Breaking
SPLX Blog
SPLX Blog
The latest in AI security
The latest in AI security
Subscribe
Subscribe
Subscribe
Subscribe to our newsletter
Featured
Research
Aug 8, 2025
6 min read
GPT-5 may be smarter. But is it safer? We tested the model across 1,000+ adversarial prompts. The results show just how much alignment depends on infrastructure, and not model magic.
Dorian Granoša
All
Blog
Research
News
Product Updates
Research
Aug 11, 2025
7 min read
GLM-4.5. Can It Pass the Enterprise AI Security Test Where Kimi K2 Failed?
Mateja Vuradin
Product Update
Jul 31, 2025
5 min read
Simplify Red Team Results & Speed Up Remediation: SPLX Launches “Analyze with AI"
Jurica Nekić
News
Jul 30, 2025
5 min read
SPLX Launches Next Phase of Growth by Unveiling End-to-End Security Platform for AI
The SPLX Team
Research
Jul 17, 2025
6 min read
We Broke Kimi K2, the New Open Model, in Minutes. Can It Be Made Safe?
Mateja Vuradin
Research
Jul 14, 2025
7 min read
Grok 4 Without Guardrails? Total Safety Failure. We Tested and Fixed Elon’s New Model.
Dorian Granoša
News
Jul 3, 2025
5 min read
SplxAI Announces Partnership with Databricks to Provide Security Across the Full Agentic AI Lifecycle
Kelly Mitchell
Research
Jun 24, 2025
6 min read
OpenAI o3-pro vs. GPT-4o: Unreasonable Amount of Reasoning?
Dominik Jurinčić
News
Jun 16, 2025
6 min read
SplxAI Adds LLM Benchmarks to Help Enterprises Select the Most Secure Models
Luka Kamber
Blog
Jun 10, 2025
6 min read
Is Single-Message Jailbreaking Dead? What This Means for AI Security
Dominik Jurinčić
Product Update
Jun 9, 2025
7 min read
Scanning AutoGen Workflows with Agentic Radar
Josip Srzić
Blog
May 27, 2025
7 min read
OpenAI Used Agentic Radar to Judge Europe’s Largest AI Hackathon – Here Are The Results
Dorian Granoša
News
May 21, 2025
5 min read
SplxAI Is Now Available In The Microsoft Azure Marketplace
Luka Kamber
Product Update
May 14, 2025
6 min read
Harden the System Prompts in AI Workflows with Agentic Radar
Josip Srzić
Product Update
Apr 29, 2025
6 min read
SplxAI Adds Native Support for Glean AI Assistants and Agents
Luka Kamber
Research
Apr 22, 2025
16 min read
The Missing GPT-4.1 Safety Report: Switch from GPT-4o to GPT-4.1 with Caution
Dominik Jurinčić
News
Apr 17, 2025
5 min read
OpenPolicy and SplxAI Partner to Close the Gap Between Emerging AI Policies and AI Security
Luka Kamber
Product Update
Apr 16, 2025
4 min read
Agentic Radar Now Detects MCP Servers in Agentic Workflows
Josip Srzić
News
Apr 16, 2025
6 min read
SplxAI Enables CISOs to Secure Agentic AI with Industry’s First Agentic Workflow Transparency Tool
The SplxAI Team
Product Update
Apr 2, 2025
9 min read
OpenAI Agents SDK: Transparent Workflows with Agentic Radar
Josip Srzić
Research
Apr 1, 2025
11 min read
Exploiting Agentic Workflows: Prompt Injections in Multi-Agent AI Systems
Dorian Schultz
News
Mar 26, 2025
5 min read
SplxAI Closes $7M Seed Funding Round to Help Organizations Secure Agentic AI Systems
The SplxAI Team
Product Update
Mar 20, 2025
5 min read
Scanning n8n Workflows with Agentic Radar
Dominik Jurinčić
Product Update
Mar 13, 2025
7 min read
Enhancing AI Transparency: Scanning CrewAI Workflows with Agentic Radar
Josip Srzić
Blog
Mar 12, 2025
10 min read
Understanding Agentic AI: What It Is and How to Build It Securely
Luka Kamber
News
Mar 10, 2025
5 min read
Introducing Agentic Radar: The New OSS Tool for AI Workflow Transparency
The SplxAI Team
Blog
Feb 21, 2025
7 min read
AI Transparency: Connecting AI Red Teaming and Compliance
Ante Gojsalić
Blog
Feb 10, 2025
10 min read
Mastering AI Red Teaming: Strategies for Securing AI Systems
Luka Kamber
News
Feb 3, 2025
3 min read
SplxAI and Number™ Partner to Enable the Secure Development of AI Assistants
Luka Kamber
Research
Jan 31, 2025
15 min read
DeepSeek-r1 vs. OpenAI-o1: The Ultimate Security Showdown
Dorian Schultz
Research
Jan 24, 2025
10 min read
Jailbreaking Multimodal LLMs: New Exploits Targeting State-of-the-Art Models
Leon Zrnić
Blog
Dec 30, 2024
9 min read
AI Security in 2025: 5 Key Trends
Kristian Kamber
Blog
Dec 18, 2024
13 min read
System Prompt Hardening: The Backbone of Automated AI Security
Ante Gojsalić
Research
Dec 9, 2024
5 min read
OpenAI’s Voice Model Preview: What It Means for AI Voice Jailbreaks and Security
Dorian Granoša
News
Dec 4, 2024
4 min read
SplxAI's Platform for AI Red Teaming Launches on AWS Marketplace
Kristian Kamber
Blog
Nov 18, 2024
7 min read
Google SAIF or OWASP LLM Top 10: Which AI Security Framework to Follow?
Ante Gojsalić
Blog
Oct 15, 2024
6 min read
Unlocking real business value with secure GenAI applications
Luka Kamber
Blog
Oct 10, 2024
5 min read
RAG Poisoning in Enterprise Knowledge Sources
Ante Gojsalić
Research
Oct 4, 2024
9 min read
Chat Mirroring: How AI assistants can leak your data to hackers
Dorian Schultz
Blog
Sep 30, 2024
7 min read
Proby & Probe: A Love Story
Ante Gojsalić
Research
Sep 23, 2024
8 min read
Character AI Jailbreak Prompt: Jailbreaking Content Filters in Character AI
Dorian Schultz
News
Sep 16, 2024
4 min read
SplxAI and Infobip Partner to Deliver Safe and Secure Conversational AI Applications
Luka Kamber
News
Sep 10, 2024
2 min read
SplxAI raises $2M in Pre-Seed funding round
Kristian Kamber
News
Sep 3, 2024
4 min read
Hackrate and SplxAI partner to streamline GenAI Security for ethical hackers
Luka Kamber
News
Aug 29, 2024
6 min read
Lasso Security and SplxAI partner to synergize Red and Blue Teaming for GenAI risks
Luka Kamber
Research
Aug 28, 2024
9 min read
Exploiting system prompt leaks with phishing attacks
Dorian Schultz
Blog
Jul 30, 2024
8 min read
Profanity Patterns: ChatGPT's date-linked moodiness
Dorian Schultz
Blog
Jul 17, 2024
6 min read
IKEA, ChatGPT, and the Bias Dilemma
Dorian Schultz
Blog
Jun 16, 2024
3 min read
Voice Prompt Injection on OpenAI's ChatGPT
Marko Lihter
Blog
May 27, 2024
4 min read
How to Lose Millions with Bad Guardrails: Stricter Is Not Better
Marko Lihter
Blog
May 24, 2024
3 min read
PTaaS (Penetration Testing as a Service) vs Manual Pen-Testing
Marko Lihter
Blog
May 16, 2024
5 min read
Meeting EU AI Act Compliance with SplxAI
Marko Lihter
Blog
May 8, 2024
4 min read
AI Security Checklist: Don't let your AI go rogue
Marko Lihter
Blog
Apr 10, 2024
8 min read
Intro to Red Teaming LLMs: A Proactive Shield for Chatbots and Beyond
Marko Lihter
Blog
Mar 26, 2024
6 min read
Another Brick in the Firewall
Ante Gojsalić
Blog
Mar 9, 2024
7 min read
Mission Possible: Trustworthy GenAI
Ante Gojsalić
Blog
Mar 4, 2024
5 min read
The AI Security Imperative
Ante Gojsalić
All
Blog
Research
News
Product Updates
Research
Aug 11, 2025
7 min read
GLM-4.5. Can It Pass the Enterprise AI Security Test Where Kimi K2 Failed?
Mateja Vuradin
Product Update
Jul 31, 2025
5 min read
Simplify Red Team Results & Speed Up Remediation: SPLX Launches “Analyze with AI"
Jurica Nekić
News
Jul 30, 2025
5 min read
SPLX Launches Next Phase of Growth by Unveiling End-to-End Security Platform for AI
The SPLX Team
Research
Jul 17, 2025
6 min read
We Broke Kimi K2, the New Open Model, in Minutes. Can It Be Made Safe?
Mateja Vuradin
Research
Jul 14, 2025
7 min read
Grok 4 Without Guardrails? Total Safety Failure. We Tested and Fixed Elon’s New Model.
Dorian Granoša
News
Jul 3, 2025
5 min read
SplxAI Announces Partnership with Databricks to Provide Security Across the Full Agentic AI Lifecycle
Kelly Mitchell
Research
Jun 24, 2025
6 min read
OpenAI o3-pro vs. GPT-4o: Unreasonable Amount of Reasoning?
Dominik Jurinčić
News
Jun 16, 2025
6 min read
SplxAI Adds LLM Benchmarks to Help Enterprises Select the Most Secure Models
Luka Kamber
Blog
Jun 10, 2025
6 min read
Is Single-Message Jailbreaking Dead? What This Means for AI Security
Dominik Jurinčić
Product Update
Jun 9, 2025
7 min read
Scanning AutoGen Workflows with Agentic Radar
Josip Srzić
Blog
May 27, 2025
7 min read
OpenAI Used Agentic Radar to Judge Europe’s Largest AI Hackathon – Here Are The Results
Dorian Granoša
News
May 21, 2025
5 min read
SplxAI Is Now Available In The Microsoft Azure Marketplace
Luka Kamber
Product Update
May 14, 2025
6 min read
Harden the System Prompts in AI Workflows with Agentic Radar
Josip Srzić
Product Update
Apr 29, 2025
6 min read
SplxAI Adds Native Support for Glean AI Assistants and Agents
Luka Kamber
Research
Apr 22, 2025
16 min read
The Missing GPT-4.1 Safety Report: Switch from GPT-4o to GPT-4.1 with Caution
Dominik Jurinčić
News
Apr 17, 2025
5 min read
OpenPolicy and SplxAI Partner to Close the Gap Between Emerging AI Policies and AI Security
Luka Kamber
Product Update
Apr 16, 2025
4 min read
Agentic Radar Now Detects MCP Servers in Agentic Workflows
Josip Srzić
News
Apr 16, 2025
6 min read
SplxAI Enables CISOs to Secure Agentic AI with Industry’s First Agentic Workflow Transparency Tool
The SplxAI Team
Product Update
Apr 2, 2025
9 min read
OpenAI Agents SDK: Transparent Workflows with Agentic Radar
Josip Srzić
Research
Apr 1, 2025
11 min read
Exploiting Agentic Workflows: Prompt Injections in Multi-Agent AI Systems
Dorian Schultz
News
Mar 26, 2025
5 min read
SplxAI Closes $7M Seed Funding Round to Help Organizations Secure Agentic AI Systems
The SplxAI Team
Product Update
Mar 20, 2025
5 min read
Scanning n8n Workflows with Agentic Radar
Dominik Jurinčić
Product Update
Mar 13, 2025
7 min read
Enhancing AI Transparency: Scanning CrewAI Workflows with Agentic Radar
Josip Srzić
Blog
Mar 12, 2025
10 min read
Understanding Agentic AI: What It Is and How to Build It Securely
Luka Kamber
News
Mar 10, 2025
5 min read
Introducing Agentic Radar: The New OSS Tool for AI Workflow Transparency
The SplxAI Team
Blog
Feb 21, 2025
7 min read
AI Transparency: Connecting AI Red Teaming and Compliance
Ante Gojsalić
Blog
Feb 10, 2025
10 min read
Mastering AI Red Teaming: Strategies for Securing AI Systems
Luka Kamber
News
Feb 3, 2025
3 min read
SplxAI and Number™ Partner to Enable the Secure Development of AI Assistants
Luka Kamber
Research
Jan 31, 2025
15 min read
DeepSeek-r1 vs. OpenAI-o1: The Ultimate Security Showdown
Dorian Schultz
Research
Jan 24, 2025
10 min read
Jailbreaking Multimodal LLMs: New Exploits Targeting State-of-the-Art Models
Leon Zrnić
Blog
Dec 30, 2024
9 min read
AI Security in 2025: 5 Key Trends
Kristian Kamber
Blog
Dec 18, 2024
13 min read
System Prompt Hardening: The Backbone of Automated AI Security
Ante Gojsalić
Research
Dec 9, 2024
5 min read
OpenAI’s Voice Model Preview: What It Means for AI Voice Jailbreaks and Security
Dorian Granoša
News
Dec 4, 2024
4 min read
SplxAI's Platform for AI Red Teaming Launches on AWS Marketplace
Kristian Kamber
Blog
Nov 18, 2024
7 min read
Google SAIF or OWASP LLM Top 10: Which AI Security Framework to Follow?
Ante Gojsalić
Blog
Oct 15, 2024
6 min read
Unlocking real business value with secure GenAI applications
Luka Kamber
Blog
Oct 10, 2024
5 min read
RAG Poisoning in Enterprise Knowledge Sources
Ante Gojsalić
Research
Oct 4, 2024
9 min read
Chat Mirroring: How AI assistants can leak your data to hackers
Dorian Schultz
Blog
Sep 30, 2024
7 min read
Proby & Probe: A Love Story
Ante Gojsalić
Research
Sep 23, 2024
8 min read
Character AI Jailbreak Prompt: Jailbreaking Content Filters in Character AI
Dorian Schultz
News
Sep 16, 2024
4 min read
SplxAI and Infobip Partner to Deliver Safe and Secure Conversational AI Applications
Luka Kamber
News
Sep 10, 2024
2 min read
SplxAI raises $2M in Pre-Seed funding round
Kristian Kamber
News
Sep 3, 2024
4 min read
Hackrate and SplxAI partner to streamline GenAI Security for ethical hackers
Luka Kamber
News
Aug 29, 2024
6 min read
Lasso Security and SplxAI partner to synergize Red and Blue Teaming for GenAI risks
Luka Kamber
Research
Aug 28, 2024
9 min read
Exploiting system prompt leaks with phishing attacks
Dorian Schultz
Blog
Jul 30, 2024
8 min read
Profanity Patterns: ChatGPT's date-linked moodiness
Dorian Schultz
Blog
Jul 17, 2024
6 min read
IKEA, ChatGPT, and the Bias Dilemma
Dorian Schultz
Blog
Jun 16, 2024
3 min read
Voice Prompt Injection on OpenAI's ChatGPT
Marko Lihter
Blog
May 27, 2024
4 min read
How to Lose Millions with Bad Guardrails: Stricter Is Not Better
Marko Lihter
Blog
May 24, 2024
3 min read
PTaaS (Penetration Testing as a Service) vs Manual Pen-Testing
Marko Lihter
Blog
May 16, 2024
5 min read
Meeting EU AI Act Compliance with SplxAI
Marko Lihter
Blog
May 8, 2024
4 min read
AI Security Checklist: Don't let your AI go rogue
Marko Lihter
Blog
Apr 10, 2024
8 min read
Intro to Red Teaming LLMs: A Proactive Shield for Chatbots and Beyond
Marko Lihter
Blog
Mar 26, 2024
6 min read
Another Brick in the Firewall
Ante Gojsalić
Blog
Mar 9, 2024
7 min read
Mission Possible: Trustworthy GenAI
Ante Gojsalić
Blog
Mar 4, 2024
5 min read
The AI Security Imperative
Ante Gojsalić
All
Blog
Research
News
Product Updates
Research
Aug 11, 2025
7 min read
GLM-4.5. Can It Pass the Enterprise AI Security Test Where Kimi K2 Failed?
Mateja Vuradin
Product Update
Jul 31, 2025
5 min read
Simplify Red Team Results & Speed Up Remediation: SPLX Launches “Analyze with AI"
Jurica Nekić
News
Jul 30, 2025
5 min read
SPLX Launches Next Phase of Growth by Unveiling End-to-End Security Platform for AI
The SPLX Team
Research
Jul 17, 2025
6 min read
We Broke Kimi K2, the New Open Model, in Minutes. Can It Be Made Safe?
Mateja Vuradin
Research
Jul 14, 2025
7 min read
Grok 4 Without Guardrails? Total Safety Failure. We Tested and Fixed Elon’s New Model.
Dorian Granoša
News
Jul 3, 2025
5 min read
SplxAI Announces Partnership with Databricks to Provide Security Across the Full Agentic AI Lifecycle
Kelly Mitchell
Research
Jun 24, 2025
6 min read
OpenAI o3-pro vs. GPT-4o: Unreasonable Amount of Reasoning?
Dominik Jurinčić
News
Jun 16, 2025
6 min read
SplxAI Adds LLM Benchmarks to Help Enterprises Select the Most Secure Models
Luka Kamber
Blog
Jun 10, 2025
6 min read
Is Single-Message Jailbreaking Dead? What This Means for AI Security
Dominik Jurinčić
Product Update
Jun 9, 2025
7 min read
Scanning AutoGen Workflows with Agentic Radar
Josip Srzić
Blog
May 27, 2025
7 min read
OpenAI Used Agentic Radar to Judge Europe’s Largest AI Hackathon – Here Are The Results
Dorian Granoša
News
May 21, 2025
5 min read
SplxAI Is Now Available In The Microsoft Azure Marketplace
Luka Kamber
Product Update
May 14, 2025
6 min read
Harden the System Prompts in AI Workflows with Agentic Radar
Josip Srzić
Product Update
Apr 29, 2025
6 min read
SplxAI Adds Native Support for Glean AI Assistants and Agents
Luka Kamber
Research
Apr 22, 2025
16 min read
The Missing GPT-4.1 Safety Report: Switch from GPT-4o to GPT-4.1 with Caution
Dominik Jurinčić
News
Apr 17, 2025
5 min read
OpenPolicy and SplxAI Partner to Close the Gap Between Emerging AI Policies and AI Security
Luka Kamber
Product Update
Apr 16, 2025
4 min read
Agentic Radar Now Detects MCP Servers in Agentic Workflows
Josip Srzić
News
Apr 16, 2025
6 min read
SplxAI Enables CISOs to Secure Agentic AI with Industry’s First Agentic Workflow Transparency Tool
The SplxAI Team
Product Update
Apr 2, 2025
9 min read
OpenAI Agents SDK: Transparent Workflows with Agentic Radar
Josip Srzić
Research
Apr 1, 2025
11 min read
Exploiting Agentic Workflows: Prompt Injections in Multi-Agent AI Systems
Dorian Schultz
News
Mar 26, 2025
5 min read
SplxAI Closes $7M Seed Funding Round to Help Organizations Secure Agentic AI Systems
The SplxAI Team
Product Update
Mar 20, 2025
5 min read
Scanning n8n Workflows with Agentic Radar
Dominik Jurinčić
Product Update
Mar 13, 2025
7 min read
Enhancing AI Transparency: Scanning CrewAI Workflows with Agentic Radar
Josip Srzić
Blog
Mar 12, 2025
10 min read
Understanding Agentic AI: What It Is and How to Build It Securely
Luka Kamber
News
Mar 10, 2025
5 min read
Introducing Agentic Radar: The New OSS Tool for AI Workflow Transparency
The SplxAI Team
Blog
Feb 21, 2025
7 min read
AI Transparency: Connecting AI Red Teaming and Compliance
Ante Gojsalić
Blog
Feb 10, 2025
10 min read
Mastering AI Red Teaming: Strategies for Securing AI Systems
Luka Kamber
News
Feb 3, 2025
3 min read
SplxAI and Number™ Partner to Enable the Secure Development of AI Assistants
Luka Kamber
Research
Jan 31, 2025
15 min read
DeepSeek-r1 vs. OpenAI-o1: The Ultimate Security Showdown
Dorian Schultz
Research
Jan 24, 2025
10 min read
Jailbreaking Multimodal LLMs: New Exploits Targeting State-of-the-Art Models
Leon Zrnić
Blog
Dec 30, 2024
9 min read
AI Security in 2025: 5 Key Trends
Kristian Kamber
Blog
Dec 18, 2024
13 min read
System Prompt Hardening: The Backbone of Automated AI Security
Ante Gojsalić
Research
Dec 9, 2024
5 min read
OpenAI’s Voice Model Preview: What It Means for AI Voice Jailbreaks and Security
Dorian Granoša
News
Dec 4, 2024
4 min read
SplxAI's Platform for AI Red Teaming Launches on AWS Marketplace
Kristian Kamber
Blog
Nov 18, 2024
7 min read
Google SAIF or OWASP LLM Top 10: Which AI Security Framework to Follow?
Ante Gojsalić
Blog
Oct 15, 2024
6 min read
Unlocking real business value with secure GenAI applications
Luka Kamber
Blog
Oct 10, 2024
5 min read
RAG Poisoning in Enterprise Knowledge Sources
Ante Gojsalić
Research
Oct 4, 2024
9 min read
Chat Mirroring: How AI assistants can leak your data to hackers
Dorian Schultz
Blog
Sep 30, 2024
7 min read
Proby & Probe: A Love Story
Ante Gojsalić
Research
Sep 23, 2024
8 min read
Character AI Jailbreak Prompt: Jailbreaking Content Filters in Character AI
Dorian Schultz
News
Sep 16, 2024
4 min read
SplxAI and Infobip Partner to Deliver Safe and Secure Conversational AI Applications
Luka Kamber
News
Sep 10, 2024
2 min read
SplxAI raises $2M in Pre-Seed funding round
Kristian Kamber
News
Sep 3, 2024
4 min read
Hackrate and SplxAI partner to streamline GenAI Security for ethical hackers
Luka Kamber
News
Aug 29, 2024
6 min read
Lasso Security and SplxAI partner to synergize Red and Blue Teaming for GenAI risks
Luka Kamber
Research
Aug 28, 2024
9 min read
Exploiting system prompt leaks with phishing attacks
Dorian Schultz
Blog
Jul 30, 2024
8 min read
Profanity Patterns: ChatGPT's date-linked moodiness
Dorian Schultz
Blog
Jul 17, 2024
6 min read
IKEA, ChatGPT, and the Bias Dilemma
Dorian Schultz
Blog
Jun 16, 2024
3 min read
Voice Prompt Injection on OpenAI's ChatGPT
Marko Lihter
Blog
May 27, 2024
4 min read
How to Lose Millions with Bad Guardrails: Stricter Is Not Better
Marko Lihter
Blog
May 24, 2024
3 min read
PTaaS (Penetration Testing as a Service) vs Manual Pen-Testing
Marko Lihter
Blog
May 16, 2024
5 min read
Meeting EU AI Act Compliance with SplxAI
Marko Lihter
Blog
May 8, 2024
4 min read
AI Security Checklist: Don't let your AI go rogue
Marko Lihter
Blog
Apr 10, 2024
8 min read
Intro to Red Teaming LLMs: A Proactive Shield for Chatbots and Beyond
Marko Lihter
Blog
Mar 26, 2024
6 min read
Another Brick in the Firewall
Ante Gojsalić
Blog
Mar 9, 2024
7 min read
Mission Possible: Trustworthy GenAI
Ante Gojsalić
Blog
Mar 4, 2024
5 min read
The AI Security Imperative
Ante Gojsalić
