Poisoning Attacks
AI Risk"Poisoning attacks [143] could influence the behavior of the model by making small changes to the training data. A number of efforts could even leverage data poisoning techniques to implant hidden triggers into models during the training process (i.e., backdoor attacks). Many kinds of triggers in text corpora (e.g., characters, words, sentences, and syntax) could be used by the attackers.""
Overview
A source-backed snapshot of this AI risk.
Risk profile
How the MIT AI Risk Repository categorizes this risk.
Merged risk records
Source records unified into this canonical risk concept.
MITRISK-Cui2024-02.10.03 - Poisoning Attacks
"Poisoning attacks [143] could influence the behavior of the model by making small changes to the training data. A number of efforts could even leverage data poisoning techniques to implant hidden triggers into models during the training process (i.e., backdoor attacks). Many kinds of triggers in text corpora (e.g., characters, words, sentences, and syntax) could be used by the attackers.""
MITRISK-Liu2024-30.07.04 - Poisoning Attacks
fool the model by manipulating the training data, usually performed on classification models
Mitigations
Defenses that may help with related attacks.
Showing 4 of 10
Source evidence
Research source for this risk, when available.
Included resource
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.