Prompt injection and model defense.
An article joins this feed when it matches these terms. Each one is also a search of its own.
Simulation tools love to show the run where they were right. This is a run where one was wrong, and why it was still worth doing. csca.ai sells prep for the CSCA exam (the test for studying in China)…
In the spirit of Hacktoberfest's 'Slow and Steady' sloth philosophy: moving too fast and breaking things is how API keys leak and injection flaws reach production. SecureScope brings steady, methodical, privacy-preserving AI audits to your workflow — because slow and steady…
Inspect AI is the open-source evaluation framework from the UK AI Security Institute. You write a task (dataset, solver, scorer), run inspect eval, and get a log you can browse. It has first-party providers for the big labs, plus a…
The Beijing-based company announced the safeguards on Saturday while unveiling Kimi K3.1 Pro, which it describes as its most capable model in the three-trillion-parameter class of open-weight artificial intelligence systems. Moonshot plans to release the model's weights — files that enable developers…
OpenAI has announced plans to conduct frontier model training with no live internet access, as it resumes reinforcement learning (RL) training and internal inference of its most advanced AI models. "Based on the current state of alignment research, monitoring systems,…
Mistral Large 4, the 1-trillion-parameter model announced in public preview on October 6, is approaching its self-imposed end-of-month release window. As of October 23—Day 22 of 31—the weights and commercial license remain unpublished. On Hugging Face, the model card fields for both weights…
Chinese AI startup Moonshot AI is deliberately limiting the hacking capabilities of its latest artificial intelligence model, highlighting a growing dilemma for the industry: how do companies make AI more powerful without making cyberattacks easier to carry out? The company…
VEKTOR 2.0 is out of the workshop, and the list of what is new runs longer than we expected. Skim the highlights below, or read the technical section if you want to see how it works. What we believe in: Sovereign…
AI-powered web browsers are being hailed as the future of internet browsing, yet I haven't found one I actually want to use—or would be willing to pay for—until some fundamental issues are addressed. All the AI browsers I've…
Tagged with security, vulnerabilitymanagement. #five-ways-a-groovy-sandbox-leaked-and-what-that-says-about-sandbox-design Five ways a Groovy sandbox leaked, and what that says about sandbox design Jenkins published five Script Security Plugin advisories on 16 September 2026. Each describes a separate route from a sandboxed Pipeline script to arbitrary code…