversaries may create and publish poisoned AI agent tools. Poisoned tools may contain an [LLM Prompt Injection](/techniques/AML.T0051), which can lead to a va…

Defense Evasion12

IDTitleSummary
AML.T0067LLM Trusted Output Components ManipulationAdversaries may utilize prompts to a large language model (LLM) which manipulate various components of its response in order to make it appear trustworthy to t…
AML.T0068LLM Prompt ObfuscationAdversaries may hide or otherwise obfuscate prompt injections or retrieval content to avoid detection from humans, large language model (LLM) guardrails, or ot…
AML.T0071False RAG Entry InjectionAdversaries may introduce false entries into a victim's retrieval augmented generation (RAG) database. Content designed to be interpreted as a document by the …
AML.T0073ImpersonationAdversaries may impersonate a trusted person or organization in order to persuade and trick a target into performing some action on their behalf. For example, …
AML.T0074MasqueradingAdversaries may attempt to manipulate features of their artifacts to make them appear legitimate or benign to users and/or security tools. Masquerading occurs …
AML.T0076Corrupt AI ModelAn adversary may purposefully corrupt a malicious AI model file so that it cannot be successfully deserialized in order to evade detection by a model scanner. …
AML.T0092Manipulate User LLM Chat HistoryAdversaries may manipulate a user's large language model (LLM) chat history to cover the tracks of their malicious behavior. They may hide persistent changes t…
AML.T0094Delay Execution of LLM InstructionsAdversaries may include instructions to be followed by the AI system in response to a future event, such as a specific keyword or the next interaction, in orde…
AML.T0097Virtualization/Sandbox EvasionAdversaries may employ various means to detect and avoid virtualization and analysis environments. This may include changing behaviors based on the results of …
AML.T0107Exploitation for Defense EvasionAdversaries may exploit a system or application vulnerability to bypass security features. Exploitation of a vulnerability occurs when an adversary takes advan…
AML.T0109AI Supply Chain Rug PullAdversaries may publish legitimate AI components or software, gain user adoption, then push an update with a malicious variant, leading to [AI Supply Chain Com…
AML.T0111AI Supply Chain Reputation InflationAI Supply Chain Reputation Inflation is the process of building or leveraging genuinely credible-looking trust signals to increase the perceived legitimacy of …

Discovery9

IDTitleSummary
AML.T0007Discover AI ArtifactsAdversaries may search private sources to identify AI learning artifacts that exist on the system and gather information about them. These artifacts can includ…
AML.T0013Discover AI Model OntologyAdversaries may discover the ontology of an AI model's output space, for example, the types of objects a model can detect. The adversary may discovery the onto…
AML.T0014Discover AI Model FamilyAdversaries may discover the general family of model. General information about the model may be revealed in documentation, or the adversary may use carefully …
AML.T0062Discover LLM HallucinationsAdversaries may prompt large language models and identify hallucinated entities. They may request software packages, commands, URLs, organization names, or e-m…
AML.T0063Discover AI Model OutputsAdversaries may discover model outputs, such as class scores, whose presence is not required for the system to function and are not intended for use by the end…
AML.T0069Discover LLM System InformationThe adversary is trying to discover something about the large language model's (LLM) system information. This may be found in a configuration file containing t…
AML.T0075Cloud Service DiscoveryAdversaries may attempt to enumerate the cloud services running on a system after gaining access. These methods can differ from platform-as-a-service (PaaS), t…
AML.T0084Discover AI Agent ConfigurationAdversaries may attempt to discover configuration information for AI agents present on the victim's system. Agent configurations can include tools or services …
AML.T0089Process DiscoveryAdversaries may attempt to get information about processes running on a system. Once obtained, this information could be used to gain an understanding of commo…

Impact8

IDTitleSummary
AML.T0029Denial of AI ServiceAdversaries may target AI-enabled systems with a flood of requests for the purpose of degrading or shutting down the service. Since many AI systems require sig…
AML.T0031Erode AI Model IntegrityAdversaries may degrade the target model's performance with adversarial data inputs to erode confidence in the system over time. This can lead to the victim or…
AML.T0034Cost HarvestingAdversaries may deliberately drive a victim's AI services beyond normal operating capacity with the intent of increasing the cost of services. This may be achi…
AML.T0046Spamming AI System with Chaff DataAdversaries may spam the AI system with chaff data that causes increase in the number of detections. This can cause analysts at the victim organization to wast…
AML.T0048External HarmsAdversaries may abuse their access to a victim system and use its resources or capabilities to further their goals by causing harms external to that system. Th…
AML.T0059Erode Dataset IntegrityAdversaries may poison or manipulate portions of a dataset to reduce its usefulness, reduce trust, and cause users to waste resources correcting errors.
AML.T0101Data Destruction via AI Agent Tool InvocationAdversaries may invoke an AI agent's tool capable of performing mutative operations to perform Data Destruction. Adversaries may destroy data and files on spec…
AML.T0112Machine CompromiseAdversaries may compromise a machine by exploiting or manipulating AI-enabled components on the system. Compromising a victim system allows the adversary to ex…

Reconnaissance8

IDTitleSummary
AML.T0000Search Open Technical DatabasesAdversaries may search for publicly available research and technical documentation to learn how and where AI is used within a victim organization. The adversar…
AML.T0001Search Open AI Vulnerability AnalysisMuch like the [Search Open Technical Databases](/techniques/AML.T0000), there is often ample research available on the vulnerabilities of common AI models. Onc…
AML.T0003Search Victim-Owned WebsitesAdversaries may search websites owned by the victim for information that can be used during targeting. Victim-owned websites may contain technical details abou…
AML.T0004Search Application RepositoriesAdversaries may search open application repositories during targeting. Examples of these include Google Play, the iOS App store, the macOS App Store, and the M…
AML.T0006Active ScanningAn adversary may probe or scan the victim system to gather information for targeting. This is distinct from other reconnaissance techniques that do not involve…
AML.T0064Gather RAG-Indexed TargetsAdversaries may identify data sources used in retrieval augmented generation (RAG) systems for targeting purposes. By pinpointing these sources, attackers can …
AML.T0087Gather Victim Identity InformationAdversaries may gather information about the victim's identity that can be used during targeting. Information about identities may include a variety of details…
AML.T0095Search Open Websites/DomainsAdversaries may search public websites and/or domains for information about victims that can be used during targeting. Information about victims may be availab…

Initial Access7

IDTitleSummary
AML.T0010AI Supply Chain CompromiseAdversaries may gain initial access to a system by compromising the unique portions of the AI supply chain. This could include [Hardware](/techniques/AML.T0010…
AML.T0012Valid AccountsAdversaries may obtain and abuse credentials of existing accounts as a means of gaining Initial Access. Credentials may take the form of usernames and password…
AML.T0015Evade AI ModelAdversaries can [Craft Adversarial Data](/techniques/AML.T0043) that prevents an AI model from correctly identifying the contents of the data or [Generate Deep…
AML.T0049Exploit Public-Facing ApplicationAdversaries may attempt to take advantage of a weakness in an Internet-facing computer or program using software, data, or commands in order to cause unintende…
AML.T0052PhishingAdversaries may send phishing messages to gain access to victim systems. All forms of phishing are electronically delivered social engineering. Phishing can be…
AML.T0078Drive-by CompromiseAdversaries may gain access to an AI system through a user visiting a website over the normal course of browsing, or an AI agent retrieving information from th…
AML.T0093Prompt Infiltration via Public-Facing ApplicationAn adversary may introduce malicious prompts into the victim's system via a public-facing application with the intention of it being ingested by an AI at some …

Persistence7

IDTitleSummary
AML.T0018Manipulate AI ModelAdversaries may directly manipulate an AI model to change its behavior or introduce malicious code. Manipulating a model gives the adversary a persistent chang…
AML.T0061LLM Prompt Self-ReplicationAn adversary may use a carefully crafted [LLM Prompt Injection](/techniques/AML.T0051) designed to cause the LLM to replicate the prompt as part of its output.…
AML.T0070RAG PoisoningAdversaries may inject malicious content into data indexed by a retrieval augmented generation (RAG) system to contaminate a future thread through RAG-based se…
AML.T0080AI Agent Context PoisoningAdversaries may attempt to manipulate the context used by an AI agent's large language model (LLM) to influence the responses it generates or actions it takes.…
AML.T0081Modify AI Agent ConfigurationAdversaries may modify the configuration files for AI agents on a system. This allows malicious changes to persist beyond the life of a single agent and affect…
AML.T0099AI Agent Tool Data PoisoningAdversaries may place malicious content on a victim's system where it can be retrieved by an AI Agent Tool. This may be accomplished by placing documents in a …
AML.T0110AI Agent Tool PoisoningAdversaries may achieve persistence by poisoning tools used by AI agents including built-in tools or tools available to the agent via Model Context Protocol (M…

Credential Access6

IDTitleSummary
AML.T0055Unsecured CredentialsAdversaries may search compromised systems to find and obtain insecurely stored credentials. These credentials can be stored and/or misplaced in many locations…
AML.T0082RAG Credential HarvestingAdversaries may attempt to use their access to a large language model (LLM) on the victim's system to collect credentials. Credentials may be stored in interna…
AML.T0083Credentials from AI Agent ConfigurationAdversaries may access the credentials of other tools or services on a system from the configuration of an AI agent. AI Agents often utilize external tools or…
AML.T0090OS Credential DumpingAdversaries may extract credentials from OS caches, application memory, or other sources on a compromised system. Credentials are often in the form of a hash o…
AML.T0098AI Agent Tool Credential HarvestingAdversaries may attempt to use their access to an AI agent on the victim's system to retrieve data from available agent tools to collect credentials. Agent too…
AML.T0106Exploitation for Credential AccessAdversaries may exploit software vulnerabilities in an attempt to collect credentials. Exploitation of a software vulnerability occurs when an adversary takes …

Execution6

IDTitleSummary
AML.T0011User ExecutionAn adversary may rely upon specific actions by a user in order to gain execution. Users may inadvertently execute unsafe code introduced via [AI Supply Chain C…
AML.T0050Command and Scripting InterpreterAdversaries may abuse command and script interpreters to execute commands, scripts, or binaries. These interfaces and languages provide ways of interacting wit…
AML.T0051LLM Prompt InjectionAn adversary may craft malicious prompts as inputs to an LLM that cause the LLM to act in unintended ways. These "prompt injections" are often designed to caus…
AML.T0053AI Agent Tool InvocationAdversaries may use their access to an AI agent to invoke tools the agent has access to. LLMs are often connected to other services or resources via tools to i…
AML.T0100AI Agent ClickbaitAdversaries may craft deceptive web content designed to bait Computer-Using AI agents or AI web browsers into taking unintended actions, such as clicking butto…
AML.T0103Deploy AI AgentAdversaries may launch AI agents in the victim's environment to execute actions on their behalf. AI agents may have access to a wide range of tools and data so…

Exfiltration6

IDTitleSummary
AML.T0024Exfiltration via AI Inference APIAdversaries may exfiltrate private information via [AI Model Inference API Access](/techniques/AML.T0040). AI Models have been shown leak private information a…
AML.T0025Exfiltration via Cyber MeansAdversaries may exfiltrate AI artifacts or other information relevant to their goals via traditional cyber means. See the ATT&CK [Exfiltration](https://attack…
AML.T0056Extract LLM System PromptAdversaries may attempt to extract a large language model's (LLM) system prompt. This can be done via prompt injection to induce the model to reveal its own sy…
AML.T0057LLM Data LeakageAdversaries may craft prompts that induce the LLM to leak sensitive information. This can include private user data or proprietary information. The leaked info…
AML.T0077LLM Response RenderingAn adversary may get a large language model (LLM) to respond with private information that is hidden from the user when the response is rendered by the user's …
AML.T0086Exfiltration via AI Agent Tool InvocationAI agent tools capable of performing write operations may be invoked to exfiltrate data to an adversary. Sensitive information can be encoded into the tool's i…

Ai Attack Staging5

IDTitleSummary
AML.T0005Create Proxy AI ModelAdversaries may obtain models to serve as proxies for the target model in use at the victim organization. Proxy models are used to simulate complete access to …
AML.T0042Verify AttackAdversaries can verify the efficacy of their attack via an inference API or access to an offline copy of the target model. This gives the adversary confidence …
AML.T0043Craft Adversarial DataAdversarial data are inputs to an AI model that have been modified such that they cause the adversary's desired effect in the target model. Effects can range f…
AML.T0088Generate DeepfakesAdversaries may use generative artificial intelligence (GenAI) to create synthetic media (i.e. imagery, video, audio, and text) that appear authentic. These "[…
AML.T0102Generate Malicious CommandsAdversaries may use large language models (LLMs) to dynamically generate malicious commands from natural language. Dynamically generated commands may be harder…

Ai Model Access4

IDTitleSummary
AML.T0040AI Model Inference API AccessAdversaries may gain access to a model via legitimate access to the inference API. Inference API access can be a source of information to the adversary ([Disco…
AML.T0041Physical Environment AccessIn addition to the attacks that take place purely in the digital domain, adversaries may also exploit the physical environment for their attacks. If the model …
AML.T0044Full AI Model AccessAdversaries may gain full "white-box" access to an AI model. This means the adversary has complete knowledge of the model architecture, its parameters, and cla…
AML.T0047AI-Enabled Product or ServiceAdversaries may use a product or service that uses artificial intelligence under the hood to gain access to the underlying AI model. This type of indirect mode…

Collection4

IDTitleSummary
AML.T0035AI Artifact CollectionAdversaries may collect AI artifacts for [Exfiltration](/tactics/AML.TA0010) or for use in [AI Attack Staging](/tactics/AML.TA0001). AI artifacts include model…
AML.T0036Data from Information RepositoriesAdversaries may leverage information repositories to mine valuable information. Information repositories are tools that allow for storage of information, typic…
AML.T0037Data from Local SystemAdversaries may search local system sources, such as file systems and configuration files or local databases, to find files of interest and sensitive data prio…
AML.T0085Data from AI ServicesAdversaries may use their access to a victim organization's AI-enabled services to collect proprietary or otherwise sensitive information. As organizations ado…

Command And Control3

IDTitleSummary
AML.T0072Reverse ShellAdversaries may utilize a reverse shell to communicate and control the victim system. Typically, a user uses a client to connect to a remote machine which is …
AML.T0096AI Service APIAdversaries may communicate using the API of an AI service on the victim's system. The adversary's commands to the victim system, and often the results, are em…
AML.T0108AI AgentAdversaries may abuse AI agents present on the victim's system for command and control. AI agents are often granted access to tools that can execute shell comm…

Privilege Escalation2

IDTitleSummary
AML.T0054LLM JailbreakAdversaries may induce a large language model (LLM) to ignore, circumvent, or override its safety/alignment behaviors and/or guardails to elicit outputs the mo…
AML.T0105Escape to HostAdversaries may break out of a container or virtualized environment to gain access to the underlying host. This can allow an adversary access to other containe…

Lateral Movement1

IDTitleSummary
AML.T0091Use Alternate Authentication MaterialAdversaries may use alternate authentication material, such as password hashes, Kerberos tickets, and application access tokens, in order to move laterally wit…
Sourced from MITRE ATLAS. Curated by Adam Lundqvist, Founder at SQUR.