{"as_of":"2026-08-13T23:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a580934761d1d3352d9b3677067dd8a6380f67958c0049fed0515b72b63da7eb","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T00:21:52.486049Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.07750/citation-record","integrity":"/paper/2608.07750/integrity","json":"/paper/2608.07750/citation-record.json","paper":"/paper/2608.07750"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.168412Z","title":"Object detection in 20 years: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.168412Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:2156c2d10de83549032670cf207f430b1e624492c1022ce54bda0723763a2d73","observation_id":"3803f8a1-5231-402d-8f2f-d2cef80e0a8a","resolution":{"observed_at":"2026-08-11T00:21:52.168412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.176566Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.176566Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:e1f54a6a65fa8d1dce637c764953f595b784b06f354e9302be1b644e7d93af66","observation_id":"1346b2b6-4cf7-492f-98c6-67cdec013818","resolution":{"observed_at":"2026-08-11T00:21:52.176566Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.542346Z","title":"Adversarial objectness gradient attacks in real- time object detection systems,","venue":null,"work_id":"5468c37f-8f09-4256-a731-b9a249e7160a","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.183676Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:4b7265cdfe8af32b3ab6bc1dff40b65766d5d7584523de44d5d8d01234240a9d","observation_id":"4c18d666-bc7e-42c8-9c57-1b1822f57a7d","resolution":{"observed_at":"2026-08-11T00:21:53.550750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.507897Z","title":"Adversarial training for free!","venue":null,"work_id":"82704a87-a5c9-4e02-8114-02fd06aba977","year":2019},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.195316Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:0de2b72a4cc2681de9f62e8803e3b12047e15e02ef3e4fce7f7aae3835d9974b","observation_id":"27442dc1-22f5-4950-acee-3b6c1d718509","resolution":{"observed_at":"2026-08-11T00:21:53.516402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.472332Z","title":"{PatchCURE}: Improving certifiable robustness, model utility, and computation effi- ciency of adversarial patch defenses,","venue":null,"work_id":"b2999a95-3603-424e-aff7-5dba43ad9769","year":2024},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.209449Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:0dfbaf81f3025338d3005c15ce465b3d923c22104878f0efb939d246eae72254","observation_id":"82b90fac-0f0b-49aa-89f1-e388f9ac17e9","resolution":{"observed_at":"2026-08-11T00:21:53.478999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.448324Z","title":"PatchCleanser: Certifiably robust defense against adversarial patches for any image classifier,","venue":null,"work_id":"8c07aeb1-f34d-474f-9c00-5247b9218903","year":2022},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.217025Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:728454bd96a5023e1c37999432154bc0700d8ced4cac58e90ab78ede645ba8c8","observation_id":"b50805c5-26e7-47ea-9234-db9b9cc9c149","resolution":{"observed_at":"2026-08-11T00:21:53.457734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.420482Z","title":"Compression to the rescue: Defending from adversarial attacks across modalities,","venue":null,"work_id":"8825ffdb-be9d-41fa-b655-3229ebe8e043","year":2018},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.234649Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:0148713c81bce0b118a9c25054af5e637c2f27e501d0bd43333054942d2ce8dd","observation_id":"dd69b589-a0e9-4bff-8910-d2db64c7d4cc","resolution":{"observed_at":"2026-08-11T00:21:53.428504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.397736Z","title":"Detecting adversarial perturbations in multi-task perception,","venue":null,"work_id":"b7ab7bb4-b837-4c7c-99f6-feb96eba6c36","year":2022},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.245723Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:db5afbcd40bb1d727637c39c8232f7c1652fbb659a2b91943cd64a809b48679a","observation_id":"7f1fa289-933c-4afc-b17e-ec7d391dce97","resolution":{"observed_at":"2026-08-11T00:21:53.405121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.367900Z","title":"Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges,","venue":null,"work_id":"43a1fc7f-23c9-49d1-a3dc-beb5e06312d8","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.252741Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:fdcd926baef331a97215e861d3d7e2c1a6f1777e3085d435e241d1047a8dfd2c","observation_id":"2226b2f8-dcac-41f9-8e72-527da171e408","resolution":{"observed_at":"2026-08-11T00:21:53.378354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.258717Z","title":"A survey on 3d object detection methods for autonomous driving applications,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.258717Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:7c40b3ee73d02ad2b619ddafbd8982d48796d45bed58350952227cb3fccf7f39","observation_id":"f7724b3b-51a5-4978-ac02-532f852b08ad","resolution":{"observed_at":"2026-08-11T00:21:52.258717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.320587Z","title":"Joint 3d instance segmentation and object detection for autonomous driving,","venue":null,"work_id":"a8d836d9-7d68-438b-b7bc-78428703e9b9","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.266896Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:d84e0738e90ba4caa07c0e2174faffca48c61eb3f79da3159e0dc95d264790ce","observation_id":"cbb33c70-5f47-4370-b5f4-222b49efa30a","resolution":{"observed_at":"2026-08-11T00:21:53.327593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.09824","last_updated":"2020-11-19T13:56:58Z","snapshot_observed_at":"2026-08-10T18:07:34.433315Z","submitted_at":"2020-11-19T13:56:58Z","title":"Multi-Task Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2011.09824","doi":null,"metadata_source":"pith","pith_arxiv_id":"2011.09824","snapshot_observed_at":"2026-08-11T00:21:52.624263Z","title":"Multi-Task Adversarial Attack","venue":"cs.LG","work_id":"d396fa4e-7eb9-4dfd-915a-5932a975917a","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.273240Z"},"links":{"cited_paper":"/paper/2011.09824","citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:db8b12c17658b0c5473c74225a2b2fe0be093df6a204467ffe065b1a7cd57530","observation_id":"35f1e97e-bc55-4599-bdcc-a586075a5392","resolution":{"observed_at":"2026-08-11T00:21:52.634197Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.301673Z","title":"Real-time memory efficient multitask learning model for autonomous driving,","venue":null,"work_id":"9dc1db6e-89cd-42f4-96d5-2311769f9580","year":2023},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.281773Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:5f5b7ec0122a5d419ad59a007d7be2d6e67a6e2cde4e150420a5d6b90ba1715e","observation_id":"aac4fc04-9993-4e2c-af21-47abb5708c50","resolution":{"observed_at":"2026-08-11T00:21:53.307349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.271665Z","title":"Multitask learning,","venue":null,"work_id":"c800007c-cc91-4a13-b6f7-29192b3dcc62","year":1997},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.289756Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:2812ab1e4338865dc55a18257ed71871f217a0a97e15dcc7583ac1963544d0ed","observation_id":"38754caa-da34-4881-a562-57340e75baad","resolution":{"observed_at":"2026-08-11T00:21:53.281585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.247734Z","title":"Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory,","venue":null,"work_id":"8e639c8b-b830-404d-9359-a423f3d35e52","year":2017},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.298310Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:7bced137864cf8ac5d994181a5a1182a4d0f426f69508f79c035a86d18fd4975","observation_id":"ff48f7ac-c548-4105-83b3-3a596b526093","resolution":{"observed_at":"2026-08-11T00:21:53.255520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.223126Z","title":"Fully- adaptive feature sharing in multi-task networks with applications in person attribute classification,","venue":null,"work_id":"e25cf0ff-429f-46d3-82b5-f0e3ef6cf9f5","year":2017},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.307215Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:fd5e75e10e246c2c93762dfbea684a5dc522182b9b78880ddddc003e0198e813","observation_id":"f9cc6cc0-6dff-40bf-8173-3c86ee6b9cc2","resolution":{"observed_at":"2026-08-11T00:21:53.231817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.201152Z","title":"Adversarial examples for semantic segmentation and object detection,","venue":null,"work_id":"a74cfa9c-890e-4475-865e-f6994fd4a4a6","year":2017},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.313240Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:e4aedf01bd735868a73ff4b843f22ebec44adfe86245f98e6d201d712b8b76be","observation_id":"7ccdb898-4768-48c5-95b5-524c3946f000","resolution":{"observed_at":"2026-08-11T00:21:53.208255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-11T00:21:52.320466Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.320466Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:baf8c3946295709025de0b6fda1a3323d291ab8a379a97921f919520de44eae8","observation_id":"11ab3aba-a982-42c8-ac1a-fe6f3e0a749d","resolution":{"observed_at":"2026-08-11T00:21:52.320466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.176063Z","title":"A novel industrial intrusion detection method based on threshold-optimized cnn-bilstm-attention using roc curve,","venue":null,"work_id":"998bd503-b809-4e59-b26c-48a132e72f0c","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.333811Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:c5a1f46304ad39968fd01737efb09f5770508a164f4e5e97be6c8b582e31bc4f","observation_id":"abb98b8d-15d2-49ad-9c97-a748bddad590","resolution":{"observed_at":"2026-08-11T00:21:53.183796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.143054Z","title":"Adversarial robustness in multi-task learning: Promises and illusions,","venue":null,"work_id":"f306068d-062f-44f2-b02b-278ba076a56a","year":2022},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.339592Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:e66c4168bf45084f141b29f91bdf0d974bfe7b01699a84241393dbc34c607184","observation_id":"20bfc2c5-951a-4c99-86bc-24ca53d26e63","resolution":{"observed_at":"2026-08-11T00:21:53.152295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.120140Z","title":"Bdd100k Model Zoo,","venue":null,"work_id":"92a0c4ad-cef5-4568-ba5f-20e8486ee591","year":2021},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.346216Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:53bf066fe7838e62afc21b416eefb2cbb43928dc55be68a9b1917dff667c9aba","observation_id":"195a68d3-fa07-46db-b2e9-435d767bbd2e","resolution":{"observed_at":"2026-08-11T00:21:53.127068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.07155","last_updated":"2019-06-17T17:58:12Z","snapshot_observed_at":"2026-08-03T13:01:27.142233Z","submitted_at":"2019-06-17T17:58:12Z","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.07155","snapshot_observed_at":"2026-08-11T00:21:52.352988Z","title":"MMDetection: Open mmlab detection toolbox and benchmark,","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.352988Z"},"links":{"cited_paper":"/paper/1906.07155","citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:7fbe3b932675adf7ff91c02f6e634a840167036cf72747640b1359fd0061b397","observation_id":"e0bb81b9-8ef1-4014-8c4e-4b573dc4881d","resolution":{"observed_at":"2026-08-11T00:21:52.352988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.095304Z","title":"Adversarially-aware robust object detector,","venue":null,"work_id":"159b31b1-f55f-464e-8f50-9815cf95f0a7","year":2022},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.359596Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:a3447a47a355f4860d88159bf1d5d6aa149cbf337586d44fe972972c2076fc57","observation_id":"f40b163b-5aab-447c-87fe-62f53ad0f8e7","resolution":{"observed_at":"2026-08-11T00:21:53.103254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02136","last_updated":"2018-10-03T07:32:57Z","snapshot_observed_at":"2026-08-02T06:41:33.803920Z","submitted_at":"2016-10-07T04:06:01Z","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02136","snapshot_observed_at":"2026-08-11T00:21:52.367035Z","title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.367035Z"},"links":{"cited_paper":"/paper/1610.02136","citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:ca1140fb626ce7d58792f3260cfd8f2d7b419045ffbf04b6d54b8f48d0a7dfdb","observation_id":"2ea7d87d-6c9b-4cac-89b1-b8eadd49ec1f","resolution":{"observed_at":"2026-08-11T00:21:52.367035Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.070732Z","title":"Detection based defense against adversarial examples from the steganalysis point of view,","venue":null,"work_id":"a0474c33-ad81-4a8d-a194-609e8b4d381b","year":2019},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.374754Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:118f539ca49521fbd99651c7061b31d81c1eba0e7e4fbdedb69a03753bbf88ea","observation_id":"16c8a98a-b241-48af-9a9c-7d7516857c00","resolution":{"observed_at":"2026-08-11T00:21:53.079059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.045418Z","title":"Detecting adversarial examples from sensitivity inconsistency of spatial-transform domain,","venue":null,"work_id":"2d9834ab-78be-4820-92ca-a1fd5c4c8e2b","year":2021},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.383637Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:e3f4977f984dffc5025b831686a9456caae1e1643165d25c4c1a7fb205ae75d0","observation_id":"97cea521-556c-476c-9b03-e01645cfc0fb","resolution":{"observed_at":"2026-08-11T00:21:53.055203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:53.019202Z","title":"Dla: dense- layer-analysis for adversarial example detection,","venue":null,"work_id":"127b19a4-aa3f-4d32-a791-5d55f1dfaed8","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.389891Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:7c90db974c9c3ac7ff2e51bcebed4cd44453e24d553c498ea2d063c65f88d569","observation_id":"51b2ff8f-86d5-4afd-bdeb-1101fb9cb514","resolution":{"observed_at":"2026-08-11T00:21:53.025817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.397365Z","title":"Using self- supervised learning can improve model robustness and uncertainty,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.397365Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:805ff48055f1c758d06d2d74f95bd53306992abaf538151c52fcb9717cecc18e","observation_id":"654f4690-b3e5-455f-b5fa-cdcadc49bd88","resolution":{"observed_at":"2026-08-11T00:21:52.397365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.979670Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":"b4dd42be-0d16-4925-b944-a3db1eab5cf2","year":2018},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.402942Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:d184844cafe307d5b16b69a7e90c1ccc45dc6ec32ce7a346b3d311b9e718cd2d","observation_id":"d13829af-82c2-4a56-855a-2418bfae7498","resolution":{"observed_at":"2026-08-11T00:21:52.986819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.954295Z","title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics,","venue":null,"work_id":"95f9f719-8f2a-43ab-90fa-b6bed5d2f349","year":2018},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.408471Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:ac70d78dc0843d13eb5ef85299c7762b5d9155f43fb8e07258646484e372ad38","observation_id":"4ceeec10-384b-4039-b5eb-a4e198611b4a","resolution":{"observed_at":"2026-08-11T00:21:52.962912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.932335Z","title":"Multitask learning strengthens adversarial robustness,","venue":null,"work_id":"e19e1078-ab40-45b9-8406-61b23d96f8f4","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.415120Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:d30456738b92c10e76e777f9381362718dfd0eebdddd743785bdfd0d37a0864d","observation_id":"382d785c-dd0b-4f2f-9fd2-b1a6ac14ef9d","resolution":{"observed_at":"2026-08-11T00:21:52.939317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.909410Z","title":"Improved noise and attack robustness for semantic segmentation by using multi-task training with self-supervised depth estimation,","venue":null,"work_id":"bcdc08cc-c987-4ec5-8eb1-95c1061e9fb2","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.420679Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:89bfab1f8245f2183867f5b5250f182a1ec412a0a01d1336eea7986ce9c9cfb2","observation_id":"308e3d12-912b-41aa-8154-75bed8d68b93","resolution":{"observed_at":"2026-08-11T00:21:52.916353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.884582Z","title":"Defending against adversarial attack towards deep neural networks via collaborative multi-task training,","venue":null,"work_id":"5fb6d330-5c12-4910-b337-8ebbb12c51c8","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.426080Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:42b1cb4274222f59e80e6975942873005cba117b508c8139c3ae9603b72d742d","observation_id":"64f39daf-cfe1-440a-b435-570498d17979","resolution":{"observed_at":"2026-08-11T00:21:52.894686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.861748Z","title":"Syndistnet: Self-supervised monocular fisheye cam- era distance estimation synergized with semantic segmentation for autonomous driving,","venue":null,"work_id":"99006eab-daa3-482f-b28a-33329adf0796","year":2021},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.431670Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:2720e325628d0f213b1e94091ca15aa88675cddd4403e16bce4fde9646463e7a","observation_id":"16e498d2-772a-4e09-9623-922dbde5135a","resolution":{"observed_at":"2026-08-11T00:21:52.868634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.830084Z","title":"Uninet: A unified scene understanding network and exploring multi-task relationships through the lens of adversarial attacks,","venue":null,"work_id":"7e6ef136-5904-466b-9321-cf6c07112e3e","year":2021},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.437037Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:ba92837592e6baf65948ca6fb1ebe2343ab5cd1ad6aa5efdafd75c3ad21b8167","observation_id":"c7ae92bd-25fc-4025-bbfb-ed1e3f854e60","resolution":{"observed_at":"2026-08-11T00:21:52.838859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.808088Z","title":"Multitask adversarial attack with dispersion amplification,","venue":null,"work_id":"e688d86e-72e6-4627-a507-2502621e7631","year":2021},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.445270Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:2f5cd71fad43ae8ca22ed5369db9e33a1d19e485309baa198ee2fdb7c4551d4b","observation_id":"60fb7ebf-21bf-4bfc-a6e1-54ff00990010","resolution":{"observed_at":"2026-08-11T00:21:52.814206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.780555Z","title":"A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies,","venue":null,"work_id":"acc7d0d0-52af-4530-ad9f-a79469353ef9","year":2022},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.451274Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:565ae4a27a90162a9c88887f9020273bcf5e703ad9665c3ca15ffb8418c41c35","observation_id":"156ab7f3-ff29-46f1-b145-e1d484b265f7","resolution":{"observed_at":"2026-08-11T00:21:52.789103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.761011Z","title":"Adversarial robustness vs. model compression, or both?","venue":null,"work_id":"4aaa6d35-d976-43c5-9af4-5a98a4c2ca13","year":2019},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.457236Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:ce5a6e1cfe57a1f5becbcbe1ffe7fdcb182f4beb145c8e429d71006fb744716e","observation_id":"e5b4426f-c3c7-46f4-8ebb-86e8d48bff5c","resolution":{"observed_at":"2026-08-11T00:21:52.766867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.740654Z","title":"When nas meets robustness: In search of robust architectures against adversarial attacks,","venue":null,"work_id":"f6958186-44cb-4f41-baf7-d1e6178c5b8a","year":2020},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.462494Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:523c8b14c370281f886dd16893b8ec40326b713626e40a9cd3e66a25da78e40e","observation_id":"c0089b23-ed1c-46c7-ac55-defc94fe05e8","resolution":{"observed_at":"2026-08-11T00:21:52.746783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.717571Z","title":"Towards adversarially robust object detection,","venue":null,"work_id":"f41ec04f-2297-4039-9a59-a0dc93bc02dd","year":2019},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.468240Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:5719a31ba96d8f0cd3226fb868d79ce1b7833fa5ce0e5f5cd8405ac483868953","observation_id":"7a438bde-a83a-4b2e-8cac-38d0a70c1073","resolution":{"observed_at":"2026-08-11T00:21:52.726116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.697494Z","title":"Class-aware robust ad- versarial training for object detection,","venue":null,"work_id":"1a570889-690a-4fc3-9516-b76519685712","year":2021},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.474573Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:c4a4379f1b2e10aa95c3643b1aae7fd5ebe79312f0509e7adf7c6da55c4d6735","observation_id":"0997edea-ecd9-4ffa-a900-23af637dc23c","resolution":{"observed_at":"2026-08-11T00:21:52.704251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.677895Z","title":"Shapeshifter: Robust physical adversarial attack on faster r-cnn object detector,","venue":null,"work_id":"ecc25c98-8adb-4959-b245-9459bc4cca63","year":2018},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.480397Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:51e0709026a4a7eef9391470382fe6429f2e9f98b772476b4307fe4e25a550ab","observation_id":"d24c658e-5fcb-4652-a395-5c8ca08aaa9e","resolution":{"observed_at":"2026-08-11T00:21:52.683686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:52.654467Z","title":"As the perturbation strength increases, it results in stronger impact on the target model and causes higher inconsistency between model pairs","venue":null,"work_id":"f22169a7-9dd3-4548-b41a-76c8758c6303","year":null},"citing_paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:52.486049Z"},"links":{"citing_paper":"/paper/2608.07750"},"observation_digest":"sha256:15954371b59dd7e9cbba3ac5775652582d242a533a0fb44eeca8cc1f2d1e7c63","observation_id":"69b99916-1d15-447c-a9cc-82427a16567f","resolution":{"observed_at":"2026-08-11T00:21:52.663304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.07750","last_updated":"2026-08-07T20:33:16Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T23:20:53.654773Z","submitted_at":"2026-08-07T20:33:16Z","title":"Multi-Task Consistency-based Detection of Adversarial Attacks"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":1,"verified_fuzzy":35},"total_outbound_references":43},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2608.07750."}