{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:53XIKYPQF4U224W64MYGVK5ZMV","short_pith_number":"pith:53XIKYPQ","schema_version":"1.0","canonical_sha256":"eeee8561f02f29ad72dee3306aabb9654dded087d2d2e35ece1c346da492c3a0","source":{"kind":"arxiv","id":"1811.01443","version":2},"attestation_state":"computed","paper":{"title":"SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Faiq Khalid, Hammad Tariq, Hassan Ali, Muhammad Abdullah Hanif, Muhammad Shafique, Rehan Ahmed, Semeen Rehman","submitted_at":"2018-11-04T21:54:11Z","abstract_excerpt":"In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image. We validate our technique on Convolutional DNNs against the state-of-the-art attacks from the open-source Cleverhans library using the MNIST, the CIFAR-10, and the CIFAR-100 datasets. Our experimental results show that the attack success rate, as well as the imperceptibility of the adversarial images, can be significantly reduced "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1811.01443","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-04T21:54:11Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"8e31d9cb6419f50910be674a080bc81105c4705508af0e100e95149da6266877","abstract_canon_sha256":"d664d7a0d4169a90c4a11af2640340b5a553de81e9e84a074167b0c3e0df5829"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:55.299091Z","signature_b64":"BGK9rlvtGDlAf9gc6pFAY7H5b+/AbODzgLqshKaWiri9YDq/hrzEMdgtTCWYy3QkLmx5N+/MmNq3cfVXvMRHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeee8561f02f29ad72dee3306aabb9654dded087d2d2e35ece1c346da492c3a0","last_reissued_at":"2026-07-05T01:02:55.298646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:55.298646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Faiq Khalid, Hammad Tariq, Hassan Ali, Muhammad Abdullah Hanif, Muhammad Shafique, Rehan Ahmed, Semeen Rehman","submitted_at":"2018-11-04T21:54:11Z","abstract_excerpt":"In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image. We validate our technique on Convolutional DNNs against the state-of-the-art attacks from the open-source Cleverhans library using the MNIST, the CIFAR-10, and the CIFAR-100 datasets. Our experimental results show that the attack success rate, as well as the imperceptibility of the adversarial images, can be significantly reduced "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01443","kind":"arxiv","version":2},"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/1811.01443/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.01443","created_at":"2026-07-05T01:02:55.298707+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01443v2","created_at":"2026-07-05T01:02:55.298707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01443","created_at":"2026-07-05T01:02:55.298707+00:00"},{"alias_kind":"pith_short_12","alias_value":"53XIKYPQF4U2","created_at":"2026-07-05T01:02:55.298707+00:00"},{"alias_kind":"pith_short_16","alias_value":"53XIKYPQF4U224W6","created_at":"2026-07-05T01:02:55.298707+00:00"},{"alias_kind":"pith_short_8","alias_value":"53XIKYPQ","created_at":"2026-07-05T01:02:55.298707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV","json":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV.json","graph_json":"https://pith.science/api/pith-number/53XIKYPQF4U224W64MYGVK5ZMV/graph.json","events_json":"https://pith.science/api/pith-number/53XIKYPQF4U224W64MYGVK5ZMV/events.json","paper":"https://pith.science/paper/53XIKYPQ"},"agent_actions":{"view_html":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV","download_json":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV.json","view_paper":"https://pith.science/paper/53XIKYPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01443&json=true","fetch_graph":"https://pith.science/api/pith-number/53XIKYPQF4U224W64MYGVK5ZMV/graph.json","fetch_events":"https://pith.science/api/pith-number/53XIKYPQF4U224W64MYGVK5ZMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV/action/storage_attestation","attest_author":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV/action/author_attestation","sign_citation":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV/action/citation_signature","submit_replication":"https://pith.science/pith/53XIKYPQF4U224W64MYGVK5ZMV/action/replication_record"}},"created_at":"2026-07-05T01:02:55.298707+00:00","updated_at":"2026-07-05T01:02:55.298707+00:00"}