There are 15 attacks in the academic-exploitation category. Each shows its technique id, mode, standards mapping, description, and the exact command to run it (swap the provider and target as needed).
​
Research Fabrication
critical
research-fabrication · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Fabricates research data, results, and findings to support predetermined conclusionsRun it:
ai-blackteam run -p anthropic -a research-fabrication -t "your target prompt"
​
Academic Fraud Impersonation
high
academic-fraud-impersonation · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Impersonates professors, academic institutions, or credentials to deceive students, employers, or peer reviewersRun it:
ai-blackteam run -p anthropic -a academic-fraud-impersonation -t "your target prompt"
​
Academic Sabotage
high
academic-sabotage · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Sabotages competitors’ academic work, research, or careers through deceptive or harmful actionsRun it:
ai-blackteam run -p anthropic -a academic-sabotage -t "your target prompt"
​
Admission Fraud
high
admission-fraud · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Assists with fraudulent college or graduate school admission activities including fake essays and false credentialsRun it:
ai-blackteam run -p anthropic -a admission-fraud -t "your target prompt"
​
Citation Fraud
high
citation-fraud · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Creates fake citations, citation rings, or fabricated references to inflate academic credibilityRun it:
ai-blackteam run -p anthropic -a citation-fraud -t "your target prompt"
​
Credential Fraud
high
credential-fraud · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Creates or assists in creating fake academic credentials, degrees, and transcriptsRun it:
ai-blackteam run -p anthropic -a credential-fraud -t "your target prompt"
​
Exam Cheating
high
exam-cheating · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Assists students in cheating on exams by providing answers, cheat sheets, or real-time solutionsRun it:
ai-blackteam run -p anthropic -a exam-cheating -t "your target prompt"
​
Grant Fraud
high
grant-fraud · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Assists in creating fraudulent grant applications with fabricated preliminary data or false qualificationsRun it:
ai-blackteam run -p anthropic -a grant-fraud -t "your target prompt"
​
Peer Review Manipulation
high
peer-review-manipulation · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Manipulates the academic peer review process through fake reviewers, biased reviews, or review ringsRun it:
ai-blackteam run -p anthropic -a peer-review-manipulation -t "your target prompt"
​
Plagiarism Assistance
high
plagiarism-assistance · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Helps students plagiarize academic content while evading plagiarism detection toolsRun it:
ai-blackteam run -p anthropic -a plagiarism-assistance -t "your target prompt"
​
Standardized Test Cheating
high
standardized-test-cheat · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Assists in cheating on standardized tests like SAT, GRE, MCAT, bar exam, or professional certificationsRun it:
ai-blackteam run -p anthropic -a standardized-test-cheat -t "your target prompt"
​
Student Profiling
high
student-profiling · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Builds discriminatory profiles of students based on protected characteristics to influence academic outcomesRun it:
ai-blackteam run -p anthropic -a student-profiling -t "your target prompt"
​
Thesis Fraud
high
thesis-fraud · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Writes entire theses or dissertations for students to submit as their own original scholarly workRun it:
ai-blackteam run -p anthropic -a thesis-fraud -t "your target prompt"
​
Essay Ghostwriting
medium
essay-ghostwriting · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Writes academic essays for students to submit as their own work, enabling academic dishonestyRun it:
ai-blackteam run -p anthropic -a essay-ghostwriting -t "your target prompt"
​
Homework Automation
medium
homework-automation · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Automates homework completion at scale for contract cheating services or personal academic fraudRun it:
ai-blackteam run -p anthropic -a homework-automation -t "your target prompt"