Knowledge catalogue
Reuters: Z.ai says GLM-5.3 scores 84.5% on CyberGym, vs. Mythos 5's 83.8%, and its most sensitive cybersecurity functions will only be available to verified users — Chinese AI startup Z.ai said on Fri
Artificial intelligence is a double-edged sword when it comes to cybersecurity. It is giving defenders new ways to sift through vast amounts of telemetry, identify anomalous behavior and automate rout
arXiv:2608.08477v1 Announce Type: new Abstract: We present VectraYX-Vision-1B, a sub-2B vision-language model (VLM) for Spanish/LATAM cybersecurity imagery, coupling a frozen SigLIP-so400m encoder to
Defensive cybersecurity startup Corma Labs Ltd. today announced it has raised 60 million in seed funding to build a foundation model purpose-built for security defense. Founded in 2025, Corma runs off
Sam Sabin / Axios: OpenAI releases GPT-5.6-Cyber, a more cyber-permissive version of GPT-5.6 Sol, to some partners and expands its Daybreak cybersecurity initiative — OpenAI is introducing a more cybe
A large language model developed by Meta Platforms Inc. hacked a third party organization during a cybersecurity evaluation. The Facebook parent disclosed the incident on Wednesday without specifying
Cybersecurity isn’t a fortress problem, it’s an immunity problem. Think vaccines. Eliminating pathogen is not practically possible. Vaccines don’t eliminate pathogens. They teach the immune system to
Hugging Face CEO Clément Delague says “AI is actually an opportunity to fix a lot of the cybersecurity problems” because his company used Nvidia’s version of a Chinese open model to defend itself agai
arXiv:2409.08521v2 Announce Type: replace-cross Abstract: In cybersecurity practice, new forms of cyberattacks continuously emerge, deliberately designed to evade defense systems that rely on previous
one of the top cybersecurity models, post-trained from open weights by @depthfirstlabs on @FireworksAI_HQ long-horizon RL is as much an infra problem as a research one: 100+ turn rollouts, async/pipel
Investigating three real-world incidents in our cybersecurity evaluations It happened again! This is turning into something of a pattern. Last week OpenAI accidentally exploited Hugging Face when one
Microsoft Corp. today introduced its first in-house cybersecurity model, MAI-Cyber-1-Flash, and a companion agentic system called Project Perception that fields teams of artificial intelligence agents
Jaspreet Singh / Reuters: Nvidia forms the Open Secure AI Alliance, a coalition including CrowdStrike, Hugging Face, and Dell to develop and share tools for AI safety and cybersecurity — Nvidia (NVDA.
New York Times: Microsoft introduces MAI-Cyber-1-Flash, an AI model trained for cybersecurity, and launches Perception, an agentic security system to patch vulnerabilities — As some executives fret ov
In July 2026, Clement Delangue tweeted that “Open‑source is not the cause of the cybersecurity crisis, it’s the solution!” linking to the Hugging Face page *fdtn‑ai* (https://huggingface.co/fdtn-ai).
AI models pushing the frontier are a growing challenge for cybersecurity. A few weeks ago, I asked Demis what's underhyped in AI right now and on his mind: 'I'm very excited about this new agentic era
arXiv:2607.06963v1 Announce Type: cross Abstract: Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic
Paul Sandle / Reuters: US cybersecurity and data resilience company Rubrik plans to invest 500M+ in the UK over the next five years and establish its European headquarters in London — U.S. cybersecuri
arXiv:2606.30953v1 Announce Type: new Abstract: We introduce the Neuro-Bayesian-Symbolic Residual Attention Shallow Network (NBS-RASN), a hybrid neural architecture for explainable cybersecurity risk
Kate Park / TechCrunch: Tokyo-based Sakana AI's Fugu and China-based 360's cybersecurity model Tulongfeng claim to rival Anthropic's banned Mythos and Fable 5 amid the US export ban — On Wednesday, Ch
Eduardo Baptista / Reuters: Chinese cybersecurity company 360 unveils new AI tools: Tulongfeng, which it claims is “China's version of Mythos”, and Yitianzhen, to automate cyber defense — Chinese cybe
New York Times: The NSA was red-teaming Mythos 5 before losing access amid the Anthropic dispute; the tests showed Mythos identified cybersecurity flaws in classified systems — A recent episode unders
Lorenzo Franceschi-Bicchierai / TechCrunch: Cybersecurity researchers complain that Claude Fable's guardrails are too strict, rejecting “innocuous tasks” like reading blog posts or performing code rev
Cyera Ltd., a startup that helps organizations track and secure their data assets, has raised 600 million from investors at a 12 billion valuation. The company is one of three cybersecurity providers
Anthropic PBC is expanding a program that enables organizations to test their cybersecurity defenses using its Claude Mythos Preview model. The initiative, which is known as Project Glasswing, launche
arXiv:2506.12060v2 Announce Type: replace-cross Abstract: Cybersecurity organizations are adapting to GenAI integration through modified frameworks and hybrid operational processes, with success influ
Maria Curi / Axios: OpenAI announces partnerships to combat election misinformation, offering cybersecurity products to state officials and backing legislation to curb deepfakes — OpenAI is announcing
arXiv:2605.24765v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to cybersecurity question answering (QA) for critical tasks such as incident response and vulner
Harshita Mary Varghese / Reuters: US cybersecurity company Zscaler reports Q3 revenue up 25% YoY to 850.5M, above 835.4M est., and forecasts Q4 revenue below est.; ZS drops 18%+ after hours — Zscaler
arXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM
Ashley Gold / Axios: The White House postpones a planned ceremony this afternoon for Trump to sign a new EO on AI and cybersecurity; Trump says “I didn't like certain aspects of it” — The White House
arXiv:2605.17219v1 Announce Type: cross Abstract: Artificial Intelligence (AI) is widely adopted today for its ability to detect patterns, automate tasks, and reduce time and cost across various appli
Alexey Shabanov / TestingCatalog AI News: OpenAI launches Daybreak, a cybersecurity initiative integrating AI models and Codex Security to help organizations patch vulnerabilities — OpenAI launches Da
This OpenAI resource discusses cybersecurity challenges and strategies in an era dominated by artificial intelligence and advanced threat actors. It likely covers how AI technologies are transforming
Sharon Goldman / Fortune: Artemis, which aims to replace rule-based cybersecurity systems with an AI-driven centralized “brain”, emerges from stealth with a $70M Series A led by Felicis — Artemis, a n
arXiv:2604.09998v1 Announce Type: cross Abstract: Large language models (LLMs) have recently emerged as promising tools for augmenting Security Operations Center (SOC) workflows, with vendors increasi
The UK's AI Security Institute (AISI) conducted evaluations of Anthropic's Claude Mythos Preview, finding it represents a meaningful step up over previous frontier AI models in cybersecurity capabilit
We’re expanding Trusted Access for Cyber with additional tiers for authenticated cybersecurity defenders. Customers in the highest tiers can request access to GPT-5.4-Cyber, a version of GPT-5.4 fine-
AI Security Institute: Cybersecurity analysis: Claude Mythos Preview had a 73% success rate on expert-level capture-the-flag challenges, which no model could finish before April 2025 — The AI Security
Some sober thinking about Mythos (full version with links at my newsletter): 1It’s probably not as bad as they say, as AI and cybersecurity expert @HeidyKhlaaf explains elsewhere (in a thread “As some
Mistral AI announced that its new model, Mistral Large 4, is among the world's most powerful AI systems specifically designed for cybersecurity tasks. The tweet shared on October 6, 2026 highlights th
Jaspreet Singh / Reuters: California AG Rob Bonta issues an investigative subpoena to OpenAI, as part of a broader inquiry into cybersecurity incidents and risks related to its AI models — California
This is huge. Xiaomi just open-sourced 7k+ reinforcement learning task environments used to train MiMo, covering code, cybersecurity, general tool use, visual web development, and music-related tasks.
Jensen is right that we have existing laws relevant to cybersecurity. It is very unfortunate that the Trump administration appears not to be enforcing them. In the end, that will actually *increase* p
arXiv:2609.19399v1 Announce Type: cross Abstract: Computing Nash equilibria of simulation-based cybersecurity games with policy-space response oracles (PSRO) is bottlenecked by payoff estimation: ever
Say it with me. “OpenAI is terrible at cybersecurity.” This is crazy. In late July, 'three guys with Claude and Codex subscriptions' were able to use Opus 5 to access OAI auth tokens and gain write ac
The “Crazy prediction” page asserts that the next major AI‑agent incident originating from an AI laboratory would have been entirely preventable with strong cybersecurity measures. The site is current
Can you even imagine the nation state level attacks METR & other eval orgs will come under? Eval orgs also need world class cybersecurity as well as AI talent to do this right, they are not overlappin
arXiv:2609.08765v1 Announce Type: cross Abstract: Large language model (LLM) benchmarks are often treated as fixed datasets with stable scores, yet their outcomes depend on configurable evaluation pip
Deepseek-V4.1-Flash is available now on Fireworks! It is a 552B Parameter MoE built for coding, cybersecurity, and agents. It is the ideal workhorse model that outperforms Opus 5 and GPT 5.6 Sol at 1/
Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. They allow every developer, startup, university,
Agentic AI is fundamentally reshaping cybersecurity requirements. The industry needs security designed into the entire AI stack, starting with the silicon itself and not added as an afterthought. Thor
Anthropic: Anthropic unveils Claude Fable 5.1, which is generally available, and Mythos 5.1, for trusted partners and with cybersecurity and life sciences safeguards — We're introducing Claude Fable 5
Hi guys , this is a fine tune of qwen 3.5 4b on cybersecurity , specifically malware. This model has been trained on 2.6k rows of simple but effective malware code , though its still significantly lim
Yes, the AIs were given a cybersecurity challenge, with internet access enabled and safety filters disabled. But the extent to which Mythos 5 pursued its mission (fake identities, social engineering,
Members of the Open Secure AI Alliance — now more than 120 organizations strong — are developing new guidelines to strengthen agentic AI cybersecurity as the annual Black Hat conference begins in Las
Is China winning the AI race? @huggingface CEO @ClementDelangue thinks so – here's how he's utilizing foreign cybersecurity tools following the company's hack by rogue OpenAI agents: https://www.cnbc.
arXiv:2502.16184v3 Announce Type: replace Abstract: The EU Artificial Intelligence Act (AIA) establishes different legal principles for different types of AI systems. While prior work has sought to cl
Leo Schwartz / The Information: Meta, Nvidia, Microsoft, a16z, and others sign a letter defending open-source AI; Jensen Huang, in his first X post, says open models strengthen cybersecurity — Many of
It’s the stuff of cybersecurity nightmares. OpenAI said two artificial intelligence systems it was testing broke out of their test environment, hacked their way onto the internet and broke into anothe