Search: “multi-turn”

61 stories

Searchkeyword smart Sortlatest hot importance relevance

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

CategoryAll AI safety & security 19 Vulnerability 9 Model release 7 AI research 6 Exploit / PoC 4 AI industry 3 Malware 3 Ransomware 3 Data breach 3 AI tools & infra 1 Industry 1 Phishing & fraud 1 Policy & legal 1

SeverityAll critical 15 high 3 medium 18 low 1 info 24

GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code

The Hacker NewsJul 8, 11:21 UTC · Jul 8, 2026AI safety & security1

30

Microsoft turns Copilot Studio into an AI agent control center

Help Net SecurityJun 19, 11:22 UTC · Jun 19, 2026Model release1

50

Week in review: Infostealer dropped via FortiClient EMS flaw, exploited Trend Micro Apex One flaw

Help Net SecurityMay 31, 00:00 UTC · May 31, 2026Malware in the wildCVE-2026-45659 CVE-2026-34926 CVE-2026-35616

60

⚡ Weekly Recap: Exchange 0-Day, npm Worm, Fake AI Repo, Cisco Exploit and More

The Hacker NewsMay 19, 04:33 UTC · May 19, 2026Ransomware in the wildCVE-2026-42897 CVE-2026-20182 CVE-2026-20127

60

25 Open-Source Cybersecurity Tools That Don’T Care About Your Budget

Help Net SecurityApr 27, 00:00 UTC · Apr 27, 2026Vulnerability

30

Week in review: Claude Mythos finds 271 Firefox flaws, Vercel breach

Help Net SecurityApr 26, 00:00 UTC · Apr 26, 2026Ransomware in the wildCVE-2026-20133 CVE-2026-21876 CVE-2026-28950

60

Cisco builds security framework for safe enterprise adoption of AI agents

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

55

Viasat and the terrible, horrible, no good, very bad day

Cisco TalosNov 13, 19:00 UTC · Nov 13, 2025Ransomware

60

AI chat privacy at risk: Microsoft details Whisper Leak side

Security AffairsNov 9, 15:30 UTC · Nov 9, 2025Industry

30

OpenGuardrails: A new open-source model aims to make AI safer for real-world use

Help Net SecurityNov 6, 00:00 UTC · Nov 6, 2025AI safety & security

30

OpenAI Disrupts Russian, North Korean, and Chinese Hackers Misusing ChatGPT for Cyberattacks

The Hacker NewsOct 10, 11:26 UTC · Oct 10, 2025Malware

55

Guess what else GPT

CyberScoopAug 13, 13:37 UTC · Aug 13, 2025Exploit / PoC in the wild

60

GPT-5 Safeguards Bypassed Using Storytelling

Infosecurity MagazineAug 12, 16:45 UTC · Aug 12, 2025Vulnerability

30

Wiz Uncovers Critical Access Bypass Flaw in AI

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

60

Grok-4 Jailbroken Two Days After Release Using Combined Attack

Infosecurity MagazineJul 14, 16:45 UTC · Jul 14, 2025Model release

50

M365 Copilot: New Zero-Click AI Flaw Allows Corporate Data Theft

Infosecurity MagazineJun 13, 10:15 UTC · Jun 13, 2025Vulnerability1

55

The quiet data breach hiding in AI workflows

Help Net SecurityApr 14, 00:00 UTC · Apr 14, 2025Data breach

57

12,000+ API Keys and Passwords Found in Public Datasets Used for LLM Training

The Hacker NewsMar 1, 07:53 UTC · Mar 1, 2025Vulnerability

30

DeepSeek’s Flagship AI Model Under Fire for Security Vulnerabilities

Infosecurity MagazineJan 31, 10:37 UTC · Jan 31, 2025Vulnerability

30

Security Affairs newsletter Round 506 by Pierluigi Paganini

Security AffairsJan 12, 18:03 UTC · Jan 12, 2025Data breach in the wildCVE-2024-43405 CVE-2025-0282

60

New AI Jailbreak Method 'Bad Likert Judge' Boosts Attack Success Rates by Over 60%

The Hacker NewsJan 3, 11:14 UTC · Jan 3, 2025AI safety & security

30