The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

• URL: http://arxiv.org/abs/2404.13208v1
• Date: Fri, 19 Apr 2024 22:55:23 GMT
• Title: The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
• Authors: Eric Wallace, Kai Xiao, Reimar Leike, Lilian Weng, Johannes Heidecke, Alex Beutel,
• Abstract summary: LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts. We propose an instruction hierarchy that explicitly defines how models should behave when instructions of different priorities conflict. We apply this method to GPT-3.5, showing that it drastically increases robustness -- even for attack types not seen during training -- while imposing minimal degradations on standard capabilities.
• Score: 21.76697662025996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts. In this work, we argue that one of the primary vulnerabilities underlying these attacks is that LLMs often consider system prompts (e.g., text from an application developer) to be the same priority as text from untrusted users and third parties. To address this, we propose an instruction hierarchy that explicitly defines how models should behave when instructions of different priorities conflict. We then propose a data generation method to demonstrate this hierarchical instruction following behavior, which teaches LLMs to selectively ignore lower-privileged instructions. We apply this method to GPT-3.5, showing that it drastically increases robustness -- even for attack types not seen during training -- while imposing minimal degradations on standard capabilities.

Related papers

• Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy [53.54777131440989]
  Large Language Models (LLMs) are susceptible to security and safety threats. One major cause of these vulnerabilities is the lack of an instruction hierarchy. We introduce the instructional segment Embedding (ISE) technique, inspired by BERT, to modern large language models.
  arXiv  Detail & Related papers  (2024-10-09T12:52:41Z)
• Aligning LLMs to Be Robust Against Prompt Injection [55.07562650579068]
  We show that alignment can be a powerful tool to make LLMs more robust against prompt injection attacks. Our method -- SecAlign -- first builds an alignment dataset by simulating prompt injection attacks. Our experiments show that SecAlign robustifies the LLM substantially with a negligible hurt on model utility.
  arXiv  Detail & Related papers  (2024-10-07T19:34:35Z)
• MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants [14.947665219536708]
  We introduce the Malicious Programming Prompt (MaPP) attack, in which an attacker adds a small amount of text to a prompt for a programming task. We show that our prompt strategy can cause an LLM to add vulnerabilities while continuing to write otherwise correct code.
  arXiv  Detail & Related papers  (2024-07-12T22:30:35Z)
• AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting [54.931241667414184]
  We propose textbfAdaptive textbfShield Prompting, which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks. Our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks.
  arXiv  Detail & Related papers  (2024-03-14T15:57:13Z)
• Instruction Backdoor Attacks Against Customized LLMs [37.92008159382539]
  We propose the first instruction backdoor attacks against applications integrated with untrusted customized LLMs. Our attack includes 3 levels of attacks: word-level, syntax-level, and semantic-level, which adopt different types of triggers with progressive stealthiness. We propose two defense strategies and demonstrate their effectiveness in reducing such attacks.
  arXiv  Detail & Related papers  (2024-02-14T13:47:35Z)
• StruQ: Defending Against Prompt Injection with Structured Queries [10.22774624798198]
  Large Language Models (LLMs) can perform text-based tasks by utilizing their advanced language understanding capabilities. Prompt injection attacks are an important threat, they trick the model into deviating from the original application's instructions and instead follow user directives. We introduce structured queries, a general approach to tackle this problem. Our system significantly improves resistance to prompt injection attacks, with little or no impact on utility.
  arXiv  Detail & Related papers  (2024-02-09T12:15:51Z)
• From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning [63.63840740526497]
  We investigate how instruction tuning adjusts pre-trained models with a focus on intrinsic changes. The impact of instruction tuning is then studied by comparing the explanations derived from the pre-trained and instruction-tuned models. Our findings reveal three significant impacts of instruction tuning.
  arXiv  Detail & Related papers  (2023-09-30T21:16:05Z)
• Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection [70.28425745910711]
  Large Language Models (LLMs) have demonstrated exceptional proficiency in instruction-following. This capability brings with it the risk of prompt injection attacks. We evaluate the robustness of instruction-following LLMs against such attacks.
  arXiv  Detail & Related papers  (2023-08-17T06:21:50Z)
• Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting [55.15697111170836]
  This paper reveals the behaviors of large language models (LLMs) towards textitinductive instructions and enhance their truthfulness and helpfulness accordingly. After extensive human and automatic evaluations, we uncovered a universal vulnerability among LLMs in processing inductive instructions. We identify that different inductive styles affect the models' ability to identify the same underlying errors, and the complexity of the underlying assumptions also influences the model's performance.
  arXiv  Detail & Related papers  (2023-05-23T06:38:20Z)

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.