Skip to main content
MIT AI Risk Initiative
BackRisks from models and algorithms (Risks of adversarial attack)
Home/Risks/National Technical Committee 260 on Cybersecurity (TC260) (2024)/Risks from models and algorithms (Risks of adversarial attack)
Risks from models and algorithms (Risks …
Risks from data (Risks of illegal collec…

Risks from models and algorithms (Risks of adversarial attack)

AI Safety Governance Framework

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

Source
Sub-category
Risk Domain
2.2AI system security vulnerabilities and attacks

Vulnerabilities that can be exploited in AI systems, software development toolchains, and hardware, resulting in unauthorized access, data and privacy breaches, or system manipulation causing unsafe outputs or behavior.

"Attackers can craft well-designed adversarial examples to subtly mislead, influence, and even manipulate AI models, causing incorrect outputs and potentially leading to operational failures."(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 data (Risks of illegal collection and use of data)

2.1 Compromise of privacy by leaking or correctly inferring sensitive information
HumanOtherOther
View all 25 risks from this paper →