category

AI Risks

Common risks that can happen when AI systems are built, deployed, or used.

Showing 1501-1520 of 1686 records

Adversarial attack

Adversarial attack is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant during 3 - Other.

Privacy violations

Privacy violations is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It...

Misuse tactics to compromise GenAI systems (Model integrity)

Misuse tactics to compromise GenAI systems (Model integrity) is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or corr...

Strategic underperformance on model evaluations

Strategic underperformance on model evaluations is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in c...

Adversarial Prompts

Adversarial Prompts is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant during 2 - Po...

Direct Harm Domains (societal harm)

Direct Harm Domains (societal harm) is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.

6.3 > Economic and cultural devaluation of human effort AI Risks

6.3 > Economic and cultural devaluation of human effort groups 30 AI risk records under 6. Socioeconomic and Environmental.

Targeting & Personalisation

Targeting & Personalisation is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, and targeted manipulation. It is most relevant durin...

Weapons acquisition

Weapons acquisition is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is most relevan...

Authoritarian Surveillance, Censorship, and Use: Authoritarian Surveillance and Targeting of Citizens

Authoritarian Surveillance, Censorship, and Use: Authoritarian Surveillance and Targeting of Citizens is an AI risk in 4. Malicious Actors & Misuse focused o...

Security

Security is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant during 1 - Pre-deployment.

Faithfulness Errors

Faithfulness Errors is an AI risk in 3. Misinformation focused on 3.1 > False or misleading information. It is most relevant during 3 - Other.

Leading users to perform unethical or illegal actions

Leading users to perform unethical or illegal actions is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe use. It is most...

User Intent

User Intent is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.

Generation of illegal or harmful content

Generation of illegal or harmful content is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most relevant during...

Trust

Trust is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe use. It is most relevant during 2 - Post-deployment.

Risk of Harm through Anthropomorphic AI Assistant Design

Risk of Harm through Anthropomorphic AI Assistant Design is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe use. It is m...

Future access risks

Future access risks is an AI risk in 6. Socioeconomic and Environmental focused on 6.1 > Power centralization and unfair distribution of benefits. It is most...

Secondary use

Secondary use is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It is mo...

Harmful Content Generation at Scale: Non-Consensual Content

Harmful Content Generation at Scale: Non-Consensual Content is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, and targeted manipul...