Verified65% confidenceFactExact time
Differential Privacy was formally defined by Cynthia Dwork in 2006, with its core guarantee being that the output of an algorithm will not change significantly due to the addition or removal of any single record in the dataset.
3
Sources
65%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
ML安全工程师职业规划：从零开始的完整学习路径
Related Claims
UnverifiedDifferential privacy is a rigorous mathematical definition of privacy: a randomized algorithm satisfies (ε, δ)-DP if the difference in output distributions on any adjacent datasets is constrained by ε and δ; the smaller ε is, the stronger the privacy protection, but usually at the cost of degraded model utility.79% similarVerifiedDifferential privacy technology was formally proposed by Cynthia Dwork in 2006.78% similarUnverified差分隐私由Cynthia Dwork等人于2006年提出，其核心定义为P[M(D)∈S] ≤ e^ε × P[M(D')∈S]77% similarUnverifiedAccording to the leak, even under privacy frameworks such as ZDR or no-training commitments, derived data is typically carved out separately and considered to fall within fair use70% similarUnverifiedTrustedRouter positions privacy protection as its core differentiator rather than merely routing efficiency or model coverage.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/697693API
curl https://kongchang.com/api/v1/knowledge/claims/697693MCP
get_claim(id=697693)