Phying News
P非影 中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

From Jeopardy! to The Terminator: AI vs. AGI vs. ASI

bugcrowd.com | blog | #ai-security | #agi | #asi | #adversarial-attacks | #alphago | #watson

Summary

From Watson to AlphaGo, narrow AI is already hackable through adversarial attacks and data poisoning. This tour of AI, AGI, and ASI shows where today's hacking primitives and threats live.
Published
Collected

original ↗

Related coverage

  1. Four ways traditional pen testing falls short for SaaS companies (bugcrowd.com)
  2. What’s changed in AI security over the past two years (bugcrowd.com)
  3. Auditing in the age of (good enough) AI (blog.trailofbits.com)
  4. 1Password's AI patching benchmark is misleading (blog.trailofbits.com)
  5. Securing the software factory at machine speed (about.gitlab.com)
  6. New MCP tools help platform teams scale automation safely (about.gitlab.com)

back