{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NINPV75IXEUAKK4HUORB7RFPQP","short_pith_number":"pith:NINPV75I","schema_version":"1.0","canonical_sha256":"6a1afaffa8b928052b87a3a21fc4af83f15e5daf8a76fd718e15b2d7e6c63e64","source":{"kind":"arxiv","id":"2307.02055","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and their Impact","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaydip Sen, Subhasis Dasgupta","submitted_at":"2023-07-05T06:40:08Z","abstract_excerpt":"This chapter introduces the concept of adversarial attacks on image classification models built on convolutional neural networks (CNN). CNNs are very popular deep-learning models which are used in image classification tasks. However, very powerful and pre-trained CNN models working very accurately on image datasets for image classification tasks may perform disastrously when the networks are under adversarial attacks. In this work, two very well-known adversarial attacks are discussed and their impact on the performance of image classifiers is analyzed. These two adversarial attacks are the fa"},"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":"2307.02055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T06:40:08Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"4089d699783a2033304d914ce4e3f2fe3ad916c9b1bd70cb2d2418db6c38de0e","abstract_canon_sha256":"d633800cc0f03deda888652b1e1b36328648492ab5e13f9a7a46c06cc4e043e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:04.537166Z","signature_b64":"5wr0s8HIBPfIByyhVjFvpdb99hinp5i/XrKPcYulJqcU95J3f703JGpyqVrDDl/bdlaXPNBnV+A4AZloh0vYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a1afaffa8b928052b87a3a21fc4af83f15e5daf8a76fd718e15b2d7e6c63e64","last_reissued_at":"2026-07-05T06:28:04.536762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:04.536762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and their Impact","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaydip Sen, Subhasis Dasgupta","submitted_at":"2023-07-05T06:40:08Z","abstract_excerpt":"This chapter introduces the concept of adversarial attacks on image classification models built on convolutional neural networks (CNN). CNNs are very popular deep-learning models which are used in image classification tasks. However, very powerful and pre-trained CNN models working very accurately on image datasets for image classification tasks may perform disastrously when the networks are under adversarial attacks. In this work, two very well-known adversarial attacks are discussed and their impact on the performance of image classifiers is analyzed. These two adversarial attacks are the fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02055","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/2307.02055/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":"2307.02055","created_at":"2026-07-05T06:28:04.536826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02055v1","created_at":"2026-07-05T06:28:04.536826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02055","created_at":"2026-07-05T06:28:04.536826+00:00"},{"alias_kind":"pith_short_12","alias_value":"NINPV75IXEUA","created_at":"2026-07-05T06:28:04.536826+00:00"},{"alias_kind":"pith_short_16","alias_value":"NINPV75IXEUAKK4H","created_at":"2026-07-05T06:28:04.536826+00:00"},{"alias_kind":"pith_short_8","alias_value":"NINPV75I","created_at":"2026-07-05T06:28:04.536826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21163","citing_title":"Generating Adversarial Point Clouds Using Diffusion Model","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP","json":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP.json","graph_json":"https://pith.science/api/pith-number/NINPV75IXEUAKK4HUORB7RFPQP/graph.json","events_json":"https://pith.science/api/pith-number/NINPV75IXEUAKK4HUORB7RFPQP/events.json","paper":"https://pith.science/paper/NINPV75I"},"agent_actions":{"view_html":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP","download_json":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP.json","view_paper":"https://pith.science/paper/NINPV75I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02055&json=true","fetch_graph":"https://pith.science/api/pith-number/NINPV75IXEUAKK4HUORB7RFPQP/graph.json","fetch_events":"https://pith.science/api/pith-number/NINPV75IXEUAKK4HUORB7RFPQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP/action/storage_attestation","attest_author":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP/action/author_attestation","sign_citation":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP/action/citation_signature","submit_replication":"https://pith.science/pith/NINPV75IXEUAKK4HUORB7RFPQP/action/replication_record"}},"created_at":"2026-07-05T06:28:04.536826+00:00","updated_at":"2026-07-05T06:28:04.536826+00:00"}