{"paper":{"title":"Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haibo Hu, Junxu Liu, Mengyu Sun, Yi Zhang, Ziyuan Yang, Zunlong Zhou","submitted_at":"2026-05-18T09:55:36Z","abstract_excerpt":"Diffusion models (DMs) are widely used for text-to-image generation, but their strong generative capabilities also raise concerns about unsafe or undesirable content. Concept erasure aims to mitigate these risks by removing specific concepts from pretrained models. However, recent studies show that such methods often suppress rather than fully eliminate target concepts, leaving models vulnerable to awakening attacks. Existing approaches primarily rely on white-box access through optimization or inversion, while concept awakening under black-box constraints remains underexplored. In this work, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18150","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.18150/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:59.093329Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.373118Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7a8cb081ae8f3d7ec07d5186a9b10cc0f7ece0420eb0b3815463e42dfd180378"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}