Saved in:
Bibliographic Details
Main Authors: Dorzhiev, Nima, Liu, Peng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.30534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913171053215744
author Dorzhiev, Nima
Liu, Peng
author_facet Dorzhiev, Nima
Liu, Peng
contents Polymorphic Prompt Assembling (PPA) defends LLM agents against prompt injections by randomly selecting separator pairs from a fixed pool to isolate user input from system instructions. Although effective, static pool reuse exposes a blast-radius vulnerability: once a separator leaks, it can be exploited in future requests. We propose a dynamic per-request separator generation using domain-separated SHA-256 digests keyed on the timestamp, session identifier, and cryptographic nonce. Each assembled prompt receives a unique (BEGIN, END) canary pair, thereby limiting leakage exposure to a single request. We evaluated our extension against 16 injection payloads on Llama-3.3-70B-Instruct-Turbo, with cross-model validation on DeepSeek-V4-Flash model. Against the M1 obfuscation payload (leetspeak + urgency), the dynamic mode reduces the Attack Success Rate (ASR) from 0.88 to 0.38, yielding a statistically significant 2.3 x mitigation verified by non-overlapping 95% Wilson confidence intervals. Against format_breakout_salad, static separator leakage (leak_rate = 0.467) is eliminated entirely in the dynamic mode (0.000), confirming the blast-radius reduction in practice. The implementation requires no model fine-tuning, adds 2.7 microseconds prompt-assembly overhead per request, and is backward compatible with the existing PPA SDK.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30534
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks
Dorzhiev, Nima
Liu, Peng
Cryptography and Security
Polymorphic Prompt Assembling (PPA) defends LLM agents against prompt injections by randomly selecting separator pairs from a fixed pool to isolate user input from system instructions. Although effective, static pool reuse exposes a blast-radius vulnerability: once a separator leaks, it can be exploited in future requests. We propose a dynamic per-request separator generation using domain-separated SHA-256 digests keyed on the timestamp, session identifier, and cryptographic nonce. Each assembled prompt receives a unique (BEGIN, END) canary pair, thereby limiting leakage exposure to a single request. We evaluated our extension against 16 injection payloads on Llama-3.3-70B-Instruct-Turbo, with cross-model validation on DeepSeek-V4-Flash model. Against the M1 obfuscation payload (leetspeak + urgency), the dynamic mode reduces the Attack Success Rate (ASR) from 0.88 to 0.38, yielding a statistically significant 2.3 x mitigation verified by non-overlapping 95% Wilson confidence intervals. Against format_breakout_salad, static separator leakage (leak_rate = 0.467) is eliminated entirely in the dynamic mode (0.000), confirming the blast-radius reduction in practice. The implementation requires no model fine-tuning, adds 2.7 microseconds prompt-assembly overhead per request, and is backward compatible with the existing PPA SDK.
title Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks
topic Cryptography and Security
url https://arxiv.org/abs/2605.30534