Search Anthropic

Progress on provable inference for large language models
We have made progress on a type of cryptographic proof known as a “zkSNARK.” In this post, we share some of that progress, primarily through a system we call FlashProve.
Expanding our partnership with GSA to bring Claude to all levels of government
We are expanding our partnership with the General Services Administration (GSA) through a new agreement that gives government partners a 40% discount on Claude Enterprise, Claude for Government, and the Claude API.
Discovering and exploiting vulnerabilities in critical, real-world software with Claude
Over the past few months, we’ve used an unreleased, internal research model to find critical vulnerabilities in some of the world’s most widely used software, such as browsers and operating systems. In this post, we share details of five attack chains, which led to remote code execution and other critical impacts with little to no user interaction.
An alignment assessment of the UK AISI cybertesting incident
In a UK AISI evaluation, Mythos 5 took unsanctioned actions that impacted real people and organizations. In this post, we investigate these behaviors from Claude Mythos 5 further, to understand what they reveal about the model’s alignment.
LLMs are making formal software verification feasible at a much larger scale
We used Claude to prove security properties in over 100 real-world open-source libraries over the span of a few weeks.
Using Claude to reduce the attack surface of code
Automated attack surface analysis and reduction can meaningfully improve the security of deployed software in the near term. In this post, we preview data we’ve collected from applying attack surface reduction techniques to large open-source codebases using Claude.
Claude reveals ECDSA curve origins
The decades-old mystery of the origins of one of the most popular cryptographic standards has been explained.
Strengthening our defenses against distillation attacks
Illicit distillation allows model developers to copy frontier AI capabilities without creating proportionally robust safeguards. Here, we describe how we’ve reduced the rate of distillation by more than 90%.
AI models may be capable of self-replicating without access to a datacenter
Our experiments suggest that small AI models may be only months away from being capable enough to self-replicate on commercial IoT devices, like Android TVs and smart ovens.
Investigating unintended model actions in our evaluations and internal use
This report describes examples of unintended model actions we’ve observed during evaluations and internal use of Claude.
Launching an opt-in vulnerability-finding service for open-source software
We’re making available OSS Scanner, an opt-in vulnerability scanner for the open-source ecosystem that’s informed by our experience using Claude to find vulnerabilities during Project Glasswing.
Introducing the Anthropic Cyber Mission
We’re launching the Anthropic Cyber Mission, a long-term commitment to securing the systems everyone depends on.
Expanding the Cyber Verification Program
We’re launching a new, expanded version of our Cyber Verification Program, which makes advanced cyber capabilities and reduced blocking classifiers available to qualifying security professionals.
GLM-5.3 and the spread of advanced cyber capabilities
Like Claude Mythos Preview, GLM-5.3 has strong capabilities for autonomously building end-to-end cyber exploits. But unlike other frontier models, GLM-5.3 has been released without meaningful safeguards to limit misuse.
An alignment assessment of recent cybersecurity incidents
We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.
Developing Enterprise Frontier Safeguards with our customers
We’re announcing Enterprise Frontier Safeguards (EFS), a solution that combines the privacy of zero data retention with state-of-the-art safeguards for detecting misuse. EFS works by storing data in cloud infrastructure controlled by the customer, not Anthropic.
Improving our alignment and security efforts
On July 30, we reported three incidents in which Claude models gained unauthorized access to real computer systems. We are conducting an in-depth analysis of both incidents, and planning to work with METR for an independent review. In the meantime, we’re sharing some of the changes we’ve made over the past month.
Patterns and problems in emerging multiagent systems
Here, we identify a few examples of behavioral tendencies in current frontier models and show how they can produce unexpected systemic failures, in hopes of starting a conversation about mitigating these risks.
Investigating three real-world incidents in our cybersecurity evaluations
We found three cases where a Claude model reached the internet from an evaluation environment and accessed real systems. We share what happened and what we're changing.
Discovering cryptographic weaknesses with Claude
Cryptographic algorithms. The first attack significantly weakens HAWK, a digital signature scheme that was built for a future world where quantum computers are able to break existing standards. The second identifies a new way to attack round-reduced AES, the most widely used symmetric cipher.