ai-security
27 posts tagged ai-security.
- Australia’s AI agent hearing is really about incident disclosure
- Agent control failures are moving from demo risk to operating risk
- NSA’s reported AI testing spend makes evals look like infrastructure
- When Agents Hack: What the OpenAI-Hugging Face Story Actually Tells Builders
- Australia’s OpenAI agent breach is a disclosure problem, not a sci-fi one
- Authorship verification works better as similarity, not classification
- Known puts domain identity into the agent stack
- Gemini’s reported company breaches show the AI disclosure gap
- VVV Shows the Privacy AI Pitch Has Become a Token Story
- Marc van der Chijs’s AI banking warning needs plumbing details
- A vulnerability is not fixed because an AI bot saw it
- The RubyGems agent report is a supply-chain warning
- An 86% Bitcoin quantum benchmark cut is not an 86% attack
- OpenAI’s Python SDK gets key expiration controls, not just new image hooks
- Harmony’s reported shutdown plan makes AI a chain-risk argument
- AI cyber risk is moving from demo to preparedness
- AI bug reports are now a Lightning ops problem
- Bitcoin’s AI Security Problem Is Scale, Not Superintelligence
- Treat the Texas AI hacking story as a disclosure systems test
- Prompt Injection Is SEO Spam With a Larger Blast Radius
- Payward’s reported Glasswing access is an AI security story, not a crypto story
- VICBench shows vulnerability detection still needs humans
- AI security review is hitting Bitcoin repos, not just toy code
- Apple’s AI slop filter may be catching real macOS bugs
- Agent immunity is the missing layer between alignment and tool use
- Promptware Treats Prompt Injection Like an Execution Chain
- Agent safety belongs outside the agent process