Skip to main content
MIT AI Risk Initiative
BackRisks from data (Risks of improper content and poisoning in training data)
Home/Risks/National Technical Committee 260 on Cybersecurity (TC260) (2024)/Risks from data (Risks of improper content and poisoning in training data)
Risks from data (Risks of illegal collec…
Risks from data (Risks of unregulated tr…

Risks from data (Risks of improper content and poisoning in training data)

AI Safety Governance Framework

National Technical Committee 260 on Cybersecurity (TC260) (2024)

Source
Sub-category
Risk Domain
1Discrimination & Toxicity
1.2Exposure to toxic content

AI that exposes users to harmful, abusive, unsafe or inappropriate content. May involve providing advice or encouraging action. Examples of toxic content include hate speech, violence, extremism, illegal acts, or child sexual abuse material, as well as content that violates community norms such as profanity, inflammatory political speech, or pornography.

"If the training data includes illegal or harmful information, such as false, biased, or IPR-infringing content, or lacks diversity in its sources, the output may include harmful content like illegal, malicious, or extreme information. Training data is also at risk of being poisoned through tampering, error injection, or misleading actions by attackers. This can interfere with the model's probability distribution, reducing its accuracy and reliability."(p. 7)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Other risks from National Technical Committee 260 on Cybersecurity (TC260) (2024) (25)

Risks from models and algorithms (Risks of explainability)

7.4 Lack of transparency or interpretability
AI systemUnintentionalOther

Risks from models and algorithms (Risks of bias and discrimination)

1.1 Unfair discrimination and misrepresentation
HumanOtherPre-deployment

Risks from models and algorithms (Risks of robustness)

7.3 Lack of capability or robustness
AI systemOtherPost-deployment

Risks from models and algorithms (Risks of stealing and tampering)

2.2 AI system security vulnerabilities and attacks
OtherOtherOther

Risks from models and algorithms (Risks of unreliable output)

3.1 False or misleading information
AI systemUnintentionalPost-deployment

Risks from models and algorithms (Risks of adversarial attack)

2.2 AI system security vulnerabilities and attacks
HumanIntentionalPost-deployment
View all 25 risks from this paper →