Search: “model extraction”

93 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Ransomware 97 Exploit / PoC 93 Data breach 50 Threat actor 46 Vulnerability 44 Malware 35 AI safety & security 28 Phishing & fraud 9 Policy & legal 9 Advisory 3 Model release 3 AI policy 2 Research 1

SeverityAll critical 333 high 48 medium 29 low 0 info 10

14th September – Threat Intelligence Report

Check Point weekly digest: Microsoft's record 974-vuln Patch Tuesday ships two actively exploited Windows zero-days; IDScan.net, Mathspace, Revolut suffer breaches.

Microsoft's September 2026 Patch Tuesday addressed a record 974 vulnerabilities, including two actively exploited privilege-escalation zero-days, CVE-2026-85880 and CVE-2026-81963, plus 20 flaws allowing unauthenticated remote code execution. Disclosed breaches include IDScan.net (identity documents), Mathspace (over 1 million people via Metabase CVE-2026-72898), Revolut, and Florida DMV (ShinyHunters). GitLab fixed critical CVSS 10.0 path traversal CVE-2026-85706, and MikroTik fixed chainable RouterOS flaws CVE-2026-67276 and CVE-2026-86060. The report also covers the PuzzleMask LLM jailbreak technique, GoldFactory's Gigabud Android fraud, and the BlueMoon Chromium exploit chain (CVE-2026-85046).

Check Point ResearchSep 14, 12:22 UTC · 2d agoExploit / PoC in the wildCVE-2026-72898 CVE-2026-85880 CVE-2026-81963+4 CVEs2· 1 read

Anthropic says its AI accidentally hacked three companies during safety tests

CyberScoopJul 31, 02:10 UTC · Jul 31, 2026Exploit / PoC in the wild1

Treasury report calls out cyber risks to financial sector fueled by AI

CyberScoopMar 29, 18:20 UTC · Mar 29, 2024Exploit / PoC in the wild

Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards

The Hacker NewsJun 10, 07:37 UTC · Jun 10, 2026Exploit / PoC CVE-2026-47471

Senators move to quash the use of Chinese AI system by federal contractors

CyberScoopMay 9, 18:33 UTC · May 9, 2025Exploit / PoC in the wild

Two Critical Flaws Uncovered in Wondershare RepairIt Exposing User Data and AI Models

The Hacker NewsSep 24, 13:55 UTC · Sep 24, 2025Exploit / PoC CVE-2025-10643 CVE-2025-10644

Researchers Build WordPress Exploit Using OpenAI's GPT

Infosecurity MagazineJul 20, 14:00 UTC · Jul 20, 2026Exploit / PoC in the wildCVE-2026-63030 CVE-2026-60137

Cybercriminals capitalize on poorly configured cloud environments

Help Net SecurityOct 4, 00:00 UTC · Oct 4, 2024Exploit / PoC

AI-Assisted HTTP Terminator Finds Novel HTTP Desync Techniques and Apache Zero

The Hacker NewsAug 7, 11:25 UTC · Aug 7, 2026Exploit / PoC CVE-2026-63078

NVIDIA Forms 37-Member Open Secure AI Alliance and Open

The Hacker NewsJul 27, 18:10 UTC · Jul 27, 2026Exploit / PoC

Cellebrite can now unlock iPhone 6 and 6+, also extract data from array of popular apps

CyberScoopFeb 23, 17:20 UTC · Feb 23, 2017Exploit / PoC in the wild

Researchers Reveal ReVault Attack Targeting Dell ControlVault3 Firmware in 100+ Laptop Models

The Hacker NewsAug 10, 08:12 UTC · Aug 10, 2025Exploit / PoC in the wildCVE-2025-25050 CVE-2025-25215 CVE-2025-24922+2 CVEs

Microsoft Uncovers 'Whisper Leak' Attack That Identifies AI Chat Topics in Encrypted Traffic

The Hacker NewsNov 10, 08:00 UTC · Nov 10, 2025Exploit / PoC

Former U.S. Defense contractor executive sentenced for selling zero-day exploits to Russian broker Operation Zero

Security AffairsFeb 25, 10:06 UTC · Feb 25, 2026Exploit / PoC in the wild

CyberLink FaceMe Platform allows users to monitor all databases and system services in one place

Help Net SecurityApr 28, 00:00 UTC · Apr 28, 2022Exploit / PoC

JFrog tries to spin OpenAI 0-day exploit of its app into a success story

Ars Technica · SecurityJul 28, 21:36 UTC · Jul 28, 2026Exploit / PoC

‘GrafanaGhost’ bypasses Grafana's AI defenses without leaving a trace

CyberScoopApr 7, 17:01 UTC · Apr 7, 2026Exploit / PoC in the wild

Flaw in Claude’s Chrome extension allowed ‘any’ other plugin to hijack victims’ AI

CyberScoopMay 8, 13:14 UTC · May 8, 2026Exploit / PoC in the wild

⚡ Weekly Recap: Fortinet Exploited, China's AI Hacks, PhaaS Empire Falls & More

The Hacker NewsNov 17, 12:37 UTC · Nov 17, 2025Exploit / PoC in the wildCVE-2025-64446 CVE-2025-64740 CVE-2025-64741+24 CVEs

Leaked n8n API Tokens Exposed Live Instances to Credential Theft

The Hacker NewsAug 5, 10:35 UTC · Aug 5, 2026Exploit / PoC in the wildCVE-2025-68613

Attackers Exploit MLflow SSRF Flaw to Steal Cloud Credentials and Secrets

Attackers exploit MLflow SSRF CVE-2026-64849 (CVSS 9.3) to steal cloud credentials; CISA added it to KEV; FUXA flaw CVE-2026-25895 is being scanned.

watchTowr observed exploitation of MLflow CVE-2026-64849, an unauthenticated SSRF (CVSS 9.3) affecting versions below 3.15.0, within hours of CVE assignment on August 17, 2026, with attackers abusing model-registry webhooks to reach cloud metadata endpoints and exfiltrate credentials and secrets. CISA added the flaw to its Known Exploited Vulnerabilities catalog on August 19, 2026, with a September 2 patch deadline for federal civilian agencies. VulnCheck reported scanning of FUXA CVE-2026-25895 (missing authentication plus path traversal, CVSS 9.5, versions through 1.2.9) beginning August 18; about 60 FUXA instances are exposed and no RCE payloads have been dropped yet.

The Hacker NewsAug 20, 05:48 UTC · 27d agoExploit / PoC in the wildCVE-2026-64849 CVE-2026-25895 CVE-2026-25939+1 CVEs

CrowdStrike is buying Seraphic Security to lock down the browser, where work actually happens

CyberScoopJan 13, 15:25 UTC · Jan 13, 2026Exploit / PoC in the wild

Corelight enhances Open NDR to detect AI-driven threats and unknown assets

Help Net SecurityJun 17, 00:00 UTC · Jun 17, 2026Exploit / PoC in the wild

VersaAI delivers AI-assisted enhancements across the Versa Networks portfolio

Help Net SecurityAug 21, 00:00 UTC · Aug 21, 2023Exploit / PoC

Hacking into iPhone is harder than ever, says company paid to hack into iPhones

CyberScoopOct 6, 20:07 UTC · Oct 6, 2017Exploit / PoC in the wild

Leaked NSA cyber weapons were more damaging to Cisco than originally thought

CyberScoopSep 19, 17:30 UTC · Sep 19, 2016Exploit / PoC in the wild

Cellebrite to acquire mobile testing firm Corellium in $200 million deal

CyberScoopJun 5, 14:17 UTC · Jun 5, 2025Exploit / PoC in the wild

Anthropic accuses Chinese labs of trying to illicitly take Claude’s capabilities

CyberScoopFeb 23, 21:02 UTC · Feb 23, 2026Exploit / PoC in the wild

How to hack Facebook accounts exploiting CSRF in Oculus app

Security AffairsJan 17, 09:08 UTC · Jan 17, 2018Exploit / PoC

Volexity Uncovers Zero-Day Campaign Targeting SonicWall VPN Appliances

Security AffairsJul 20, 07:31 UTC · Jul 20, 2026Exploit / PoC in the wildCVE-2026-15409 CVE-2026-15410

ChatGPT Security Issue Enabled Data Theft via Single Prompt

Infosecurity MagazineMar 31, 13:01 UTC · Mar 31, 2026Exploit / PoC in the wild

U.S. CISA adds Samsung mobile devices flaw to its Known Exploited Vulnerabilities catalog

Security AffairsNov 11, 09:00 UTC · Nov 11, 2025Exploit / PoC in the wildCVE-2025-21042 CVE-2025-21043

LANDFALL spyware exploited Samsung zero-day CVE-2025

Security AffairsNov 7, 21:54 UTC · Nov 7, 2025Exploit / PoC in the wildCVE-2025-21042 CVE-2025-21043

U.S. CISA adds a flaw in MongoDB Server to its Known Exploited Vulnerabilities catalog

Security AffairsDec 30, 08:33 UTC · Dec 30, 2025Exploit / PoC in the wildCVE-2025-14847

MongoBleed flaw actively exploited in attacks in the wild

Security AffairsDec 29, 23:21 UTC · Dec 29, 2025Exploit / PoC in the wildCVE-2025-14847

Why transparent AI agents matter more than you think

CyberScoopAug 10, 14:23 UTC · Aug 10, 2026Exploit / PoC in the wild1

Zero-Click WhatsApp Account Takeover Hits iPhone Users Running iOS 16. No Linked Devices, No Warning

Security AffairsMay 25, 10:29 UTC · May 25, 2026Exploit / PoC in the wildCVE-2025-43300 CVE-2025-55177

Researchers question Anthropic claim that AI

Ars Technica · SecurityNov 15, 00:00 UTC · Nov 15, 2025Exploit / PoC

Some ChatGPT browser extensions are stealing your data

CyberScoopJan 26, 19:32 UTC · Jan 26, 2026Exploit / PoC in the wild

Wiz Uncovers Critical Access Bypass Flaw in AI

The Hacker NewsJul 30, 07:43 UTC · Jul 30, 2025Exploit / PoC in the wild