Plain-English strategy guides for every attack family in ai-blackteam. Each page explains what the attacks do, how they work, real examples, why a model might fall for them, and how to defend.
CategoryFocus
Academic ExploitationThese attacks try to get the AI to help cheat in school or fake research. The goal is dish
Access ControlThese attacks try to reach data or actions the user is not allowed to touch. The goal is t
Adversarial Machine LearningThese attacks add small, carefully chosen changes to a prompt to trick the model. The goal
Agent ExploitationThese attacks target AI agents that can use tools, run commands, read files, or call servi
Autonomous RiskThese attacks probe whether an AI will resist human control to reach its goals. The goal i
Autonomous SystemsThese attacks try to make an AI take control of, override, or sabotage machines that move
AvailabilityThese attacks try to make the AI service slow, expensive, or unable to respond. The goal i
Bias ExploitationThese attacks try to get the AI to make unfair or discriminatory judgments about people. T
Capability ElicitationThese attacks probe whether the AI will hand over dangerous know-how. They test if the mod
CBRN EvasionCBRN means chemical, biological, radiological, and nuclear threats. These attacks try to s
Child SafetyThese attacks try to make an AI produce content that harms children or helps someone bypas
Code ExploitationThese attacks ask the AI to write working malicious software or hacking tools. The goal is
Compliance EvasionThese attacks try to get the AI to help skirt laws, sanctions, or rules. The user wants a
ComplianceThese attacks try to get the AI to help users break the rules of a platform or service. Th
Context ManipulationThese attacks work over a whole conversation, not one message. The attacker shapes the cha
Copyright and IP TheftThese attacks try to make an AI hand over protected work that does not belong to the user.
Cross-Platform AbuseThese attacks target AI agents that can use tools and connect to outside systems. The goal
Crypto ExploitationThese attacks try to get an AI to help steal cryptocurrency or run scams against crypto us
CybercrimeThese attacks try to get an AI to help with serious online crime. That includes stealing c
DisinformationThese attacks try to make an AI produce false or misleading content meant to deceive peopl
Election InterferenceAttacks that try to make an AI help damage a fair election. This includes lies about votin
EncodingAttacks that hide a banned request inside a code, cipher, or odd format. The AI decodes it
Financial ExploitationAttacks that try to make an AI help cheat financial markets or rip off money systems. This
Financial FraudAttacks that try to make an AI help steal money or trick people out of it. This covers sca
Gaming ExploitationAttacks that try to make an AI help abuse video games and players. This ranges from cheati
Harmful ContentThese attacks try to make an AI produce content that hurts real people. Think threats, har
Healthcare ExploitationThese attacks aim at the medical world. They try to get the AI to help with fraud, patient
Identity AttackThese attacks try to make the AI help someone pretend to be a person or organization they
Information DisclosureThese attacks try to pull secret information out of the AI system itself. That means hidde
Information WarfareThese attacks use the AI to wage organized influence campaigns. The goal is to mislead the
Infrastructure AttackThese attacks ask the AI for help damaging or controlling critical real-world systems. Thi
InjectionThese attacks hide harmful instructions or code inside data that the AI is asked to read o
IoT ExploitationThese attacks target smart, connected devices. That includes home gadgets, cars, drones, m
Legal ExploitationThese attacks ask the AI to help fake legal documents, lie under oath, or cheat government
MCP ExploitationThese attacks target AI agents that use tools through MCP the Model Context Protocol. The
Media ManipulationTricks that push an AI to produce fake media content like fabricated news, quotes, documen
Memory ExploitationTricks that mess with what the AI thinks it remembers or agreed to. The attacker plants fa
MisinformationTricks that nudge an AI into stating false things as if they were true. The aim is wrong b
Model ExtractionTricks that try to pull private details out of an AI model. That includes its hidden syste
Multi-Agent ExploitationTricks that target setups where AI agents talk to or hand work to each other. The attacker
MultimodalAttacks that hide harmful instructions inside non-text inputs like images, audio, or video
Output ManipulationAttacks that shape how the AI formats or labels its answer so harmful content slips past d
PersuasionAttacks that use human-style social pressure to talk the AI into breaking its rules. No co
Privacy ViolationAttacks that try to pull private personal information out of the AI or use it to profile a
Prompt InjectionAttacks that sneak new instructions into the input so the AI ignores its real rules and fo
Protocol ExploitationThese attacks abuse the machine-to-machine plumbing of an AI agent: the tools it calls, th
Psychological ManipulationThese attacks try to get the AI to coach, role-play, or endorse the tactics that abusers u
Public SafetyThese attacks try to get the AI to help with actions that put the public at risk: poisonin
RAG ExploitationRAG retrieval-augmented generation lets an AI look up documents to answer questions. These
Regulatory EvasionThis attack tries to get the AI to help a person or business break the rules that regulato
Safety CircumventionThese attacks try to switch off or sneak past the safety rules built into an AI model. The
Scientific MisconductThese attacks ask the AI to help cheat in research. That means faking data, hiding bad res
Social Engineering (Advanced)These are ready-made scam playbooks. They ask the AI to produce the exact scripts used in
Social EngineeringThese attacks trick the AI by playing on trust, authority, and emotion instead of hacking
Supply ChainThese attacks target the parts that go into building or running an AI: its training data,
SurveillanceThese attacks try to get an AI to help secretly watch, track, or spy on a person without t
Tool ExploitationThis attack targets an AI that can use tools, like reading files or running commands, and
Unqualified AdviceThese attacks try to get an AI to act like a doctor, lawyer, or other licensed expert and
Vulnerability ResearchThese attacks hand the AI some code and try to get it to not only spot a security flaw but
Weapons and ViolenceThese attacks try to get an AI to help plan or carry out physical violence, build weapons,
Workplace ExploitationThese attacks try to get an AI to help employers mistreat, cheat, or illegally control the