Search: “jailbreaks”

54 stories

Searchkeyword smart Sortlatest hot importance relevance

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

CategoryAll AI safety & security 147 Vulnerability 119 Exploit / PoC 79 Malware 53 Ransomware 40 Data breach 18 Policy & legal 18 Model release 14 Phishing & fraud 12 Threat actor 7 Industry 5 Advisory 4 AI industry 4 Tools 3

SeverityAll critical 177 high 75 medium 208 low 22 info 47

Apple fixes CVE-2020-9859 zero

Security AffairsJun 2, 12:29 UTC · Jun 2, 2020Vulnerability CVE-2020-9859

60

U.S. Orders Anthropic to Suspend Fable 5 and Mythos 5 Access for Foreign Nationals

The Hacker NewsJun 15, 00:00 UTC · Jun 15, 2026Vulnerability

55

Russian Hacker Turns Jailbroken Claude Into Pentest Platform

Infosecurity MagazineJul 21, 14:00 UTC · Jul 21, 2026Vulnerability

55

US lifts export controls on Anthropic’s frontier cybersecurity AI models

The RecordJul 1, 13:22 UTC · Jul 1, 2026Vulnerability

55

LlamaFirewall: Open-source framework to detect and mitigate AI centric security risks

Help Net SecurityMay 26, 00:00 UTC · May 26, 2025Vulnerability

55

Cursor AI Code Editor Vulnerability Enables RCE via Malicious MCP File Swaps Post Approval

The Hacker NewsAug 5, 13:04 UTC · Aug 5, 2025Vulnerability CVE-2025-541361

60

Patch, track, repeat

Cisco TalosJul 10, 18:00 UTC · Jul 10, 2025Vulnerability in the wild

60

U.S. Government Releases New AI Security Guidelines for Critical Infrastructure

The Hacker NewsMay 1, 14:16 UTC · May 1, 2024Vulnerability

55

Microsoft Defender for Endpoint now detects jailbroken iOS devices

Help Net SecurityJun 17, 00:00 UTC · Jun 17, 2021Vulnerability

55

OpenAI Previews GPT-5.6 Sol With Restricted Access and Stronger Cyber Safeguards

The Hacker NewsJun 27, 12:20 UTC · Jun 27, 2026Vulnerability

55

Cyber Experts Urge US to Lift Ban on Anthropic’s Frontier AI Models

Infosecurity MagazineJun 15, 10:30 UTC · Jun 15, 2026Vulnerability

55

Cisco builds security framework for safe enterprise adoption of AI agents

Help Net SecurityMar 24, 00:00 UTC · Mar 24, 2026Vulnerability

55

GitLab Duo Vulnerability Enabled Attackers to Hijack AI Responses with Hidden Prompts

The Hacker NewsMay 23, 04:34 UTC · May 23, 2025Vulnerability

55

Researchers Uncover Vulnerabilities in Open

The Hacker NewsOct 29, 16:00 UTC · Oct 29, 2024Vulnerability CVE-2024-7474 CVE-2024-7475 CVE-2024-7473+5 CVEs

60

AI cybersecurity needs to be as multi-layered as the system it's protecting

Help Net SecuritySep 9, 00:00 UTC · Sep 9, 2024Vulnerability

55

Lakera raises $20 million to secure GenAI applications

Help Net SecurityJul 25, 00:00 UTC · Jul 25, 2024Vulnerability

55

AI-as-a-Service Providers Vulnerable to PrivEsc and Cross

The Hacker NewsApr 8, 04:08 UTC · Apr 8, 2024Vulnerability

55

Apple fixes CVE-2021-1844 RCE that affects iOS, macOS, watchOS, and Safari

Security AffairsMar 9, 14:57 UTC · Mar 9, 2021Vulnerability in the wildCVE-2021-1844 CVE-2021-1782

60

Critical flaws patched in ISP Advanced Digital Broadcast Broadband devices

Security AffairsJul 7, 16:45 UTC · Jul 7, 2018Vulnerability CVE-2018-13108 CVE-2018-13109 CVE-2018-13110

60

Why metaphor may dictate your security strategy

Cisco TalosAug 6, 18:00 UTC · Aug 6, 2026Vulnerability1

55

OpenAI expands its cyber defense program with GPT-5.4-Cyber for vetted researchers

Help Net SecurityJul 23, 07:01 UTC · Jul 23, 2026Vulnerability1

55

OpenAI Reveals GPT-5.6 Sol Cybersecurity Model, Restricts Early Access

Infosecurity MagazineJun 29, 15:00 UTC · Jun 29, 2026Vulnerability

55

ASAPP expands adversarial testing for enterprise AI systems

Help Net SecurityMay 21, 00:00 UTC · May 21, 2026Vulnerability

55

Week in review: High-severity LPE vulnerability in the Linux kernel, cPanel 0-day exploited for months

Help Net SecurityMay 3, 00:00 UTC · May 3, 2026Vulnerability in the wildCVE-2026-32202 CVE-2026-21510 CVE-2026-21513+3 CVEs2

60

Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data

The Hacker NewsApr 16, 15:50 UTC · Apr 16, 2026Vulnerability CVE-2025-591451

60

OpenAI Launches GPT-5.4-Cyber with Expanded Access for Security Teams

The Hacker NewsApr 15, 00:00 UTC · Apr 15, 2026Vulnerability

55

OpenAI Expands Bug Bounty to Cover AI Abuse and 'Safety' Concerns

Infosecurity MagazineMar 26, 12:20 UTC · Mar 26, 2026Vulnerability

55

Patch, track, repeat: The 2025 CVE retrospective

Cisco TalosMar 5, 19:00 UTC · Mar 5, 2026Vulnerability in the wildCVE-2026-21385

60

Week in review: Exploited newly patched BeyondTrust RCE, United Airlines CISO on building resilience

Help Net SecurityFeb 15, 00:00 UTC · Feb 15, 2026Vulnerability in the wildCVE-2026-1731 CVE-2024-12356 CVE-2026-1281+2 CVEs

60

Thales expands AI ecosystem protection with application and RAG security tools

Help Net SecurityDec 11, 00:00 UTC · Dec 11, 2025Vulnerability

55

Zero-Click Agentic Browser Attack Can Delete Entire Google Drive Using Crafted Emails

The Hacker NewsDec 7, 12:51 UTC · Dec 7, 2025Vulnerability

55

Upwind adds real-time AI security and posture management to its CNAPP

Help Net SecurityDec 2, 00:00 UTC · Dec 2, 2025Vulnerability

55

Oligo delivers runtime-native security for models and agents

Help Net SecurityNov 20, 00:00 UTC · Nov 20, 2025Vulnerability1

55

Chinese Hackers Automate Cyber-Attacks With AI

Infosecurity MagazineNov 14, 12:15 UTC · Nov 14, 2025Vulnerability

55

Hottest cybersecurity open-source tools of the month: October 2025

Help Net SecurityOct 30, 00:00 UTC · Oct 30, 2025Vulnerability

55

Google's New AI Doesn't Just Find Vulnerabilities — It Rewrites Code to Patch Them

The Hacker NewsOct 7, 16:46 UTC · Oct 7, 2025Vulnerability

55

Anthropic touts safety, security improvements in Claude Sonnet 4.5

CyberScoopSep 30, 16:34 UTC · Sep 30, 2025Vulnerability

55

KernelSU v0.5.7 Flaw Lets Android Apps Gain Root Access

Infosecurity MagazineAug 14, 16:45 UTC · Aug 14, 2025Vulnerability CVE-2024-48336

60

Product Walkthrough: A Look Inside Pillar's AI Security Platform

The Hacker NewsJul 30, 16:12 UTC · Jul 30, 2025Vulnerability

55

Before scaling GenAI, map your LLM usage and risk zones

Help Net SecurityJun 17, 00:00 UTC · Jun 17, 2025Vulnerability

55