Paper Detail

Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

Pingyu Wu, Lingyao Zhu, Weiming Zhang, Nenghai Yu

huggingface Score 7.5

Published 2026-07-30 · First seen 2026-08-03

General AI

Abstract

Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence available about downstream use. When that evidence is copyable, we derive the exact worst-case floor on attacker assistance while preserving useful answers. The result yields a safety trilemma: Useful Capability, Reliable Safety, and Open Access cannot coexist. We then show how a trusted credential can complement existing safeguards by adding hard-to-copy information that predicts actual downstream use, and identify the stronger condition needed to eliminate the floor. Evidence from dual-use evaluations, adaptive attacks, and deployed trusted-access programs supports the practical relevance of these conditions.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{wu2026safeguards,
  title = {Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs},
  author = {Pingyu Wu and Lingyao Zhu and Weiming Zhang and Nenghai Yu},
  year = {2026},
  abstract = {Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence available about downstream use. When that evidence is copyable, we derive the exact worst-case floor on attacker assistance while preserving usef},
  url = {https://huggingface.co/papers/2607.27951},
  keywords = {huggingface daily},
  eprint = {2607.27951},
  archiveprefix = {arXiv},
}

Metadata

{}