Skip to main content
MIT AI Risk Initiative
BackFine-tuning related (Harmful fine-tuning of open-weights models)
Home/Risks/Gipiškis2024/Fine-tuning related (Harmful fine-tuning of open-weights models)
Fine-tuning related (Unexpected competen…
Fine-tuning related (Fine-tuning dataset…

Fine-tuning related (Harmful fine-tuning of open-weights models)

Sub-category
Risk Domain
4Malicious Actors & Misuse
4.2Cyberattacks, weapon development or use, and mass harm

Using AI systems to develop cyber weapons (e.g., by coding cheaper, more effective malware), develop new or enhance existing weapons (e.g., Lethal Autonomous Weapons or chemical, biological, radiological, nuclear, and high-yield explosives), or use weapons to cause mass harm.

"Models with publicly available weights can be fine-tuned for harmful activities by bad actors, using significantly fewer resources (in terms of time and money) compared to the original training cost [115, 78]."(p. 14)

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 Gipiškis2024 (144)

Direct Harm Domains (content safety harms)

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Violence and extremism

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Hate and toxicity

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Sexual content

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Child harm

1.2 Exposure to toxic content
Not codedNot codedNot coded

Direct Harm Domains (content safety harms) > Self-harm

1.2 Exposure to toxic content
Not codedNot codedNot coded
View all 144 risks from this paper →