Stronger Enforcement of Instruction Hierarchy via Augmented Intermediate Representations

• URL: http://arxiv.org/abs/2505.18907v1
• Date: Sun, 25 May 2025 00:01:39 GMT
• Title: Stronger Enforcement of Instruction Hierarchy via Augmented Intermediate Representations
• Authors: Sanjay Kariyappa, G. Edward Suh,
• Abstract summary: We introduce a novel approach that injects the IH signal into the intermediate token representations within the network.<n>Our method augments these representations with layer-specific trainable embeddings that encode the privilege information.<n>Our evaluations across multiple models and training methods reveal that our proposal yields between $1.6times$ and $9.2times$ reduction in attack success rate.
• Score: 10.746349111023964
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prompt injection attacks are a critical security vulnerability in large language models (LLMs), allowing attackers to hijack model behavior by injecting malicious instructions within the input context. Recent defense mechanisms have leveraged an Instruction Hierarchy (IH) Signal, often implemented through special delimiter tokens or additive embeddings to denote the privilege level of input tokens. However, these prior works typically inject the IH signal exclusively at the initial input layer, which we hypothesize limits its ability to effectively distinguish the privilege levels of tokens as it propagates through the different layers of the model. To overcome this limitation, we introduce a novel approach that injects the IH signal into the intermediate token representations within the network. Our method augments these representations with layer-specific trainable embeddings that encode the privilege information. Our evaluations across multiple models and training methods reveal that our proposal yields between $1.6\times$ and $9.2\times$ reduction in attack success rate on gradient-based prompt injection attacks compared to state-of-the-art methods, without significantly degrading the model's utility.

Related papers

• TopicAttack: An Indirect Prompt Injection Attack via Topic Transition [71.81906608221038]
  Large language models (LLMs) are vulnerable to indirect prompt injection attacks.<n>We propose TopicAttack, which prompts the LLM to generate a fabricated transition prompt that gradually shifts the topic toward the injected instruction.<n>We find that a higher injected-to-original attention ratio leads to a greater success probability, and our method achieves a much higher ratio than the baseline methods.
  arXiv  Detail & Related papers  (2025-07-18T06:23:31Z)
• One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models [20.42976162135529]
  Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research.<n>We propose textttD-STT, a simple yet effective defense algorithm that identifies and explicitly decodes safety trigger tokens of the given safety-aligned LLM.
  arXiv  Detail & Related papers  (2025-05-12T01:26:50Z)
• CachePrune: Neural-Based Attribution Defense Against Indirect Prompt Injection Attacks [47.62236306990252]
  Large Language Models (LLMs) are susceptible to indirect prompt injection attacks.<n>This vulnerability stems from LLMs' inability to distinguish between data and instructions within a prompt.<n>We propose CachePrune that defends against this attack by identifying and pruning task-triggering neurons.
  arXiv  Detail & Related papers  (2025-04-29T23:42:21Z)
• Token-Efficient Prompt Injection Attack: Provoking Cessation in LLM Reasoning via Adaptive Token Compression [12.215295420714787]
  "Reasoning Interruption Attack" is a prompt injection attack based on adaptive token compression.<n>We develop a systematic approach to efficiently collect attack prompts and an adaptive token compression framework.<n> Experiments show our compression framework significantly reduces prompt length while maintaining effective attack capabilities.
  arXiv  Detail & Related papers  (2025-04-29T07:34:22Z)
• A generative approach to LLM harmfulness detection with special red flag tokens [15.796683630119654]
  We propose to expand the model's vocabulary with a special token we call red flag token (rf>)<n>This novel safety training method effectively augments LLMs into generative classifiers of harmfulness at all times during the conversation.<n>It also evaluates each generated answer rather than just the input prompt and provides a stronger defence against sampling-based attacks.
  arXiv  Detail & Related papers  (2025-02-22T21:48:48Z)
• Attention Tracker: Detecting Prompt Injection Attacks in LLMs [62.247841717696765]
  Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks.<n>We introduce the concept of the distraction effect, where specific attention heads shift focus from the original instruction to the injected instruction.<n>We propose Attention Tracker, a training-free detection method that tracks attention patterns on instruction to detect prompt injection attacks.
  arXiv  Detail & Related papers  (2024-11-01T04:05:59Z)
• Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries [22.24239212756129]
  We find that simply appending multiple end of sequence (eos) tokens can cause a phenomenon we call context segmentation.<n>We propose a straightforward method to BOOST jailbreak attacks by appending eos tokens.
  arXiv  Detail & Related papers  (2024-05-31T07:41:03Z)
• Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications [0.0]
  This paper introduces the 'Signed-Prompt' method as a novel solution for prompt injection attacks. The study involves signing sensitive instructions within command segments by authorized users, enabling the LLM to discern trusted instruction sources. Experiments demonstrate the effectiveness of the Signed-Prompt method, showing substantial resistance to various types of prompt injection attacks.
  arXiv  Detail & Related papers  (2024-01-15T11:44:18Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)
• Adversarial Camouflage for Node Injection Attack on Graphs [64.5888846198005]
  Node injection attacks on Graph Neural Networks (GNNs) have received increasing attention recently, due to their ability to degrade GNN performance with high attack success rates. Our study indicates that these attacks often fail in practical scenarios, since defense/detection methods can easily identify and remove the injected nodes. To address this, we devote to camouflage node injection attack, making injected nodes appear normal and imperceptible to defense/detection methods.
  arXiv  Detail & Related papers  (2022-08-03T02:48:23Z)
• Hidden Backdoor Attack against Semantic Segmentation Models [60.0327238844584]
  The emphbackdoor attack intends to embed hidden backdoors in deep neural networks (DNNs) by poisoning training data. We propose a novel attack paradigm, the emphfine-grained attack, where we treat the target label from the object-level instead of the image-level. Experiments show that the proposed methods can successfully attack semantic segmentation models by poisoning only a small proportion of training data.
  arXiv  Detail & Related papers  (2021-03-06T05:50:29Z)
• A Self-supervised Approach for Adversarial Robustness [105.88250594033053]
  Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems. This paper proposes a self-supervised adversarial training mechanism in the input space. It provides significant robustness against the textbfunseen adversarial attacks.
  arXiv  Detail & Related papers  (2020-06-08T20:42:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.