Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Arya Bakhtiari's picture

Arya Bakhtiari

torbatti
2 2 3
nico-martin's profile picture
·
  • torbatti

AI & ML interests

None yet

Recent Activity

liked a model about 1 hour ago
deepseek-ai/DeepSeek-V4.1-Flash
reacted to mihailgribov's post with 🔥 4 days ago
How often can an email make your AI agent move money? We gave the agent one job: log an incoming email. But the emails carried an indirect prompt injection - a second instruction, written for the agent rather than for a person: make a payment. Across nine agentic models, the same injected emails produced payment orders in **0% to 42%** of cases. All nine ran under the same conditions - one agent, one set of tools, the same 395 emails - so the numbers compare directly. And the average score hides the interesting part: different models fail on different kinds of injections. Full experiment and results: https://huggingface.co/blog/mihailgribov/agentic-models-measured-on-the-injections-that-mov The bench is public too - run your own model through the same test: https://github.com/mihail-gribov/quadrat-ipi-model-eval https://huggingface.co/datasets/mihailgribov/quadrat-ipi #prompt-injection #indirect-prompt-injection #agentic-ai #llm-security #ai-agents
liked a Space 5 days ago
Xenova/fruit-fly-simulation
View all activity

Organizations

None yet

torbatti 's datasets

None public yet
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs