Unverified70% confidenceFactExact time
The concept of adversarial examples was first systematically articulated by Ian Goodfellow et al. in 2014, demonstrating that adding imperceptibly small perturbations to images in the computer vision domain can cause classifiers to produce incorrect judgments.
2
Sources
70%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedAfter superimposing tiny perturbations that are nearly invisible to the human eye onto an image correctly classified by a neural network, the model output will produce an error with extremely high confidence.75% similarUnverifiedAI可见性仪表盘用有限的预设问题推断整体可见性，存在极大的采样偏差74% similarUnverifiedAdversarial sample attacks can add noise to images that is nearly imperceptible to the human eye yet causes models to produce incorrect classifications73% similarUnverifiedVisual reasoning benchmarks that have emerged in recent years began introducing compositionality, counterfactuals, and distractor designs, for example mixing similar objects into counting tasks and adding mirror confusion to spatial relation judgments.71% similarUnverified对抗样本（Adversarial Examples）概念由Szegedy等人于2013年在图像识别领域首次系统性提出71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/832012API
curl https://kongchang.com/api/v1/knowledge/claims/832012MCP
get_claim(id=832012)