id	url	sha256	token_count	exact_duplicate_group	near_duplicate_pair_count	review_status	confirmed_companion_group
src-001	https://arxiv.org/abs/2408.03354	cf998d59e1a737b4b3192450afa044ea5f17cf76724581a6c3761bc24d0a6623	769		0	unique_bytes; near-duplicate scan below	none
src-002	https://arxiv.org/abs/2410.20287	162da8c17e6a372cbb7427177746b8e0b01cdeeb5fba3f46328084a81602553a	660		0	unique_bytes; near-duplicate scan below	none
src-003	https://arxiv.org/abs/2502.00961	9b7510312de27b89f599f05e76c760eb07d777cfd1e9afec66bbb8dd623dc5db	629		0	unique_bytes; near-duplicate scan below	none
src-004	https://assets.recordedfuture.com/Executive-Insights/eir-2025-0828.pdf	12db962ad79a35bf3d8c1533df6298c15900f45547efa2be99d7ecc542beac0d	1795		1	confirmed_companion_format_duplicate	dup-001
src-005	https://blog.talosintelligence.com/content/files/2025/03/2024YiR-report.pdf	0ae328f3db3e3f1cc66e5d61705ebb8d4221efe126d4523b485f7ac2f77b2fd2	11552		0	unique_bytes; near-duplicate scan below	none
src-006	https://blog.talosintelligence.com/keep-going-bro-youve-got-this-a-data-driven-look-at-how-adversaries-are-weaponizing-ai/	03592f01f1ec64ff67ae6ce15bf8e100031865178caac15ac07a973ece82daeb	8125		0	unique_bytes; near-duplicate scan below	none
src-007	https://blog.talosintelligence.com/uat-10147-chinese-speaking-adversary-integrates-agentic-ai-into-post-compromise-operations/	2eb4ace3d0c0d540542bdcc20438893a02eefcf4acda90947300a64e3df0dcdd	4003		0	unique_bytes; near-duplicate scan below	none
src-008	https://cdn-dynmedia-1.microsoft.com/is/content/microsoftcorp/microsoft/final/en-us/microsoft-brand/documents/2024-State-of-Multicloud-Security-Risk-Report.pdf	fb9803131fe9f6711de684b163cef80babefc9e85f35da955b9f277966d9fe8e	6264		0	unique_bytes; near-duplicate scan below	none
src-009	https://cert.europa.eu/publications/threat-intelligence/tlr2025/	84f4722b075157b5ec0f3ab037f2a7c47a90ed4da99a0a0cb5d86c219d411fdc	400		0	unique_bytes; near-duplicate scan below	none
src-010	https://cert.gov.ua/article/6284730	7b14f3434cf702424413b9f240383e54d709e69140c89a4e3271367b293f021d	414		0	unique_bytes; near-duplicate scan below	none
src-011	https://cloud.google.com/blog/products/identity-security/the-dawn-of-agentic-ai-in-security-operations-at-rsac-2025	cb918295d43a60f1dbf9e79959c5b4e691ba8f34181eaeb34cbebcc8dd339d69	1546		0	unique_bytes; near-duplicate scan below	none
src-012	https://cloud.google.com/blog/topics/threat-intelligence/adversarial-misuse-generative-ai	d5c19e6dc4d2a76698781cf665aacdbb17359e820e0615138d321b006a259de9	7326		0	unique_bytes; near-duplicate scan below	none
src-013	https://cloud.google.com/blog/topics/threat-intelligence/ai-enhancing-your-adversarial-emulation	f14fa50f1249c0f1e66e026dd1d80d819df7af431a86201bdc2af80fa18cc4e7	4868		0	unique_bytes; near-duplicate scan below	none
src-014	https://cloud.google.com/blog/topics/threat-intelligence/ai-powered-voice-spoofing-vishing-attacks	4332536aeb71b0b3f892aaa134c0facdb450bb651380b9e9484f36d441914205	2135		0	unique_bytes; near-duplicate scan below	none
src-015	https://cloud.google.com/blog/topics/threat-intelligence/ai-vulnerability-exploitation-initial-access	3d6ff6cfdd9f2b8492659912e5946966d3c2f7c3182a7ef88b28d4141780da93	6376		0	unique_bytes; near-duplicate scan below	none
src-016	https://cloud.google.com/blog/topics/threat-intelligence/cybercriminals-weaponize-fake-ai-websites/	d96103004e5c779b3c03a3c2d94a098361770d53bc06c8957318e323fddda445	4866		0	unique_bytes; near-duplicate scan below	none
src-017	https://cloud.google.com/blog/topics/threat-intelligence/defending-enterprise-ai-vulnerabilities	dceecaa7f4ae44f11d02e916e6c2248e4c5bef21a9e8dd6161cb0d5b497f470b	3371		0	unique_bytes; near-duplicate scan below	none
src-018	https://cloud.google.com/blog/topics/threat-intelligence/distillation-experimentation-integration-ai-adversarial-use	1c2bc07d3b6f4d09d56608ea784663f4d3a7e3a1e033ee73b9aadeccf2abd22c	5787		0	unique_bytes; near-duplicate scan below	none
src-019	https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools	32eb6d0451cfc64c4e8c377ef321b4e3253725e58f5bb1dd8df1989f4f86ef8b	5101		1	confirmed_companion_format_duplicate	dup-002
src-020	https://cloud.google.com/blog/topics/threat-intelligence/threat-actors-generative-ai-limited	75acd543c00c106445b7ba94e60c655650b78a381e995bab700c77a86f01c715	2678		0	unique_bytes; near-duplicate scan below	none
src-021	https://cloud.google.com/blog/topics/threat-intelligence/unc1069-targets-cryptocurrency-ai-social-engineering	70840583c0318e54de007ac6b9ebb198970e15328b9ff2a62934091039e81c2c	5198		0	unique_bytes; near-duplicate scan below	none
src-022	https://filestore.fortinet.com/fortiguard/2025_Global_Threat_Landscape_Report.pdf	721810f6a569775327507484c6978614304aed7aaf263f277651b797edda0480	6167		0	unique_bytes; near-duplicate scan below	none
src-023	https://info.ke-la.com/hubfs/Reports/KELA%20Report%20-%202025%20AI%20Threat%20Report.pdf	4e757adaa2b40042afee894879b8be67b9b3f2aca9fbba7475337c14a7d52c2a	3987		0	confirmed_companion_format_duplicate	dup-003
src-024	https://openai.com/global-affairs/an-update-on-disrupting-deceptive-uses-of-ai/	0f754720d8996f01838dcf5648225fdd93142b70ff2818e27b8784a8d44267e1	294		0	unique_bytes; near-duplicate scan below	none
src-025	https://openai.com/global-affairs/disrupting-malicious-uses-of-ai-june-2025/	c7c6be032b3bbddc441329967d698be54a3570dd50a38eb479b677cd15e1ad73	246		0	unique_bytes; near-duplicate scan below	none
src-026	https://openai.com/global-affairs/disrupting-malicious-uses-of-ai-october-2025/	310d0d84c2172bac5a7bebcedca639793d1f5f08450f9ad32a5f589a80f34790	994		0	unique_bytes; near-duplicate scan below	none
src-027	https://openai.com/global-affairs/disrupting-malicious-uses-of-ai/	23c71f01d4f03cc301231f1e59cfb2765fed37ed013d4d1dd08943462622b887	252		0	unique_bytes; near-duplicate scan below	none
src-028	https://openai.com/index/disrupting-malicious-uses-of-ai-by-state-affiliated-threat-actors/	b394e65bc5b7ae8062346b18f80b6984358c0ce5dc25f7b1c8f8406f2a6b330a	1857		0	unique_bytes; near-duplicate scan below	none
src-029	https://openai.com/index/disrupting-malicious-uses-of-ai-scam-operations/	228fe5e2b8edb51a56b8f756c63a60382e3e7a9f1089971debff4cdf280e35f5	1312		0	unique_bytes; near-duplicate scan below	none
src-030	https://openai.com/index/disrupting-malicious-uses-of-ai-storm-0817/	38573b12b3693d19d29ab797363e9e77107c457a9c8d980d13a4ce5ebbe7920a	687		0	unique_bytes; near-duplicate scan below	none
src-031	https://research.checkpoint.com/2023/opwnai-cybercriminals-starting-to-use-chatgpt/	4a4711efccf4f42e89cc87cfd942c566b66d4b00a223abc5d33fc61471f78901	1953		0	unique_bytes; near-duplicate scan below	none
src-032	https://research.checkpoint.com/2025/funksec-alleged-top-ransomware-group-powered-by-ai/	ecef804fa828c45795cdbd3b4cf83ca3052ad4e8e06eeaca204f52b3a0fb299e	3444		0	unique_bytes; near-duplicate scan below	none
src-033	https://research.checkpoint.com/2025/impersonated-kling-ai-site-installs-malware/	6a1a79a18d54c3093c15ff34ad889db01501445347e2042694c22539f8e43155	3046		0	unique_bytes; near-duplicate scan below	none
src-034	https://research.checkpoint.com/2025/sate-of-ai-in-cyber-security/	6c228a036762a26c429594df72e5a0b9a12b837065809479552352644b8a220b	2414		0	unique_bytes; near-duplicate scan below	none
src-035	https://research.checkpoint.com/2026/ai-in-the-middle-turning-web-based-ai-services-into-c2-proxies-the-future-of-ai-driven-attacks/	930892e7563d8f08808e1199748c49ef9fb2f79b9119e615ded8bf60c910153f	4533		0	unique_bytes; near-duplicate scan below	none
src-036	https://research.checkpoint.com/2026/browser-only-ransomware-from-llm-hallucinations-to-a-practical-attack-technique/	e84f6eec92b516647968a78ce62ca6064f78daaf6cfbd93230bafdb0767130bd	4285		0	unique_bytes; near-duplicate scan below	none
src-037	https://research.checkpoint.com/2026/chatgpt-data-leakage-via-a-hidden-outbound-channel-in-the-code-execution-runtime/	5473d33818cc99d6aae82632ac3c730c2531c393e84762546528e2af67594019	2761		0	unique_bytes; near-duplicate scan below	none
src-038	https://securelist.com/bluenoroff-apt-campaigns-ghostcall-and-ghosthire/117842/	00f2495474057898c4550c362163b4711910f7a9040b7f475c3756d5a109c0b3	14613		0	unique_bytes; near-duplicate scan below	none
src-039	https://services.google.com/fh/files/misc/advances-in-threat-actor-usage-of-ai-tools-en.pdf	bc517904af9d5c40ad4f3a7dc1f8bba30c6b874f42ca93a1146a02ea1f86bf45	5451		1	confirmed_companion_format_duplicate	dup-002
src-040	https://unit42.paloaltonetworks.com/2025-unit-42-global-incident-response-report-social-engineering-edition/	78a6ebba8778d80ccdc8e8c9091e4324312165d6a3f3b52a6123600a24e45e5f	5941		0	unique_bytes; near-duplicate scan below	none
src-041	https://unit42.paloaltonetworks.com/agentic-ai-threats/	090d177b7f6fd41b9e319f4995ba8821740e1454d5140d4f6e7413aabf1fc020	7442		0	unique_bytes; near-duplicate scan below	none
src-042	https://unit42.paloaltonetworks.com/ai-enabled-malware-analysis/	a44017345f3a14bb2878634d1ebe588be0cab911812279b05f0633366a4b5040	2954		0	unique_bytes; near-duplicate scan below	none
src-043	https://unit42.paloaltonetworks.com/ai-use-in-malware/	2d93a1391a76fe86e7da0decb0c8ba76b4ea7634c607405eea8c72a4d76998ac	4922		0	unique_bytes; near-duplicate scan below	none
src-044	https://unit42.paloaltonetworks.com/autonomous-ai-cyber-attack-campaign/	34214cdb6388760898904e8bd1a1838127dae5af2d57df09ec7a752c3a7ef01c	3901		0	unique_bytes; near-duplicate scan below	none
src-045	https://unit42.paloaltonetworks.com/frontier-ai-vulnerability-burst/	2d173507054b99aeb80b7a340dac841c72bf0a7461063b41e1351b67b94a72d2	3639		0	unique_bytes; near-duplicate scan below	none
src-046	https://unit42.paloaltonetworks.com/genai-phishing-bait/	dac7c6315e7f49c08d54a13c90a6b5ec5ea6b04d355638da43ea13a9bb40a1f7	2883		0	unique_bytes; near-duplicate scan below	none
src-047	https://unit42.paloaltonetworks.com/real-time-malicious-javascript-through-llms/	a8947c92b43c8dbcaf315385e2f5fc06c10ce9dd4fbe875bb0fd7436d2548417	3255		0	unique_bytes; near-duplicate scan below	none
src-048	https://unit42.paloaltonetworks.com/tuxbot-v3-evolution-iot-botnet/	93b23b7d3dded061eb73a9fcbfb5acad4f2ef1be416d8657d8340067617aa811	7364		0	unique_bytes; near-duplicate scan below	none
src-049	https://www-cdn.anthropic.com/d7dd50dd1185f59be051b307150d877f2b82bd2c.pdf	f35a7b90d06e60c6fc14c99c12945f3d13026861dee97ebb2ed5ac5e1d8bebf5	2761		0	confirmed_companion_format_duplicate	dup-004
src-050	https://www.anthropic.com/news/AI-enabled-cyber-threats-mitre-attack	92906e0749a5640037657010f19c7b7cca6e00baa55b31853578b8e5b7840539	1472		0	unique_bytes; near-duplicate scan below	none
src-051	https://www.anthropic.com/news/detecting-and-countering-malicious-uses-of-claude-march-2025	3e23806a28fbeb1cc675eb7eaf23bf88d4427534983a3ca6f10fa38f5adb3eb0	1943		0	unique_bytes; near-duplicate scan below	none
src-052	https://www.anthropic.com/news/detecting-countering-misuse-aug-2025	34caa200b4d0c3e50bc660df5a34d31866c4f2002fdf4b35615653a92449e142	1867		0	unique_bytes; near-duplicate scan below	none
src-053	https://www.anthropic.com/news/disrupting-AI-espionage	35651e58e438207b0413574736bcec803dd0f4c06b15ce561d68b98e5cbf256f	1755		0	confirmed_companion_format_duplicate	dup-004
src-054	https://www.anthropic.com/research/attack-navigator	fb4b52f6256ed838a1dde997415f41e015c5ce22db247f6e44dab5024b2a4031	4870		0	unique_bytes; near-duplicate scan below	none
src-055	https://www.checkpoint.com/resources/all-assets-460c/report-ai-security-report-2025?fw=c778b	2a860885b7cb78f7cc117d8bc1aacba6f07d895f25e4a091616f0e43f51821f2	2637		0	unique_bytes; near-duplicate scan below	none
src-056	https://www.cisa.gov/news-events/cybersecurity-advisories/aa26-204a	c0cc9642e86f19521ea4eb9c3d5983132e59a16544e7c40ef67afad2b8e7ed10	10729		0	unique_bytes; near-duplicate scan below	none
src-057	https://www.cisa.gov/news-events/cybersecurity-advisories/aa26-231a	41bfb45fdf4a79fbd00750df43857c97b3581995229da679576e2362a2b3fafd	3327		0	unique_bytes; near-duplicate scan below	none
src-058	https://www.crowdstrike.com/content/dam/crowdstrike/www/en-us/wp/2024/08/2024-Threat-Hunting-Executive-Report.pdf	6fb11c4e162c7740aef21cdf01937703c2e4de70566e7beb818095e08ed071e9	1986		0	unique_bytes; near-duplicate scan below	none
src-059	https://www.crowdstrike.com/en-us/blog/ai-vs-ai-cybersecurity-arms-race/	04a10589f2d9bab42259ef6cd090d119d9a0be29cac6bc6934b5a7d0bc031da5	3979		0	unique_bytes; near-duplicate scan below	none
src-060	https://www.crowdstrike.com/en-us/blog/crowdstrike-2024-global-threat-report/	be0c4337cdb9b6dfb80ca34acd2d19d7829527d738046f4b3ea54c8d18dbbb84	1982		2	unique_bytes; near-duplicate scan below	none
src-061	https://www.crowdstrike.com/en-us/blog/crowdstrike-2025-threat-hunting-report-ai-weapon-target/	004be29536b7538650cbc463bece4aca9557e32523ded899b315cea1864519c9	1967		2	unique_bytes; near-duplicate scan below	none
src-062	https://www.crowdstrike.com/en-us/blog/how-crowdstrike-hunts-identifies-and-defeats-cloud-threats/	392a3ebe58620355585f83d3e50531850a7f7315e4c9e3492bc45b8e9a3e676a	2229		2	unique_bytes; near-duplicate scan below	none
src-063	https://www.crowdstrike.com/en-us/resources/articles/crowdstrike-2025-global-threat-report-genai-exploits-cloud-attacks/	4e22d107c56f97ccef7eb134f15a2652cca1e75091c27ae93108c2c1a11334ff	1058		0	unique_bytes; near-duplicate scan below	none
src-064	https://www.crowdstrike.com/en-us/resources/articles/crowdstrike-2025-global-threat-report-genai-powers-social-engineering/	b7e9d8620157151e6dcc9c2ddb74a06821de50d0feeef0c84ebae3ee16b70bfa	1015		0	unique_bytes; near-duplicate scan below	none
src-065	https://www.crowdstrike.com/wp-content/uploads/2024/02/crowdstrike-2024-global-threat-report-executive-summary.pdf	717c69ea64b27536d38570fabef932a6310128334bc70333edea2e6ccfb0b0ed	2124		0	unique_bytes; near-duplicate scan below	none
src-066	https://www.enisa.europa.eu/publications/enisa-threat-landscape-2025	a469f7616072994630317214931bb830b56c214c9f6ae9ba63cdf453c06d9a07	737		0	unique_bytes; near-duplicate scan below	none
src-067	https://www.eset.com/us/about/newsroom/press-releases/eset-threat-report-infostealers-using-ai-banking-malware-creating-deepfake-videos-to-steal-money-2/	760df72ea0dcc00535c54052bfcea13b6e80ad67e9711bcaa689f48840a7e735	1391		0	unique_bytes; near-duplicate scan below	none
src-068	https://www.europol.europa.eu/publications-events/publications/facing-reality-law-enforcement-and-challenge-of-deepfakes	2ff5fee32544039abba09515a9853eec4e108478b2e7d320a0b8434f842292d5	4569		0	unique_bytes; near-duplicate scan below	none
src-069	https://www.fbi.gov/investigate/cyber/alerts/2025/senior-us-officials-continue-to-be-impersonated-in-malicious-messaging-campaign	51527f74ea824f0affd3d42af7e5dff21ccc4892d7ee580e2438a0e64cc5c4d7	1258		0	unique_bytes; near-duplicate scan below	none
src-070	https://www.fincen.gov/news/news-releases/fincen-issues-alert-fraud-schemes-involving-deepfake-media-targeting-financial	c4d767c0257ca49d931519450ac78460594c25a7625ce4d1c4cb8514e39878db	511		0	unique_bytes; near-duplicate scan below	none
src-071	https://www.fortinet.com/blog/threat-research/2024-threat-predictions-chained-ai-and-caas-operations	c33497247404c064d4490b071c2b77f02f866bf99428707ac771c6c5488bbabb	1381		0	unique_bytes; near-duplicate scan below	none
src-072	https://www.fortinet.com/blog/threat-research/key-takeaways-from-the-2025-global-threat-landscape-report	07a9ce3119f61072dcdb4a64a6bcad8b747608012749b4bdb1af2f5eb7039d89	1246		0	unique_bytes; near-duplicate scan below	none
src-073	https://www.fortinet.com/content/dam/fortinet/assets/threat-reports/report-threat-prediction-2025.pdf	57df36ab08cea5a706c9ce59ff979f58a839fe9cf6801b33016d1d0e6a3e5795	5200		0	unique_bytes; near-duplicate scan below	none
src-074	https://www.gov.uk/government/publications/international-scientific-report-on-the-safety-of-advanced-ai/international-scientific-report-on-the-safety-of-advanced-ai-interim-report	af8a0c386ae9b9f28f152be2fc7347f6edd2cfccda9ee0c8b97492550d18b44e	75507		0	unique_bytes; near-duplicate scan below	none
src-075	https://www.ibm.com/think/x-force/2024-x-force-threat-intelligence-index	b305d10848eebd0eafa806510c622e7b68ab2f239b1b5656125d06547040a607	1564		0	unique_bytes; near-duplicate scan below	none
src-076	https://www.ibm.com/think/x-force/adversary-didnt-wait-neither-should-you	4b3b03496dd7ff51566d2cfd5bdd5973d1a60625f4955777f11da1c5f6a55ff6	1616		0	unique_bytes; near-duplicate scan below	none
src-077	https://www.ibm.com/think/x-force/hive0137-on-ai-journey	e6b62e8508c2e1cedd7617de47e526afadeb1e7ce881f6e5c217e272af83f81c	3235		0	unique_bytes; near-duplicate scan below	none
src-078	https://www.ic3.gov/PSA/2024/PSA241203	1a237f7bc86f39c0622e4a97e9fa4f5e682ce9a0884ea2c3f5eebb52207e484b	998		0	unique_bytes; near-duplicate scan below	none
src-079	https://www.interpol.int/News-and-Events/News/2026/INTERPOL-report-finds-AI-linked-to-more-than-half-of-cybercrime-in-Africa	6825b2fccb3c0edde8de26cc28e807f1bf60e191d59a126426177ef1c5f4d09a	933		0	unique_bytes; near-duplicate scan below	none
src-080	https://www.kelacyber.com/resources/research/2025-ai-threat-report/	57ab0996974f0cf64dad0de553bbc46d212d59e3fce913aaa00f6c4335936920	500		0	confirmed_companion_format_duplicate	dup-003
src-081	https://www.kroll.com/en/reports/cyber/threat-intelligence-reports/q1-2024-threat-landscape-report-insider-threat-phishing-evolve-under-ai	e102e7933bd3f5c4b926636cd5d5813ea2b9590fcf462db17526c02504ca320a	2970		0	unique_bytes; near-duplicate scan below	none
src-082	https://www.microsoft.com/en-us/security/blog/2024/02/14/staying-ahead-of-threat-actors-in-the-age-of-ai/	24f88bbf7e7bb39418fa7a75b3fca7d2b9c5500cdc112eefca0afda2216202c2	3778		0	unique_bytes; near-duplicate scan below	none
src-083	https://www.microsoft.com/en-us/security/security-insider/threat-landscape/cyber-signals-issue-6-navigating-cyberthreats-and-strengthening-defenses	2c599d2825b5ba92f202e6d3c8672bc75f5259ce8c831b59742eea265618c6fd	2915		0	unique_bytes; near-duplicate scan below	none
src-084	https://www.ncsc.gov.uk/report/impact-ai-cyber-threat-now-2027	9f3612312a7a8b95882f905beda6ef2bc805875eae2ab6bda7de56ef43a7cb23	2352		0	unique_bytes; near-duplicate scan below	none
src-085	https://www.ncsc.gov.uk/report/impact-of-ai-on-cyber-threat	79ae56a71f08773dfd076ad14f9870016d3b6d4aa984828a523e20e1955302df	2486		0	unique_bytes; near-duplicate scan below	none
src-086	https://www.proofpoint.com/us/blog/threat-insight/operation-endgame-quakes-rhadamanthys	08f96e7858ac4c7c5802984bb390d76ed3fbd8a0d2098c6b7e018de0999ce668	3638		0	unique_bytes; near-duplicate scan below	none
src-087	https://www.proofpoint.com/us/blog/threat-insight/security-brief-artificial-sweetener-sugargh0st-rat-used-target-american	11eccfd1e17d1402edd3e4b5c488a99f22c53554c71e794db6dbe3136b75cce5	1760		2	unique_bytes; near-duplicate scan below	none
src-088	https://www.proofpoint.com/us/blog/threat-insight/security-brief-ta547-targets-german-organizations-rhadamanthys-stealer	73fc5907bb5bbd34aaa3931f16dcf947ae46b1c4de338a2abf7659c77c8d70e4	1612		1	unique_bytes; near-duplicate scan below	none
src-089	https://www.proofpoint.com/us/blog/threat-insight/threat-landscape-always-changing-what-expect-2024	f7f8a3728575d593a908bb628a7dbca63f6afb188e11f8fd054eda5fd167ddbc	1877		1	unique_bytes; near-duplicate scan below	none
src-090	https://www.rapid7.com/blog/post/3-ways-social-engineering-is-evolving-and-what-security-teams-must-do-next/	62f188ebab17472450cdcb8301d65c4eb5cc73236765337b4479bd6ebc2c5bd5	1734		0	unique_bytes; near-duplicate scan below	none
src-091	https://www.rapid7.com/blog/post/ai-goes-on-offense-how-llms-are-redefining-the-cybercrime-landscape/	bdb5bc62932809971f84545e5c8f50296730a4444e5dda5365ddd9740c689611	2213		0	unique_bytes; near-duplicate scan below	none
src-092	https://www.rapid7.com/blog/post/emerging-trends-in-ai-related-cyberthreats-in-2025-impacts-on-organizational-cybersecurity/	96f1582a979cef3807daa5c036564c32ce9ad379c3fa29dc8c1016d69c018867	1996		0	unique_bytes; near-duplicate scan below	none
src-093	https://www.rapid7.com/blog/post/tr-rapid7-q3-2025-threat-landscape-report/	feb822073260123b97ee6bf7121490ce853f118fb7d50489122776b702d29089	1315		0	confirmed_companion_format_duplicate	dup-005
src-094	https://www.rapid7.com/cdn/assets/bltbd2f1cd70f9e3e7f/691360b9c91291146f1a5308/threat-landscape-report-q3-2025.pdf	859301aa4d1c50e9a39d1fd13f4208c612696a867c7b2cdea8f66acbe0a630a8	6040		0	confirmed_companion_format_duplicate	dup-005
src-095	https://www.recordedfuture.com/research/2024-annual-report	929818899df5630cbd1487ab20648b70f030a627d3779709fa54a18ea50ca720	770		0	unique_bytes; near-duplicate scan below	none
src-096	https://www.recordedfuture.com/research/2025-cloud-threat-hunting-defense-landscape	11d8d25d3642f362f42bfdc2698ec70b167029cac72b1de976cef1b6a766fec6	19098		0	unique_bytes; near-duplicate scan below	none
src-097	https://www.recordedfuture.com/research/2025-year-in-review-malicious-infrastructure	9024e490039713118f6eaf872814b65f6b6e82d9d3238753f2678934d75434df	1104		0	unique_bytes; near-duplicate scan below	none
src-098	https://www.recordedfuture.com/research/adversarial-intelligence-red-teaming-malicious-use-cases-ai	49e5527f4e6634b7d7d848665930dec42bfc64222697ef1540f42cebbe235bea	414		0	unique_bytes; near-duplicate scan below	none
src-099	https://www.recordedfuture.com/research/emerging-ai-threats-future-of-automated-operations	433a195cfe4497873550c1e94830d2864915ba6c957091573c8f44468e7a0268	1521		1	confirmed_companion_format_duplicate	dup-001
src-100	https://www.recordedfuture.com/research/emerging-enterprise-security-risks-of-ai	3ebbce2736b96b1bf6d87d18c173d9ec8653876623f9cf3b989bf786c6202a06	2091		0	unique_bytes; near-duplicate scan below	none
src-101	https://www.recordedfuture.com/research/i-chatbot	e451fc5c60611145fc2c77b34ed9b0397942d6bae10608a314e2034795ad4cbe	1717		0	unique_bytes; near-duplicate scan below	none
src-102	https://www.recordedfuture.com/research/i-have-no-mouth-and-i-must-do-crime	b2335f6ff38508eb578a08665ec3314a399e295396fd37ce982ccdaa85b9fd70	476		0	unique_bytes; near-duplicate scan below	none
src-103	https://www.sans.org/white-papers/2024-cti-survey-managing-evolving-threat-landscape	3c169e41b47fb9c9cd8a5779b635266eb782fd97d6d0b4b815187fbe91a42289	1395		0	unique_bytes; near-duplicate scan below	none
src-104	https://www.sentinelone.com/labs/akirabot-ai-powered-bot-bypasses-captchas-spams-websites-at-scale/	a1a532ef9e99430fb749c25b5cd76119005a4a312d783d7e545e62d093b93dc6	2812		0	unique_bytes; near-duplicate scan below	none
src-105	https://www.sentinelone.com/labs/predator-ai-chatgpt-powered-infostealer-takes-aim-at-cloud-platforms/	84c2ae1196f6ec53cc1d01496c3808e0af8e556b321fdf4c5e60743e08f12966	2250		0	unique_bytes; near-duplicate scan below	none
src-106	https://www.sentinelone.com/labs/prompts-as-code-embedded-keys-the-hunt-for-llm-enabled-malware/	c7b911717d543f66244aad02ba9a100426bd1702efd2f3ff6582cb5f254db2da	3378		0	unique_bytes; near-duplicate scan below	none
src-107	https://www.sophos.com/en-us/blog/the-sophos-annual-threat-report-cybercrime-on-main-street-2025	b7eeb4b165b776defbcb862c08d0c07baacf8b8e7e0e8615c2030ffb6590ed14	5362		0	unique_bytes; near-duplicate scan below	none
src-108	https://www.sophos.com/en-us/blog/why-cybercriminals-are-not-necessarily-embracing-ai	9853c53692ca75c6393f4ea6e406fee9a857298c721568e623a6b9d221ba782c	2645		0	unique_bytes; near-duplicate scan below	none
src-109	https://www.sophos.com/en-us/press/press-releases/2023/11/sophos-anticipates-ai-based-attack-techniques-and-prepares-detections	41a6c62cb6d7a575a0f60d1d08b03bd53ab5dd7e2d9cfee5f2584624d6d3e115	847		0	unique_bytes; near-duplicate scan below	none
src-110	https://www.threatdown.com/blog/threatdown-state-of-malware-report-2025/	a2c676a617fe540c8f1a3c00b9cced7fa1babb81ced86a302686fa5f77e1fec3	1152		0	unique_bytes; near-duplicate scan below	none
src-111	https://www.trendmicro.com/vinfo/de/security/news/cybercrime-and-digital-threats/2025-apt-report-staying-ahead-of-the-modern-threat-landscape	60c76e338cb83b6f541de427258a87ddb246e905a23e6efc42085d2f9950e799	3665		0	unique_bytes; near-duplicate scan below	none
src-112	https://www.trendmicro.com/vinfo/gb/security/news/cybercrime-and-digital-threats/back-to-the-hype-an-update-on-how-cybercriminals-are-using-genai	d57b97abbe8093442a56424efa79ab46fc0e4e598630f3173a9675adba131594	3360		0	unique_bytes; near-duplicate scan below	none
src-113	https://www.trendmicro.com/vinfo/pl/security/news/cybercrime-and-digital-threats/hype-vs-reality-ai-in-the-cybercriminal-underground	0016d10b5c4bb941429a406475e7dc1cee7c647a9e48fcd110e89e8d0e4a0ca0	4640		0	unique_bytes; near-duplicate scan below	none
src-114	https://www.unodc.org/roseap/uploads/documents/Publications/2025/UNODC_Report_Emerging_threats_-_The_intersection_of_criminal_and_technological_innovation_in_the_use_of_automation_and_AI.pdf	51e3fb31ea278b64e1969aa0543d368113baca27f4e2c1876c0afae9b8373f3b	12459		0	unique_bytes; near-duplicate scan below	none
src-115	https://www.usenix.org/conference/usenixsecurity24/presentation/lin-zilong	4e87ca5fa7b1fa8636e9ac4d2a98745a0fd6afdf44cdcadb894d4938a4aafc6d	449		0	unique_bytes; near-duplicate scan below	none
src-116	https://www.zscaler.com/resources/industry-reports/threatlabz-ai-security-report-2025.pdf	91a5db511103fa74288ff225e52b9900de34d761a34e687197d4724441add31b	13207		0	unique_bytes; near-duplicate scan below	none
