paper-with-me

Papers

Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code

2024-03-11 · Cristina Improta

AI-based code generators have gained a fundamental role in assisting developers in writing software starting from natural language (NL). However, since these large language models are trained on massive volumes of data collected from unreliable online sources (e.g., GitHub, Hugging Face), AI models become an easy target for data poisoning attacks, in which an attacker corrupts the training data by injecting a small amount of poison into it, i.e., astutely crafted malicious samples. In this position paper, we address the security of AI code generators by identifying a novel data poisoning attack that results in the generation of vulnerable code. Next, we devise an extensive evaluation of how these attacks impact state-of-the-art models for code generation. Lastly, we discuss potential solutions to overcome this threat.

📄 PDF Abstract BibTeX arXiv:2403.06675

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationData PoisoningPosition

Similar Papers 제목 키워드 기반

A Systematic Review of Poisoning Attacks Against Large Language Models

2025-06-06 · Neil Fendley, Edward W. Staley, Joshua Carney, William Redman 외

With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased significantly. One of these security ri…

Turning Generative Models Degenerate: The Power of Data Poisoning Attacks

2024-07-17 · Shuli Jiang, Swanand Ravindra Kadhe, Yi Zhou, Farhan Ahmed 외

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable …

Data Poisoningparameter-efficient fine-tuningText GenerationText Summarization

Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks

2023-12-07 · Shuli Jiang, Swanand Ravindra Kadhe, Yi Zhou, Ling Cai 외

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnera…

Data Poisoningobject-detectionObject DetectionText Generation

VPN: Verification of Poisoning in Neural Networks

2022-05-08 · Youcheng Sun, Muhammad Usman, Divya Gopinath, Corina S. Păsăreanu

Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification techniques for verifying neural network prop…

Data Poisoningimage-classificationImage ClassificationNeural Network Security

A Survey on Poisoning Attacks Against Supervised Machine Learning

2022-02-05 · Wenjun Qiu

With the rise of artificial intelligence and machine learning in modern computing, one of the major concerns regarding such techniques is to provide privacy and security against adversaries. We present this survey paper …

BIG-bench Machine LearningSurvey