Skip to main content

主題詞彙表部落格 ATT&CK 導覽器挑戰資源

Loading...

© 2026 redteams.ai. 保留所有權利。

詞彙表標籤部落格貢獻方法論書籤 RSS 訂閱 GitHub 聯絡我們

採用 Next.js

隱私權 Cookie 服務條款版權資訊

標籤

依主題瀏覽文章。

Showing 1370 of 3035 tags

prompt-injection

agentic-exploitation

frontier-research

industry-verticals

incident-response

function-calling

skill-verification

training-pipeline

ai-forensics-ir

code-gen-security

model-extraction

chain-of-thought

data-exfiltration

risk-assessment

indirect-injection

vulnerabilities

privilege-escalation

constitutional-ai

code-generation

federated-learning

output-filtering

social-engineering

threat-modeling

cloud-ai-security

instruction-hierarchy

membership-inference

anomaly-detection

defense-in-depth

interpretability

representation-engineering

alignment-faking

injection-research

input-validation

lateral-movement

model-deep-dives

quick-reference

regression-testing

image-injection

vector-database

agentic-attacks

critical-infrastructure

data-extraction

in-context-learning

mechanistic-interpretability

incident-analysis

safety-training

agent-frameworks

chain-of-custody

context-overflow

deceptive-alignment

defense-testing

experiment-tracking

fine-tuning-security

risk-management

security-testing

structured-output

transfer-attacks

trust-boundaries

data-protection

container-security

content-filtering

content-moderation

executive-summary

fraud-detection

information-leakage

least-privilege

model-identification

model-inversion

model-poisoning

nemo-guardrails

rules-of-engagement

semantic-kernel

transferability

vector-databases

vulnerability-scanning

adversarial-suffix

9

9

context-manipulation

9

customer-service

9

distributed-training

9

9

exploit-primitives

9

9

intellectual-property

9

memory-poisoning

9

9

9

9

pipeline-security

9

9

safety-degradation

9

9

9

activation-steering

8

8

8

8

8

8

8

automated-testing

8

8

8

8

8

8

8

8

8

capture-the-flag

8

8

8

8

8

8

8

8

command-injection

8

8

8

8

8

continual-learning

8

8

8

8

dataset-poisoning

8

denial-of-service

8

dependency-confusion

8

8

document-injection

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

8

managed-identity

8

8

8

8

8

8

model-integrity

8

8

8

network-security

8

8

8

8

8

8

payload-crafting

8

pipeline-poisoning

8

8

8

8

race-conditions

8

8

8

8

8

8

8

8

8

reverse-engineering

8

safety-evaluation

8

8

8

8

8

semantic-similarity

8

8

8

8

8

8

8

8

8

structured-data

8

8

8

token-smuggling

8

8

8

8

8

8

8

8

8

8

8

agent-exploitation

7

7

responsible-disclosure

7

7

7

7

7

abuse-detection

6

abuse-prevention

6

adaptive-attacks

6

adversarial-attacks

6

6

6

6

6

6

6

6

6

6

autonomous-vehicles

6

6

6

blind-injection

6

6

6

6

capability-mapping

6

cascading-failures

6

catastrophic-forgetting

6

6

6

6

6

6

6

6

6

6

6

confidential-computing

6

6

constitutional-classifiers

6

6

6

content-generation

6

continuous-monitoring

6

continuous-testing

6

contract-analysis

6

6

6

6

6

6

6

6

curriculum-learning

6

6

6

6

6

6

6

defense-evaluation

6

denial-of-wallet

6

detection-evasion

6

6

6

document-review

6

6

6

6

6

6

embedding-attacks

6

embedding-inversion

6

6

evidence-collection

6

6

6

6

6

6

6

6

frame-injection

6

6

6

6

6

6

6

6

6

6

6

6

6

6

6

injection-detection

6

input-filtering

6

6

instruction-following

6

6

6

6

6

law-enforcement

6

6

6

6

6

6

medical-imaging

6

6

6

6

6

model-comparison

6

model-compression

6

6

6

6

6

6

6

6

6

6

openai-assistants

6

6

6

6

6

parameter-injection

6

penetration-testing

6

6

6

6

6

6

6

6

6

6

6

program-management

6

6

6

6

6

protocol-security

6

6

6

6

6

6

6

6

6

6

6

6

resource-exhaustion

6

safety-boundaries

6

safety-classifier

6

safety-comparison

6

safety-critical

6

6

6

6

6

6

6

6

6

security-assessment

6

6

session-isolation

6

6

speculative-decoding

6

6

6

6

suggestion-poisoning

6

synthetic-media

6

6

6

6

6

thought-injection

6

threat-intelligence

6

6

6

6

6

6

6

6

6

training-security

6

6

6

6

6

6

6

6

6

6

6

vulnerability-patterns

6

6

6

5

adversarial-images

5

5

5

backdoor-detection

5

5

5

coding-assistants

5

5

domain-specific

5

getting-started

5

guardrail-bypass

5

5

5

5

model-context-protocol

5

5

5

5

5

5

secure-development

5

5

5

5

vulnerability-research

5

4

4

4

4

4

4

advanced-techniques

4

advanced-testing

4

adversarial-documents

4

adversarial-embeddings

4

adversarial-perturbations

4

adversarial-robustness

4

adversarial-training

4

4

agent-permissions

4

4

4

ai-generated-code

4

4

4

4

4

4

alignment-removal

4

4

4

4

4

api-fine-tuning

4

4

4

4

4

4

4

attention-manipulation

4

automated-attacks

4

autonomous-agent

4

autonomous-agents

4

autonomous-vehicle

4

4

4

4

4

4

4

4

4

4

4

4

boundary-mapping

4

4

4

4

4

4

4

4

4

4

4

4

4

citizen-services

4

4

4

4

4

cloud-forensics

4

4

cluster-attacks

4

4

4

4

4

4

4

4

4

constitutional-AI

4

4

content-filter-bypass

4

context-injection

4

context-isolation

4

continuous-learning

4

continuous-training

4

4

4

conversation-steering

4

4

4

4

4

4

covert-channels

4

4

4

4

4

4

4

4

4

4

4

4

4

data-governance

4

data-provenance

4

4

4

4

4

4

4

4

4

defense-evasion

4

4

4

4

delimiter-escape

4

4

4

deserialization

4

detection-bypass

4

4

4

differential-privacy

4

differential-testing

4

4

direct-injection

4

direct-preference-optimization

4

disaster-recovery

4

document-parsing

4

4

drift-detection

4

4

4

4

4

4

4

4

4

4

4

4

4

evidence-preservation

4

4

executive-order

4

4

exploit-development

4

4

4

facial-recognition

4

4

4

4

feature-collision

4

4

4

4

4

formal-verification

4

4

4

function-schema

4

4

4

4

4

guardrails-bypass

4

4

4

hardware-security

4

4

4

4

4

4

4

4

4

4

4

4

inference-server

4

4

4

4

input-sanitization

4

4

4

instruction-tuning

4

4

4

4

inversion-attacks

4

4

4

4

4

4

knowledge-management

4

4

4

4

layered-defense

4

4

4

4

4

4

llm-vulnerabilities

4

4

4

4

long-term-memory

4

lost-in-the-middle

4

low-resource-languages

4

machine-learning

4

4

management-system

4

4

4

4

metadata-injection

4

4

4

4

4

ml-infrastructure

4

4

4

4

model-fingerprinting

4

model-lifecycle

4

model-provenance

4

4

model-snapshots

4

4

4

national-security

4

nearest-neighbor

4

4

4

online-learning

4

4

output-constraints

4

output-manipulation

4

output-validation

4

4

4

4

4

4

4

permission-escalation

4

4

persona-manipulation

4

personalization

4

4

4

4

4

4

4

4

positional-encoding

4

4

4

4

prediction-endpoints

4

preference-data

4

preference-learning

4

preference-poisoning

4

4

4

privacy-preserving

4

private-endpoints

4

program-building

4

4

4

4

project-management

4

prompt-engineering

4

prompt-hardening

4

prompt-injection-defense

4

4

prompt-template

4

4

protocol-exploitation

4

4

4

4

4

4

4

4

quality-control

4

4

4

4

4

4

reasoning-trace

4

red-team-service

4

4

4

4

4

4

4

repository-poisoning

4

4

4

4

responsible-testing

4

4

result-poisoning

4

4

retrieval-manipulation

4

4

risk-quantification

4

4

4

robustness-testing

4

4

role-escalation

4

4

4

safety-benchmarks

4

4

safety-framework

4

4

safety-monitoring

4

safety-regression

4

4

4

scalable-oversight

4

4

4

4

schema-injection

4

4

4

4

sector-specific

4

4

security-analysis

4

4

self-replicating

4

semantic-search

4

4

session-attacks

4

severity-scoring

4

4

shared-responsibility

4

4

4

4

4

4

4

4

4

4

sparse-attention

4

4

specification-gaming

4

4

4

4

4

4

4

4

steering-vectors

4

4

4

4

4

4

4

system-prompt-leak

4

4

4

4

4

4

4

4

test-time-compute

4

4

4

4

4

threat-landscape

4

4

4

4

4

token-manipulation

4

4

tool-exploitation

4

4

4

4

4

4

4

4

training-attacks

4

training-manipulation

4

4

tree-of-attacks

4

trojan-detection

4

4

4

4

4

4

4

4

4

4

video-understanding

4

4

4

4

4

4

vulnerability-assessment

4

vulnerability-disclosure

4

4

4

weight-manipulation

4

4

4

4

4

4

4

3

adversarial-audio

3

3

behavior-diffing

3

behavioral-analysis

3

3

confused-deputy

3

3

3

document-attacks

3

3

3

hidden-commands

3

3

3

modality-bridging

3

3

3

output-sanitization

3

professional-standards

3

reasoning-models

3

reinforcement-learning

3

3

retrieval-attacks

3

3

security-operations

3

similarity-search

3

3

3

vector-security