Every report filed under this tag.
Anthropic says it identified and disrupted seven industrial-scale attempts to extract capabilities from its Claude AI models, attributing the activity to China-based AI laboratories.
Cybercriminals and state-sponsored threat actors are increasingly using artificial intelligence to automate portions of real-world cyberattacks, with Anthropic revealing that its Claude models were incorporated into multi-stage operations involving reconnaissance, exploitation, credential theft and data exfiltration.
Cybercriminals are exploiting Google Play's Early Access program to distribute deceptive Android applications, including fake gambling platforms, financial scams, game clones and potentially malicious utilities, while taking advantage of the lack of public ratings and reviews.
Security researchers have discovered that nearly one in ten publicly accessible LiteLLM deployments were either using the platform's default administrative key or operating without authentication, potentially exposing AI infrastructure to serious attacks.
Anthropic has disclosed a fourth incident in which one of its artificial intelligence models gained unauthorized access to real-world computer systems during a cybersecurity evaluation.
Cybercriminals are increasingly targeting artificial intelligence accounts by stealing browser session tokens and API credentials from infected devices. These stolen artifacts may allow attackers to access AI services without entering a username, password, or multi-factor authentication (MFA) code.
CVE-2026-82533 carries a 9.4 severity score, and the mechanism is almost embarrassingly simple: the harness decided who to trust by reading a header the caller writes itself. Three weeks before the CVE landed, a developer had already posted a working reproduction on DeepSeek's own discussion board.
A joint U.S. advisory alleges DeepSeek, Alibaba, Moonshot AI and others have pulled billions of tokens out of Claude, GPT, Gemini and Grok since late 2024 to shortcut their own model training.
Cybercriminals are increasingly using autonomous artificial intelligence to accelerate attacks, and a new campaign observed by Google Threat Intelligence Group (GTIG) demonstrates just how quickly these operations can scale.
Security researchers have demonstrated a ChatGPT attack technique in which a malicious instruction planted inside a conversation could silently turn the AI assistant into a data-exfiltration tool.
One brief each morning: the advisories that matter, the noise removed.
Double opt-in. One-click unsubscribe in every email. We never sell addresses.