AI Risks

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 3 - Other.

2.2 > AI system security vulnerabilities and attacks AI Risks

2.2 > AI system security vulnerabilities and attacks groups 108 AI risk records under 2. Privacy & Security.

Information Security

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

Evasion Attacks

Evasion Attacks 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-de...

Risks to privacy

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

Adversarial input

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

7.3 > Lack of capability or robustness AI Risks

7.3 > Lack of capability or robustness groups 114 AI risk records under 7. AI System Safety, Failures, & Limitations.

Model weight leak

Model weight leak is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant during 2 - Post...

Extraction attack

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

Compromising privacy by leaking private infiormation

Compromising privacy by leaking private infiormation is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly in...

Attribute inference attack

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

Misuse of interpretability techniques

Misuse of interpretability techniques is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most rele...

Multi-step Jailbreaks

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

Generative AI Outputs

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

Technical vulnerabilities (Robustness - vulnerability to jailbreaking

Technical vulnerabilities (Robustness - vulnerability to jailbreaking is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilit...

Steganography

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

Factual Errors Injected by External Tools

Factual Errors Injected by External Tools is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most...

Text encoding-based attacks

Text encoding-based attacks is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant durin...

Creating avenues for exploiting user trust, nudging or manipulation

Creating avenues for exploiting user trust, nudging or manipulation is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe u...

Extraction Attacks

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