Search Anthropic

Deliberately trying to find flaws, vulnerabilities, or harmful outputs in AI systems before they're deployed. Red teams think like adversaries to surface problems that normal testing might miss.
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.
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.
Partnering with Accenture on embedded evaluation
We’re partnering with Accenture on independent evaluation of frontier AI—part of our recent commitment to embed evaluators at Anthropic. Both we and Accenture expect to invest at least $1 billion to build capacity in this area over the next five years.
Measuring tactical intelligence targeting and conventional weapons capabilities of AI models
Anthropic’s Frontier Red Team developed new evaluations to measure AI capabilities in tactical intelligence targeting and conventional weapons development.
Reverse engineering Claude's CVE-2026-2796 exploit
This post dives deep into how Claude wrote an exploit for one of the vulnerabilities it found in Firefox.
Making frontier cybersecurity capabilities available to defenders
Claude Code Security is one step towards our goal of more secure codebases and a higher security baseline across the industry.
Next-generation Constitutional Classifiers: More efficient protection against universal jailbreaks
Constitutional Classifiers++ improve on our previous approach, yielding a system that is even more robust, has a much lower refusal rate, and is dramatically cheaper to run.
Experimenting with AI to defend critical infrastructure
AI could help defenders of critical infrastructure identify the vulnerabilities that attackers might exploit—and close them before they are exploited. Anthropic has partnered with Pacific Northwest National Laboratory (PNNL) to explore this defensive application of AI, demonstrating both the potential of AI-accelerated defense and the value of public-private partnerships in harnessing AI for national security.
Mitigating the risk of prompt injections in browser use
Claude Opus 4.5 achieves a 1% attack success rate against prompt injections in browser use, and Claude for Chrome moves to beta.
Strengthening our safeguards through collaboration with US CAISI and UK AISI
Over the past year, we've collaborated with the US Center for AI Standards and Innovation (CAISI) and UK AI Security Institute (AISI), government bodies established to measure and improve the security of AI systems.
Developing nuclear safeguards for AI
Together with the NNSA and DOE national laboratories, we have co-developed a classifier—an AI system that automatically categorizes content—that distinguishes between concerning and benign nuclear-related conversations with high accuracy in preliminary testing.
Agentic misalignment: How LLMs could be insider threats
New research on simulated blackmail, industrial espionage, and other misaligned behaviors in LLMs.
Testing our safety defenses with a new bug bounty program
A new bug bounty program with HackerOne challenges red-teamers to find universal jailbreaks in safety classifiers we haven't yet deployed.
Progress from our Frontier Red Team
What we've learned about the trajectory of national security risks from frontier AI models, and best practices for evaluating those risks.
Auditing language models for hidden objectives
A collaboration between Anthropic's Alignment Science and Interpretability teams
Forecasting rare language model behaviors
Anthropic research on predicting rare, undesirable AI behaviors
Constitutional Classifiers: Defending against universal jailbreaks
A paper from Anthropic describing a new way to guard LLMs against jailbreaking.
Elections and AI in 2024: Observations and learnings
Lessons and observations from generative AI in the first major election year since Claude has been available.
U.S. elections readiness
How Anthropic prepared for the 2024 US elections, from usage policy enforcement to redirecting voting queries to authoritative sources.
Expanding our model safety bug bounty program