CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

• URL: http://arxiv.org/abs/2403.07865v4
• Date: Sun, 9 Jun 2024 15:04:34 GMT
• Title: CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
• Authors: Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Wai Lam, Lizhuang Ma,
• Abstract summary: This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs. Our studies reveal a new and universal safety vulnerability of these models against code input. We find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization.
• Score: 117.178835165855
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from human feedback have enhanced their safety, these methods primarily focus on natural languages, which may not generalize to other domains. This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs, presenting a novel environment for testing the safety generalization of LLMs. Our comprehensive studies on state-of-the-art LLMs including GPT-4, Claude-2, and Llama-2 series reveal a new and universal safety vulnerability of these models against code input: CodeAttack bypasses the safety guardrails of all models more than 80\% of the time. We find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization, such as encoding natural language input with data structures. Furthermore, we give our hypotheses about the success of CodeAttack: the misaligned bias acquired by LLMs during code training, prioritizing code completion over avoiding the potential safety risk. Finally, we analyze potential mitigation measures. These findings highlight new safety risks in the code domain and the need for more robust safety alignment algorithms to match the code capabilities of LLMs.

Related papers

• Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval [20.959848710829878]
  Large language models (LLMs) have brought significant advancements to code generation and code repair. However, their training using unsanitized data from open-source repositories, like GitHub, raises the risk of inadvertently propagating security vulnerabilities. We aim to present a comprehensive study aimed at precisely evaluating and enhancing the security aspects of code LLMs.
  arXiv  Detail & Related papers  (2024-07-02T16:13:21Z)
• Can We Trust Large Language Models Generated Code? A Framework for In-Context Learning, Security Patterns, and Code Evaluations Across Diverse LLMs [2.7138982369416866]
  Large Language Models (LLMs) have revolutionized automated code generation in software engineering. However, concerns have arisen regarding the security and quality of the generated code. Our research aims to tackle these issues by introducing a framework for secure behavioral learning of LLMs.
  arXiv  Detail & Related papers  (2024-06-18T11:29:34Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming [64.86326523181553]
  ALERT is a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy. It aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models.
  arXiv  Detail & Related papers  (2024-04-06T15:01:47Z)
• ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding [89.0074567748505]
  We present reverse prompt contrastive decoding (ROSE), a simple-yet-effective method to boost the safety of existing instruction-tuned LLMs without any additional training. Experiments on 6 safety and 2 general-purpose tasks show that, our ROSE not only brings consistent and significant safety improvements (up to +13.8% safety score) upon 5 types of instruction-tuned LLMs, but also benefits the general-purpose ability of LLMs.
  arXiv  Detail & Related papers  (2024-02-19T06:58:42Z)
• Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities [12.82645410161464]
  Large Language Models (LLMs) have demonstrated remarkable performance on code-related tasks. We evaluate whether pre-trained LLMs can detect security vulnerabilities and address the limitations of existing tools.
  arXiv  Detail & Related papers  (2023-11-16T13:17:20Z)
• Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation [24.668682498171776]
  Large language models (LLMs) have brought significant advancements to code generation, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, introduces the risk of inadvertently propagating security vulnerabilities. This paper presents a comprehensive study focused on evaluating and enhancing code LLMs from a software security perspective.
  arXiv  Detail & Related papers  (2023-10-25T00:32:56Z)
• Red Teaming Language Model Detectors with Language Models [114.36392560711022]
  Large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. Recent works have proposed algorithms to detect LLM-generated text and protect LLMs. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation.
  arXiv  Detail & Related papers  (2023-05-31T10:08:37Z)
• CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models [58.27254444280376]
  Large language models (LLMs) for automatic code generation have achieved breakthroughs in several programming tasks. Training data for these models is usually collected from the Internet (e.g., from open-source repositories) and is likely to contain faults and security vulnerabilities. This unsanitized training data can cause the language models to learn these vulnerabilities and propagate them during the code generation procedure.
  arXiv  Detail & Related papers  (2023-02-08T11:54:07Z)

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.