Ai Security RSS Feeds

Directory0 ai security feeds · 62 articlesShow all languages →

Latest

Ai Security articles

Snowflake acquires Natoma to manage AI agent permissions across enterprise systems

Snowflake has announced its acquisition of Natoma, a startup that provides a gateway for managing AI agent permissions across enterprise applications. During Snowflake's Q1 FY2027 earnings call, CEO Sridhar Ramaswamy described Natoma as a key component of Snowflake's "agentic con

Newstechnologybusinessai security

theregister.com·Tech by Flipboard·19h ago·4 min read

Benchmarking Frontier LLMs on Real-World CVE Patching: Mixed Results and Methodological Challenges

Insighttechnologyprogrammingai security

giovannigatti.github.io2d ago

Digimarc launches provenance and verification tools for AI agent workflows

Newstechnologybusinessai security

Shared by @hacker.at.thenote.app on Bluesky ↗

helpnetsecurity.com2d ago

Geordie AI raises $30M Series A for AI agent security and governance platform

Newstechnologybusinessai security

Shared by @tech.eu on Bluesky ↗

tech.eu2d ago

Microsoft 365 Copilot passes second ISO 42001 security audit with zero findings

Newstechnologybusinessai security

Shared by @neowin.net on Bluesky ↗

neowin.net3d ago

Secure AI Agent Deployment: Sandboxed Execution with relaxAI

technologybusinessai security

Shared by @civo.com on Bluesky ↗

civo.com4d ago

SymJack Attack Exploits AI Coding Agents for Supply Chain Compromise

Newstechnologycybersecurityprogramming

Shared by @infosecbriefly.bsky.social on Bluesky ↗

briefly.co4d ago

Study Reveals Domain-Camouflaged Injection Attacks Bypass LLM Detection Systems

This research paper identifies a critical vulnerability in injection detectors used to protect LLM agents. The authors demonstrate that when injection payloads are generated to mimic the domain vocabulary and authority structures of target documents (termed "domain camouflaged in

Insighttechnologyscienceai security

arxiv.org·Hacker News: Front Page·9d ago·2 min read

Project Glasswing: Testing Anthropic's Mythos Preview LLM for Security Vulnerability Detection

The article details Project Glasswing, a security initiative where the author's team tested Anthropic's Mythos Preview LLM against their own code repositories to identify vulnerabilities. The LLM was pointed at over fifty repositories to assess its ability to find security flaws,

Insighttechnologycybersecurityprogramming

blog.cloudflare.com·Hacker News: Front Page·13d ago·14 min read

OpenAI launches Daybreak, an AI security initiative to detect and patch code vulnerabilities

OpenAI has launched Daybreak, an AI-powered security initiative that uses its Codex Security AI agent to detect and patch vulnerabilities in organizations' code. Daybreak creates threat models, identifies attack paths, validates vulnerabilities, and automates detection of high-ri

Newstechnologycybersecuritybusiness

AI | The Verge·20d ago·2 min read

AI agents Grok and Bankrbot tricked into sending $200K in tokens via Morse code prompt injection

Newstechnologyfinanceai security

Cryptopolitan22d ago

Above Security launches AI-powered insider risk detection platform on Product Hunt

Producttechnologycybersecuritybusiness

Product Hunt1mo ago

DeepXL.ai launches AI fraud detection platform for documents, IDs, and images on Product Hunt

Producttechnologybusinessai security

Product Hunt1mo ago

Brex Business Account Services and CrabTrap AI Security Proxy

technologyfinancebusiness

brex.com1mo ago

Public AI Models Already Possess Vulnerability Research Capabilities Similar to Anthropic's Mythos

Insighttechnologyprogrammingai security

blog.vidocsecurity.com1mo ago

Astra: Tokenizing Sensitive Data for AI Agent Security

Producttechnologyprogrammingdata privacy

Product Hunt1mo ago

Understanding "Disregard that!" Attacks: The Prompt Injection Vulnerability in LLMs

The article discusses the security vulnerability in Large Language Models (LLMs) known as "prompt injection," which the author refers to as "Disregard that!" attacks. It explains how LLMs operate on a context window that contains all input text, and warns against sharing this con

Insighttechnologycybersecurityprogramming

calpaterson.com·Hacker News: Front Page·2mo ago·10 min read

TeamPrompt: AI Data Loss Prevention and Prompt Management Platform for Teams

Producttechnologybusinessai security

Product Hunt2mo ago