By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Model artifact risks

Serialized model files such as pickles can execute code when loaded, and fine-tuned weights can carry hidden backdoors that survive safety training. Prefer safe formats, scan artifacts before loading them, and verify where they came from.

Read in this order

  1. OfficialHugging Face: Pickle ScanningStart here: why pickles are dangerous and how model hubs scan for them.
  2. Open sourcetrailofbits/fickling: A Python pickling decompiler and static analyzerA tool to inspect and analyze pickle files before you load them.
  3. PaperSleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingShows backdoored behavior can persist through safety training, so provenance matters.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.