Search: “llm serving”

32 stories

Searchkeyword smart Sortlatest hot importance relevance

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

CategoryAll Malware 45 Vulnerability 32 AI safety & security 29 Threat actor 28 Exploit / PoC 21 Policy & legal 21 Ransomware 19 Model release 13 AI research 11 Phishing & fraud 11 Research 9 AI industry 8 AI tools & infra 7 Data breach 6

SeverityAll critical 77 high 48 medium 60 low 31 info 51

Researchers Find Serious AI Bugs Exposing Meta, Nvidia, and Microsoft Inference Frameworks

The Hacker NewsNov 15, 00:00 UTC · Nov 15, 2025Vulnerability CVE-2024-50050 CVE-2025-30165 CVE-2025-23254+1 CVEs

60

OWASP Warns of Growing Data Exposure Risk from AI in New Top 10 List

Infosecurity MagazineNov 20, 11:00 UTC · Nov 20, 2024Vulnerability

55

Is Agentic AI too smart for your own good?

Help Net SecuritySep 9, 09:52 UTC · Sep 9, 2025Vulnerability

55

Ruflo MCP Flaw Lets Unauthenticated Attackers Run Commands and Poison AI Memory

The Hacker NewsJul 29, 15:39 UTC · Jul 29, 2026Vulnerability CVE-2026-597261

60

Critical Vulnerability in Anthropic's MCP Exposes Developer Machines to Remote Exploits

The Hacker NewsJul 4, 09:23 UTC · Jul 4, 2025Vulnerability CVE-2025-49596

60

Cequence Unified API Protection defends against attacks targeting AI applications

Help Net SecurityAug 7, 00:00 UTC · Aug 7, 2024Vulnerability

30

"Context bombs" can frustrate AI-driven attacks, researchers found

Help Net SecurityJul 14, 00:00 UTC · Jul 14, 2026Vulnerability

30

Gemini hackers can deliver more potent attacks with a helping hand from… Gemini

Ars Technica · SecurityMar 28, 11:00 UTC · Mar 28, 2025Vulnerability

30

Before scaling GenAI, map your LLM usage and risk zones

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

55

Exclusive: OpenAI’s Atlas browser — and others — can be tricked by manipulated web content

CyberScoopOct 28, 18:27 UTC · Oct 28, 2025Vulnerability

42

Week in review: cPanel vulnerability actively exploited, DigiCert breach, LinkedIn job scams

Help Net SecurityMay 10, 00:00 UTC · May 10, 2026Vulnerability in the wildCVE-2026-41940 CVE-2026-4670 CVE-2026-5174+4 CVEs

60

Side-Channel Attacks Against LLMs

Schneier on SecurityMar 14, 11:28 UTC · Mar 14, 2026Vulnerability

30

Lakera raises $20 million to secure GenAI applications

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

55

Palo Alto Networks Prisma AIRS safeguards the enterprise AI ecosystem

Help Net SecurityApr 28, 00:00 UTC · Apr 28, 2025Vulnerability

55

Italy Bans Chinese DeepSeek AI Over Data Privacy and Ethical Concerns

The Hacker NewsFeb 1, 06:31 UTC · Feb 1, 2025Vulnerability

42

Anthropic's Fable and the State of AI

Schneier on SecurityJun 19, 11:03 UTC · Jun 19, 2026Vulnerability

30

Arctic Wolf launches Cipher to enhance security investigations with AI insights

Help Net SecurityApr 29, 00:00 UTC · Apr 29, 2025Vulnerability

30

With AI's help, North Korean hackers stumbled into a near-undetectable attack

Help Net SecurityApr 23, 00:00 UTC · Apr 23, 2026Vulnerability

42

Stealthy attack serves poisoned web pages only to AI agents

Help Net SecurityApr 21, 13:00 UTC · Apr 21, 2026Vulnerability

30

ArmorCode Anya accelerates critical security decisions

Help Net SecurityApr 28, 00:00 UTC · Apr 28, 2025Vulnerability

55

AutoPatchBench: Meta's new way to test AI bug fixing tools

Help Net SecurityMay 21, 00:00 UTC · May 21, 2025Vulnerability

30

Friday Squid Blogging: NGC 1068 Is the "Squid Galaxy"

Schneier on SecurityJun 2, 03:22 UTC · Jun 2, 2025Vulnerability1

30

Don't let these open-source cybersecurity tools slip under your radar

Help Net SecurityJan 27, 00:00 UTC · Jan 27, 2025Vulnerability

30

Friday Squid Blogging: New Giant Squid Video

Schneier on SecurityApr 17, 21:05 UTC · Apr 17, 2026Vulnerability

30

Week in review: Backdoor found in SOHO devices running Linux, high-risk WinRAR RCE flaw patched

Help Net SecurityJun 29, 00:00 UTC · Jun 29, 2025Vulnerability CVE-2025-6218 CVE-2025-49144 CVE-2025-5777

60

LMDeploy CVE-2026-33626 Flaw Exploited Within 13 Hours of Disclosure

The Hacker NewsApr 27, 04:26 UTC · Apr 27, 2026Vulnerability in the wildCVE-2026-33626 CVE-2026-0740 CVE-2026-3844

60

LangSmith Bug Could Expose OpenAI Keys and User Data via Malicious Agents

The Hacker NewsJun 17, 17:37 UTC · Jun 17, 2025Vulnerability

30

Week in review: Sudo local privilege escalation flaws fixed, Google patches actively exploited Chrome

Help Net SecurityJul 6, 00:00 UTC · Jul 6, 2025Vulnerability in the wildCVE-2025-32462 CVE-2025-32463 CVE-2025-6554+4 CVEs

60

AI Summarization Optimization

Schneier on SecurityNov 15, 00:00 UTC · Nov 15, 2025Vulnerability

55

ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface

The Hacker NewsMay 29, 18:07 UTC · May 29, 2026Vulnerability CVE-2026-25592 CVE-2026-26030

47

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

Week in review: Fully patched FortiGate firewalls are getting compromised, attackers probe Cisco RCE flaw

Help Net SecurityJan 25, 00:00 UTC · Jan 25, 2026Vulnerability CVE-2026-20045 CVE-2025-59718

60