arXiv:2610.36295v1 Announce Type: new Abstract: Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access controls. These prompts are vulnerable to query-based leakage attacks, where black-box adversaries extract confidential instructions through adaptive, multi-turn interactions. Existing defenses often assess queries independently, missing malicious behavior that emerges across interactions.

Read the full article at arXiv cs.CR →