📄 文章列表
17 篇文章
AlphaSignal
Vals AI's CyberOffense Shows DeepSeek V4.1 Flash Hacking Corporate Networks for Under $3
AlphaSignal
OpenAI's AI Pipeline Finds 948 Linux Root Exploits in a Single Run
cn_ai
Spring Security 7 中的服务端 DPoP 和令牌交换
VentureBeat
AI agents don't have to break security controls to go rogue. Here's how to keep them in check
VentureBeat
Microsoft's record Patch Tuesday shows why severity can't decide what gets patched first
VentureBeat
Anthropic documented a new problem for security teams: Attacks that can adapt while they're underway
VentureBeat
AI agents are exposing a security gap between the data they read and the systems they can change
VentureBeat
Meta patched Muse’s zero-day, but security teams still lack visibility into what the agent can access
TDS
GPT-6 Astra Just Hit OpenAI's Highest Cybersecurity Risk Level
VentureBeat
Safety guardrails blocked Hugging Face's defenders, not the attacker, when an AI agent breached its systems
VentureBeat
The attack that hijacked Claude Code came through Sentry. Datadog, PagerDuty, and Jira have the same exposure.
TDS
The MCP Security Survival Guide: Best Practices, Pitfalls, and Real-World Lessons
TDS
What Does “Following Best Practices” Mean in the Age of AI?
VentureBeat
Claude Code 512000 Line Source Leak Attack Paths Audit Security Leaders
VentureBeat
Mfa Verifies Who Logged In It Has No Idea What They Do Next
VentureBeat
Anthropic Says Its Most Powerful Ai Cyber Model Is Too Dangerous To Release
VentureBeat