On Extracting Specialized Code Abilities from Large Language Models: A
Feasibility Study
- URL: http://arxiv.org/abs/2303.03012v4
- Date: Tue, 31 Oct 2023 13:37:00 GMT
- Title: On Extracting Specialized Code Abilities from Large Language Models: A
Feasibility Study
- Authors: Zongjie Li, Chaozheng Wang, Pingchuan Ma, Chaowei Liu, Shuai Wang,
Daoyuan Wu, Cuiyun Gao, Yang Liu
- Abstract summary: We investigate the feasibility of launching imitation attacks on large language models (LLMs)
We show that attackers can train a medium-sized backbone model to replicate specialized code behaviors similar to the target LLMs.
- Score: 22.265542509143756
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent advances in large language models (LLMs) significantly boost their
usage in software engineering. However, training a well-performing LLM demands
a substantial workforce for data collection and annotation. Moreover, training
datasets may be proprietary or partially open, and the process often requires a
costly GPU cluster. The intellectual property value of commercial LLMs makes
them attractive targets for imitation attacks, but creating an imitation model
with comparable parameters still incurs high costs. This motivates us to
explore a practical and novel direction: slicing commercial black-box LLMs
using medium-sized backbone models. In this paper, we explore the feasibility
of launching imitation attacks on LLMs to extract their specialized code
abilities, such as"code synthesis" and "code translation." We systematically
investigate the effectiveness of launching code ability extraction attacks
under different code-related tasks with multiple query schemes, including
zero-shot, in-context, and Chain-of-Thought. We also design response checks to
refine the outputs, leading to an effective imitation training process. Our
results show promising outcomes, demonstrating that with a reasonable number of
queries, attackers can train a medium-sized backbone model to replicate
specialized code behaviors similar to the target LLMs. We summarize our
findings and insights to help researchers better understand the threats posed
by imitation attacks, including revealing a practical attack surface for
generating adversarial code examples against LLMs.
Related papers
- SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors [0.0]
Large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks, such as code understanding and code generation.
However, an equally important yet underexplored question is whether LLMs can serve as general-purpose surrogate code executors.
This study provides empirical insights into the feasibility of using LLMs as surrogate code executors.
arXiv Detail & Related papers (2025-02-16T15:38:19Z) - Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.
Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.
We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
arXiv Detail & Related papers (2025-02-04T17:26:58Z) - What You See Is Not Always What You Get: An Empirical Study of Code Comprehension by Large Language Models [0.5735035463793009]
We investigate the vulnerability of large language models (LLMs) to imperceptible attacks, where hidden character manipulation in source code misleads LLMs' behaviour while remaining undetectable to human reviewers.
These attacks include coding reordering, invisible coding characters, code deletions, and code homoglyphs.
Our findings confirm the susceptibility of LLMs to imperceptible coding character attacks, while different LLMs present different negative correlations between perturbation magnitude and performance.
arXiv Detail & Related papers (2024-12-11T04:52:41Z) - OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models [70.72097493954067]
Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems.
While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs remain limited.
We introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community.
arXiv Detail & Related papers (2024-11-07T17:47:25Z) - Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data.
We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
arXiv Detail & Related papers (2024-10-22T06:43:28Z) - zsLLMCode: An Effective Approach for Functional Code Embedding via LLM with Zero-Shot Learning [6.976968804436321]
Large language models (LLMs) have the capability of zero-shot learning, which does not require training or fine-tuning.
We propose zsLLMCode, a novel approach that generates functional code embeddings using LLMs.
arXiv Detail & Related papers (2024-09-23T01:03:15Z) - An Empirical Study of Automated Vulnerability Localization with Large Language Models [21.84971967029474]
Large Language Models (LLMs) have shown potential in various domains, yet their effectiveness in vulnerability localization remains underexplored.
Our investigation encompasses 10+ leading LLMs suitable for code analysis, including ChatGPT and various open-source models.
We explore the efficacy of these LLMs using 4 distinct paradigms: zero-shot learning, one-shot learning, discriminative fine-tuning, and generative fine-tuning.
arXiv Detail & Related papers (2024-03-30T08:42:10Z) - Knowledge Fusion of Large Language Models [73.28202188100646]
This paper introduces the notion of knowledge fusion for large language models (LLMs)
We externalize their collective knowledge and unique strengths, thereby elevating the capabilities of the target model beyond those of any individual source LLM.
Our findings confirm that the fusion of LLMs can improve the performance of the target model across a range of capabilities such as reasoning, commonsense, and code generation.
arXiv Detail & Related papers (2024-01-19T05:02:46Z) - If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code
Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
Large language models (LLMs) are trained on a combination of natural language and formal language (code)
Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
arXiv Detail & Related papers (2024-01-01T16:51:20Z) - Transfer Attacks and Defenses for Large Language Models on Coding Tasks [30.065641782962974]
We study the effect of adversarial perturbations on coding tasks with large language models (LLMs)
We propose prompt-based defenses that involve modifying the prompt to include examples of adversarially perturbed code and explicit instructions for reversing adversarial perturbations.
Our experiments show that adversarial examples obtained with a smaller code model are indeed transferable, weakening the LLMs' performance.
arXiv Detail & Related papers (2023-11-22T15:11:35Z) - Language models are weak learners [71.33837923104808]
We show that prompt-based large language models can operate effectively as weak learners.
We incorporate these models into a boosting approach, which can leverage the knowledge within the model to outperform traditional tree-based boosting.
Results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
arXiv Detail & Related papers (2023-06-25T02:39:19Z)
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.