{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/robustified-anns-reveal-wormholes-between","title":"Robustified ANNs Reveal Wormholes Between Human Category Percepts","arxiv_id":"2308.06887","date":"2023-08-14","proceeding":null,"authors":["Guy Gaziv","Michael J. Lee","James J. DiCarlo"],"abstract":"The visual object category reports of artificial neural networks (ANNs) are notoriously sensitive to tiny, adversarial image perturbations. Because human category reports (aka human percepts) are thought to be insensitive to those same small-norm perturbations -- and locally stable in general -- this argues that ANNs are incomplete scientific models of human visual perception. Consistent with this, we show that when small-norm image perturbations are generated by standard ANN models, human object category percepts are indeed highly stable. However, in this very same \"human-presumed-stable\" regime, we find that robustified ANNs reliably discover low-norm image perturbations that strongly disrupt human percepts. These previously undetectable human perceptual disruptions are massive in amplitude, approaching the same level of sensitivity seen in robustified ANNs. Further, we show that robustified ANNs support precise perceptual state interventions: they guide the construction of low-norm image perturbations that strongly alter human category percepts toward specific prescribed percepts. These observations suggest that for arbitrary starting points in image space, there exists a set of nearby \"wormholes\", each leading the subject from their current category perceptual state into a semantically very different state. Moreover, contemporary ANN models of biological visual processing are now accurate enough to consistently guide us to those portals.","url_abs":"https://arxiv.org/abs/2308.06887v2","url_pdf":"https://arxiv.org/pdf/2308.06887v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robustified-anns-reveal-wormholes-between","repo_url":"https://github.com/ggaziv/wormholes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.06887","atlas_url":"https://app.syntology.ai/?focus=2308.06887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06887"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/ggaziv/Wormholes","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ggaziv/wormholes","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"078da01e51a28471","entry":"add_args_to_parser","repo":"ggaziv/Wormholes","repo_kind":"official","path":"wormholes/defaults.py","file_url":"https://github.com/ggaziv/Wormholes/blob/HEAD/wormholes/defaults.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"078da01e51a28471"}},{"code_sha256_prefix":"3b26d6ebbd9142b2","entry":"alexnet","repo":"ggaziv/Wormholes","repo_kind":"official","path":"wormholes/imagenet_models/alexnet.py","file_url":"https://github.com/ggaziv/Wormholes/blob/HEAD/wormholes/imagenet_models/alexnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b26d6ebbd9142b2"}},{"code_sha256_prefix":"85c4757ab3246b61","entry":"densenet121","repo":"ggaziv/Wormholes","repo_kind":"official","path":"wormholes/imagenet_models/densenet.py","file_url":"https://github.com/ggaziv/Wormholes/blob/HEAD/wormholes/imagenet_models/densenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85c4757ab3246b61"}},{"code_sha256_prefix":"6b70762b5419b176","entry":"densenet161","repo":"ggaziv/Wormholes","repo_kind":"official","path":"wormholes/imagenet_models/densenet.py","file_url":"https://github.com/ggaziv/Wormholes/blob/HEAD/wormholes/imagenet_models/densenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6b70762b5419b176"}},{"code_sha256_prefix":"019686268f24b3b5","entry":"densenet169","repo":"ggaziv/Wormholes","repo_kind":"official","path":"wormholes/imagenet_models/densenet.py","file_url":"https://github.com/ggaziv/Wormholes/blob/HEAD/wormholes/imagenet_models/densenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"019686268f24b3b5"}},{"code_sha256_prefix":"0b37f66b062a0e55","entry":"get_restricted_imagenet_mapped_model","repo":"ggaziv/Wormholes","repo_kind":"official","path":"wormholes/model_utils.py","file_url":"https://github.com/ggaziv/Wormholes/blob/HEAD/wormholes/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b37f66b062a0e55"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}