Unverified50% confidenceFactExact time
Data poisoning occurs during the training or fine-tuning stage, where attackers mix malicious samples into the dataset, causing the model to produce erroneous behavior under specific trigger conditions.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe core principle of adversarial example attacks is to apply imperceptibly small perturbations to input data that are nearly undetectable to the human eye, causing a trained deep learning model to produce completely incorrect outputs.76% similarUnverifiedMembership inference attacks can detect data contamination via perplexity: if a model's perplexity for a given code segment is significantly lower than for code of equivalent complexity, this often indicates the segment appeared in the training set.74% similarUnverifiedResearchers can use n-gram overlap analysis and membership inference attacks to determine whether specific data appeared in a model's training set, but with the limitation of a high false positive rate.73% similarVerifiedBenchmark data contamination refers to the phenomenon where, after a test set is made public, its questions may appear in the pre-training corpora of subsequent models, causing scores to reflect memorization rather than genuine reasoning ability.73% similarUnverifiedAdversarial examples are specially crafted test inputs that cause a model to produce incorrect outputs by applying imperceptibly small perturbations to input data.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048671API
curl https://kongchang.com/api/v1/knowledge/claims/1048671MCP
get_claim(id=1048671)