Knowledge catalogue
Editor’s note: Today’s post is by Scott Gatreau, Director of Information Security, at Turner Industries, a privately owned industrial contractor that provides construction, maintenance, and fabricatio
@anthropicai: Anthropic says the US government is allowing Mythos 5 to be redeployed to critical infrastructure operators, and is working to restore general access to Fable 5 — Since June 12, we've be
arXiv:2606.27202v1 Announce Type: new Abstract: Graph neural networks have moved from a niche representation-learning technique to the default model class wherever data carry relational structure. The
Written by: Jordan Jones Introduction Google Threat Intelligence Group (GTIG) has conducted an in-depth analysis of a .NET backdoor, tracked as STOCKSTAY, that has been continually developed and deplo
arXiv:2606.24962v1 Announce Type: new Abstract: Recent progress in large-scale sequence modeling has shown that a single model can learn useful representations across highly diverse data distributions
arXiv:2508.18684v2 Announce Type: replace-cross Abstract: Signature-based Intrusion Detection Systems (IDS) detect malicious activity by matching network or host events against predefined rules. Secur
Benchmarks tell only part of the story. Fugu’s real value shows up in long, messy, real-world workflows. During our beta with 500 users, we saw Fugu Ultra drive meaningful progress in fully automated
Daybreak is an OpenAI initiative focused on developing and distributing security tools designed to protect organizations globally from cyber threats. The program aims to democratize access to advanced
Gray Swan: Red-Teaming after Mythos & the coming AI security crisis https://www.latent.space/p/gray-swan @GraySwanAI cofounders @zicokolter and Matt Fredrikson explain why AI security is fundamentally
The US government ordered Anthropic to cut off foreign access to its Mythos 5 and Claude Fable 5 AI models in June 2026, citing national security concerns related to jailbreak vulnerabilities that cou
How does it work? Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackl
Lily Hay Newman / Wired: OpenAI unveils an updated GPT-5.5-Cyber model, launches the Patch the Planet initiative in partnership with Trail of Bits to fix open source bugs, and more — Amid concerns abo
arXiv:2606.11272v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative and privacy-preserving model training across distributed clients, but most existing FL systems implicitl
If Claude Fable stops helping you, you'll never know Jonathon Ready highlights one of the more eyebrow-raising details from the 319 page system card for Fable 5 and Mythos 5. Here's a longer excerpt,
Anthropic PBC today introduced Claude Mythos 5 and Claude Fable 5, two large language models that it says outperform the competition across a wide range of benchmarks. The LLMs are derived from the Cl
It's confusing that Trump constantly warns about the security of our elections & foreign interference, yet his administration has taken several steps to dismantle or divert resources away from key saf
@METR_Evals previously on @cognition_labs https://x.com/swyx/status/2062611218196771017?s=20 Finally! the first eval ship from cog!!!!!!!!!! 👼🏼 To contextualize: @METR_Evals cap out at ~16 hours. Cog
arXiv:2606.05584v1 Announce Type: cross Abstract: High-dimensional feature representations are widely used in machine learning-based cyberattack detection systems. However, they increase computational
Building AI that Builds AI: Introducing the Sakana AI RSI Lab 🚀 https://sakana.ai/rsi-lab Today, we are announcing the Sakana AI Recursive Self-Improvement (RSI) Lab: a dedicated research group in Tok
In March 2026, the FCC added all consumer-grade routers produced in foreign countries to its Covered List, prohibiting new models from receiving authorization . The ban cites supply chain vulnerabilit
Finally! the first eval ship from cog!!!!!!!!!! 👼🏼 To contextualize: @METR_Evals cap out at ~16 hours. Cog has private enterprise evals up to 100hrs, and is confident enough to put a financial guarant
Sam Altman argues that US leadership in artificial intelligence requires three concurrent priorities: advancing cutting-edge AI model development, ensuring these models incorporate robust safety measu
arXiv:2504.05871v3 Announce Type: replace Abstract: The increasing deployment of intelligent agents in digital ecosystems, such as social media platforms, has raised significant concerns about traceab
This article explores the applications and impact of artificial intelligence on national security and defense operations, examining how AI technologies are transforming military capabilities, threat d
At Google Cloud Next, we announced the preview of graph algorithms with Spanner Graph, bringing Google Research’s state-of-the-art graph mining capabilities natively to your database. These graph inte
President Donald Trump signed an executive order Tuesday creating a 'voluntary framework' for AI companies to share their frontier models with the federal government before they're released 'to promot
arXiv:2605.30667v1 Announce Type: cross Abstract: Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis witho
OpenAI frontier models and Codex are now generally available on AWS, giving enterprises a new way to build on Amazon Bedrock with OpenAI through the security, compliance, and governance workflows they
Aaron Holmes / The Information: Palo Alto Networks says Mythos found 24+ critical bugs using $1M+ in tokens; Anthropic subsidizes Mythos but some companies plan to boost their Mythos budgets — When Pa
Gian Volpicelli / Bloomberg: Sources: Anthropic plans to let the EU's cyber agency ENISA join Project Glasswing, giving it access to Mythos; EU officials went to the US to ask for access — Anthropic P
arXiv:2605.31593v1 Announce Type: cross Abstract: Language models can find thousands of severe software vulnerabilities, and agents are increasingly being misused for cyberattacks. To avoid detection,
arXiv:2509.23571v3 Announce Type: replace-cross Abstract: As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect a
Welcome to the second Cloud CISO Perspectives for May 2026. Today, Usman Chaudhary, Field CISO, Google Public Sector, offers a guide for CISOs protecting government agencies and critical infrastructur
Samantha Subin / CNBC: SentinelOne's stock closes down 8% after the company announced plans to lay off 8% of its workforce and forecasted Q2 and FY revenue guidance below estimates — SentinelOne share
arXiv:2605.26446v1 Announce Type: cross Abstract: Graph anomaly detection (GAD) aims to identify nodes or substructures whose behavior or attributes deviate significantly from the overall pattern in g
arXiv:2605.27063v1 Announce Type: new Abstract: The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node f
arXiv:2511.20236v3 Announce Type: replace Abstract: Counterfactual explanations improve the actionable interpretability of machine learning models by identifying minimal changes required to achieve a
arXiv:2605.23946v1 Announce Type: cross Abstract: Climate volatility, regional production concentration, labor constraints, cyber risk, and dependence on long-distance fresh-produce supply chains expo
arXiv:2605.25120v1 Announce Type: cross Abstract: Radiology reports remain the primary mechanism by which imaging findings are communicated to clinical teams. However, much of the structured informati
The way we work has fundamentally changed. From automated agents to sophisticated AI services, Generative AI (GenAI) has become a daily tool for a vast majority of employees. But with this rapid adopt
arXiv:2603.11001v2 Announce Type: replace-cross Abstract: Human uplift studies, or studies that measure the effects of AI access on human performance via randomized controlled trials (RCT) or similar
Here’s a key line in this mythos update. This is precisely an example of why engineers don’t go away, ever. We’ve made it far easier to create and find security issues, which means the new bottleneck
Many of the world’s fastest-growing AI startups are choosing to build their future — and the world’s — on Google Cloud because of our complete and open AI stack. We embed AI into every layer of our ar
Zscaler Inc. is acquiring Symmetry Systems Inc., a venture-backed startup that helps companies monitor their data assets. The companies announced the acquisition today without disclosing the financial
arXiv:2605.18991v1 Announce Type: cross Abstract: We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted comp
arXiv:2605.19233v1 Announce Type: cross Abstract: Unmanned aerial vehicles (UAVs) are cyber-physical systems whose attack surface spans networked avionics and on-board sensor fusion: a compromised GPS
arXiv:2605.19362v1 Announce Type: cross Abstract: Users often interpret and select agent skills through their exttt{SKILL.md} specifications. To protect users, existing audits mainly focus on maliciou
arXiv:2605.17530v1 Announce Type: cross Abstract: Network intrusion detection systems play a vital role in protecting networks by detecting malicious network traffic which can then be investigated by
arXiv:2605.16707v1 Announce Type: cross Abstract: The rapid evolution of digital health technologies is redefining healthcare services worldwide. The integration of wireless communication and Internet
Brian Krebs / Krebs on Security: A CISA contractor maintained a now-offline GitHub repo that exposed credentials to AWS GovCloud accounts and CISA systems; CISA is investigating the situation — Until
arXiv:2505.11708v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) agents are increasingly used to simulate sophisticated cyberattacks, but their decision-making processes remain op
arXiv:2605.12507v1 Announce Type: cross Abstract: While Large Language Model (LLM) multi-agent systems (MAS) offer a transformative approach to simulating human behavior in complex systems, it remains
Welcome to the first Cloud CISO Perspectives for May 2026. Today, Vinod D’Souza, director, Office of the CISO, shares highlights from his RSA Conference fireside chat with Anthony Belfiore, chief stra
Continual Harness proposes an approach to online adaptation for foundation agents that moves beyond traditional gradient-based retraining by introducing a dual-agent architecture (Teacher/Student) wit
Cyber risk management company SecurityScorecard Inc. announced today that it has acquired Driftnet Ltd., a U.K.-based internet scanning and threat intelligence startup, in a deal aimed at bolting real
A lot of people have been wondering about Mythos, Glasswing, and the vulns we / our partners are fixing. Today, I’m excited for us to start sharing more. (For context, I lead Glasswing @AnthropicAI.)
Claroty developed an AI-powered library that serves as a translation tool for industrial control system (CPS) protocols and communications, helping security teams understand and analyze diverse indust
arXiv:2605.11205v1 Announce Type: new Abstract: Benchmark evaluation across AI and safety-critical domains overwhelmingly relies on simple averaging. We demonstrate that this practice produces substan
Marina Temkin / TechCrunch: Exaforce, which uses AI agents to detect and thwart cyberattacks, raised a 125M Series B at a 725M valuation, bringing its total funding to $200M — As bad actors weaponize
arXiv:2605.09408v1 Announce Type: new Abstract: Link prediction (inferring missing or future connections between nodes in a graph) is a fundamental problem in network science with widespread applicati