An AI CTF write-up detailing a five-stage prompt injection challenge: what failed, what worked, and which LLM jailbreak techniques transfer to real guardrail design. TL;DR We launched our AI Red Teaming Agent against Breaking the Prompt by TrendAI at MTX × DEF CON. The challenge is a five-stage jailbreak CTF: ...
Jailbreaks that won’t die, ChatGPhish turning page summaries into phishing, and 1,652 wide-open Ollama APIs — June’s GenAI security reading, sorted by category.
Our May 2026 top includes practical insights on frontier Anthropic’s Mythos model, new research bypassing GPT-5.4’s safety, LLM-specific CIS lifecycle frameworks, and tools to secure enterprise AI deployments against automated exploits.
Explore 19 resources covering the massive LiteLLM supply chain compromise, 128K+ context window poisoning, compound RAG database exploits, and the latest defense approaches for April 2026.
March’s GenAI security digest highlights a shift toward industrial-scale AI exploitation and systemic manipulation. Explore 22 resources covering real life distillation attacks, AI recommendation poisoning, new exploits like “Large Language Lobotomy,” and the latest defense architectures for GenAI.
February’s GenAI security digest highlights practical attacks on production AI systems. Explore over 40 resources covering indirect prompt injection in Google Gemini and Perplexity, new jailbreak techniques like “Semantic Chaining,” and the latest defense frameworks for 2026.
How we extracted the Opus 4.6 system prompt the day after its release and what we learned about the model’s security constraints and guardrails.
The GenAI security landscape entered 2026 with urgent warnings from global agencies and breakthrough research. CISA and international partners released comprehensive frameworks for securing AI in critical infrastructure, while researchers discovered that AI-generated code now shows 1.7x higher bug density than human-written code. Major stakeholders, including the UK NCSC and ...
GenAI Security: Essential Resources for December 2025 Generative AI has rapidly become ubiquitous in business applications, and the installed base of AI assistants already exceeds one billion users. Security considerations for this wide adoption range from sophisticated prompt-injection attacks to novel side-channel vulnerabilities, and the threat landscape for AI systems ...
Introducing Universal LLM Jailbreak approach. Subscribe for the latest AI Jailbreaks, Attacks and Vulnerabilities If you want more news and valuable insights on a weekly and even daily basis, follow our LinkedIn to join a community of other experts discussing the latest news. In the world of artificial intelligence (AI), [...]
