Longterm Wiki

Adversarial Robustness

Redwood ResearchResearch Areasadversarial-robustness

Record Metadata

Record Keyadversarial-robustness
EntityRedwood Research
CollectionResearch Areas(2 records total)
SchemaMajor research initiatives and focus areas.
YAML Filepackages/kb/data/things/dwMzc9WzPa.yaml

Fields

NameAdversarial Robustness
DescriptionTesting and improving robustness of AI safety techniques against adversarial inputs
StartedJun 2021
NotesEarly work on adversarial training for harmlessness classifiers

Other Records in Research Areas (1)

KeyNameDescriptionStarted
ai-controlAI ControlDeveloping techniques to safely deploy AI systems even if they are not fully alignedJan 2023
Record: adversarial-robustness | Longterm Wiki