#llm-security
4 articles exploring llm-security. Expert insights and analysis from our editorial team.
Articles
LangChain CVE-2026-34070: load_prompt Path Traversal Patched in 1.2.22, Symlink Bypass Left Open
LangChain CVE-2026-34070 (CVSS 7.5) enables arbitrary file reads via load_prompt traversal; langchain-core 1.2.22 patches direct traversal but leaves a symlink bypass open.
DPrivBench Exposes a Blind Spot: LLMs Can't Reliably Verify Their Own Differential Privacy Guarantees
A new benchmark tests 11 LLMs on 720 DP verification tasks. Top models ace textbook questions — then fall apart on the algorithms that actually appear in production privacy code.
Jailbreak Scaling Laws: Why Reasoning Models Are Now the Cheapest Attack Vector Against Other LLMs
Two converging studies show LRMs achieve 97% autonomous jailbreak success and exponential scaling — here's what that means for production deployments.
Don't Trust the Salt: How Non-English Prompts Break LLM Guardrails
AI safety guardrails are built primarily in English. Research shows they can be trivially bypassed using other languages, exposing critical vulnerabilities in global AI deployment.