Historical milestone · 1993
Learning with malicious errors
Reviewed through September 18, 2026
1993 · Historical milestone
Learning with malicious errors
- Era
- 1990s
- Theme
- Safety, security & alignment
- Evidence form
- Analyzed PAC learning when an adversary can corrupt a fraction of examples
- School / paradigm
- Robust learning theory
- Institution / context
- AT&T Bell Laboratories / Harvard
- Researchers
- Michael Kearns; Ming Li
School of thought
Computational learning theory
Matched on representative researcher.
Learning should be defined by explicit assumptions about samples, computational resources, accuracy, confidence, and adversaries.
Critique. Worst-case abstractions may not predict empirical deep-learning behavior or open-ended environments.
Modern descendants. Generalization, robust training, benchmark design, data requirements, and formal assurance.
Understand
Plain-language record, transferred from the reviewed source module.
Theory or experimental setup. Formalized limits and possibilities of learning under worst-case data contamination.
Result / historical claim. Adversarial label-noise models are abstract and do not capture adaptive attacks on complex deployed systems.
Apply
Professional implication, only where the reviewed record states one.
The checked-in record does not state a separate professional application for this entry. The topic page places it in the wider research lineage: Safety, security, and alignment.
Verify
Evidence status, stated limitations, and the external sources this record actually carries.
Evidence form. Analyzed PAC learning when an adversary can corrupt a fraction of examples
Limitation / debate. Data poisoning, robust training, threat models, and guarantees under contaminated feedback.
Source status. The source link below is the verified link our reviewed topic research already carries for this milestone.
Reproduce
A reproduction tutorial is linked only when one exists for this exact record.
A reproduction tutorial is not yet available for this entry. The closest reviewed material is Safety, security, and alignment.
Cite or share
APA-like: This historical record carries a year only, and no author or publisher of record in the checked-in data. An APA reference would have to invent that metadata.
BibTeX: BibTeX requires an author and publication venue. Historical lineage entries store a narrative record and its source link, not structured authorship, so the field would be fabricated.
Related
Appears in AI governance becomes measurable infrastructure.