hypothesis
active
hypothesis:superposition-may-be-a-major-contributing-factor-or-even-the-primary-cause-of-adversarial-examplesSuperposition may be a major contributing factor, or even the primary cause, of adversarial examples.
Hypothesis under test.
Source paper
extracted_from(2025) · Gorton, Liv · Lewis, Owen
Neighborhood — ranked by edge-count
Papers (1)
paper
- Adversarial Examples Are Not Bugs, They Are Superpositionmentionssupports
Claims (1)
claim
- Central thesis.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Superposition maximalist stance.
- Supported by Table 1.
- Adversarial example transfer may be predicted by correlated arrangement of features in superpositionhypothesis0.846Speculative.
- Discussion implication.
- superposition is deeply linked to the ability to identify and enumerate over all features in a modelquote0.800Safety rationale.
- Novelty claim.
- Core mechanism statement.
- Explains robust models being more robust than expected.