archive

All Records

AI security records indexed from public vulnerability, risk, and attack datasets.

Showing 961-980 of 3706 records

Building an AI able to adapt to humans

Building an AI able to adapt to humans is an AI risk in 6. Socioeconomic and Environmental focused on 6.2 > Increased inequality and decline in employment qu...

Privacy protection

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

Building a human-AI environment

Building a human-AI environment is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with hum...

Human-AI interaction

Human-AI interaction is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe use. It is most relevant during 3 - Other.

Uniformity in the AI field

Uniformity in the AI field is an AI risk in 6. Socioeconomic and Environmental focused on 6.1 > Power centralization and unfair distribution of benefits. It...

Threats to human institutions and life

Threats to human institutions and life is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm...

Balancing AI's risks

Balancing AI's risks is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most relevant dur...

Algorithm and data

Algorithm and data is an AI risk in 1. Discrimination & Toxicity focused on 1.1 > Unfair discrimination and misrepresentation. It is most relevant during 1 -...

Design of AI

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

Sexual Content

Sexual Content is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most relevant during 2 - Post-deployment.

Nonviolent Crimes

Nonviolent Crimes is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most relevant during 2 - Post-deployment.

Hate

Hate is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most relevant during 2 - Post-deployment.

Nonphysical Hazards

Nonphysical Hazards is an AI risk focused on X.1 > Excluded. It is most relevant during 2 - Post-deployment.

Suicide & Self-Harm

Suicide & Self-Harm is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most relevant during 2 - Post-deployment.

Driving opinion manipulation

Driving opinion manipulation is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale. It is most...

Eroding trust and undermining shared knowledge

Eroding trust and undermining shared knowledge is an AI risk in 3. Misinformation focused on 3.2 > Pollution of information ecosystem and loss of consensus r...

Entrenching specific ideologies

Entrenching specific ideologies is an AI risk in 3. Misinformation focused on 3.2 > Pollution of information ecosystem and loss of consensus reality. It is m...

Weaponised misinformation agents

Weaponised misinformation agents is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale. It is m...

Degraded and homogenised information environments

Degraded and homogenised information environments is an AI risk in 3. Misinformation focused on 3.2 > Pollution of information ecosystem and loss of consensu...

Entrenched viewpoints and reduced political efficacy

Entrenched viewpoints and reduced political efficacy is an AI risk in 3. Misinformation focused on 3.2 > Pollution of information ecosystem and loss of conse...