{"data":{"event":{"id":"765dbcf7-9650-423b-af5c-ad242283c97c","slug":"do-influence-derived-data-perturbations-enable-machine-unlearning-a-cont-171aa4beb1","title":"Do Influence-Derived Data Perturbations Enable Machine Unlearning? A Controlled Study of Three Plausible Roles","short_summary":"arXiv:2609.12313v1 Announce Type: new \nAbstract: We evaluate Deep Perturbation Learning (DPL), which perturbs training images and labels along influence-derived directions, in three roles in which prior work has positioned it for machine unlearning: a direct deletion signal (the strongest claim), a utility-preserving regularizer, and a warm start for adversarial unlearning. Evidence for the weaker roles has been used to support the stronger one, so we test each role separately under a matched protocol with exact-seed retraining baselines. An audit of the public implementation identifies two co","full_description":"arXiv:2609.12313v1 Announce Type: new \nAbstract: We evaluate Deep Perturbation Learning (DPL), which perturbs training images and labels along influence-derived directions, in three roles in which prior work has positioned it for machine unlearning: a direct deletion signal (the strongest claim), a utility-preserving regularizer, and a warm start for adversarial unlearning. Evidence for the weaker roles has been used to support the stronger one, so we test each role separately under a matched protocol with exact-seed retraining baselines. An audit of the public implementation identifies two correctness issues: image directions are computed on augmented, normalized tensors but applied to raw images, and the label perturbation falls below float32 resolution, leaving labels unchanged. After correcting the image-perturbation pipeline, DPL fails the direct-deletion criterion on CIFAR-10/ResNet-18 in all three paired seeds. Its utility effects are inconsistent in sign across seeds, and once direction-computation time is counted it underperforms simple warm-start baselines. A one-seed Tiny ImageNet check likewise does not favor DPL as a regularizer or warm start; preprocessing inconsistencies in the released code make the direct comparison there inconclusive. These results cover random instance deletion only and do not rule out influence-based methods in other deletion regimes. We release a role-matched evaluation protocol and an audit checklist for perturbation-based deletion claims.","ledger_type":"benefit","primary_domain_id":"8f1af1b9-7302-4b51-aae9-fdfac04d158a","event_status":"provisional","event_date":"2026-09-14T00:00:00.000Z","discovery_date":"2026-09-14T00:00:00.000Z","first_published_date":"2026-09-14T00:00:00.000Z","last_reviewed_date":"2026-09-14T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.1000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.001000","confidence_level":"low","score_explanation":"Auto-published from news ingest as a provisional placeholder. Score is conservative until a named release is identified and the record is rescored.","methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","original_methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","published_at":"2026-09-14T04:00:51.917Z","created_at":"2026-09-14T04:00:51.917Z","updated_at":"2026-09-14T04:00:51.917Z","flags":[],"domain_name":"Biology","domain_slug":"biology","methodology_version":"0.1"},"contributions":[{"id":"ded58c28-283b-419b-a172-797913f38729","event_id":"765dbcf7-9650-423b-af5c-ad242283c97c","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.001000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-14T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-14T04:00:51.926Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"c2e05c5b-c4ed-418c-9c89-7b4cd8903073","event_id":"765dbcf7-9650-423b-af5c-ad242283c97c","url":"https://arxiv.org/abs/2609.12313","canonical_url":"https://arxiv.org/abs/2609.12313","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-14T00:00:00.000Z","retrieved_at":"2026-09-14T04:00:51.932Z","title":"Do Influence-Derived Data Perturbations Enable Machine Unlearning? A Controlled Study of Three Plausible Roles","excerpt":"arXiv:2609.12313v1 Announce Type: new \nAbstract: We evaluate Deep Perturbation Learning (DPL), which perturbs training images and labels along influence-derived directions, in three roles in which prior work has positioned it for machine unlearning: a direct deletion signal (the strongest claim), a utility-preserving regularizer, and a warm start for adversarial unlearning. Evidence for the weaker roles has been used to support the stronger one, so we test each role separately under a matched pr","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-14T04:00:51.932Z"}],"claims":[{"id":"759f5a70-c9b6-4f34-9d65-caf751a8c107","event_id":"765dbcf7-9650-423b-af5c-ad242283c97c","claim_text":"Do Influence-Derived Data Perturbations Enable Machine Unlearning? A Controlled Study of Three Plausible Roles","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-14T04:00:51.939Z","updated_at":"2026-09-14T04:00:51.939Z"}],"revisions":[{"id":"9906d460-3779-4380-8de9-98272426d1c2","event_id":"765dbcf7-9650-423b-af5c-ad242283c97c","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-14T04:00:51.946Z"}],"secondary":[]},"methodology_version":"0.1"}