paper-with-me

Papers

AIJack: Let's Hijack AI! Security and Privacy Risk Simulator for Machine Learning

2023-12-29 · Hideaki Takahashi

This paper introduces AIJack, an open-source library designed to assess security and privacy risks associated with the training and deployment of machine learning models. Amid the growing interest in big data and AI, advancements in machine learning research and business are accelerating. However, recent studies reveal potential threats, such as the theft of training data and the manipulation of models by malicious attackers. Therefore, a comprehensive understanding of machine learning's security and privacy vulnerabilities is crucial for the safe integration of machine learning into real-world products. AIJack aims to address this need by providing a library with various attack and defense methods through a unified API. The library is publicly available on GitHub (https://github.com/Koukyosyumei/AIJack).

📄 PDF Abstract BibTeX arXiv:2312.17667

Code (1)

Koukyosyumei/AIJack 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models

2024-10-30 · Yucheng Zhang, Qinfeng Li, Tianyu Du, Xuhong Zhang 외

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge, making them adaptable and cost-effective for various applications. However, the growing reliance on the…

RAGRetrievalRetrieval-augmented Generation

F-RBA: A Federated Learning-based Framework for Risk-based Authentication

2024-12-16 · Hamidreza Fereidouni, Abdelhakim Senhaji Hafid, Dimitrios Makrakis, Yaser Baseri

The proliferation of Internet services has led to an increasing need to protect private data. User authentication serves as a crucial mechanism to ensure data security. Although robust authentication forms the cornerston…

Anomaly DetectionFeature EngineeringFederated LearningUnsupervised Anomaly Detection

Quantifying Conversation Drift in MCP via Latent Polytope

2025-08-08 · Haoran Shi, Hongwei Yao, Shuo Shao, Shaopeng Jiao 외 arxiv

The Model Context Protocol (MCP) enhances large language models (LLMs) by integrating external tools, enabling dynamic aggregation of real-time data to improve task execution. However, its non-isolated execution context …

Feature Space Hijacking Attacks against Differentially Private Split Learning

2022-01-11 · Grzegorz Gawron, Philip Stubbings

Split learning and differential privacy are technologies with growing potential to help with privacy-compliant advanced analytics on distributed datasets. Attacks against split learning are an important evaluation tool a…

Dimensionality Reduction

SnatchML: Hijacking ML models without Training Access

2024-06-03 · Mahmoud Ghorbel, Halima Bouzidi, Ioan Marius Bilasco, Ihsen Alouani

Model hijacking can cause significant accountability and security risks since the owner of a hijacked model can be framed for having their model offer illegal or unethical services. Prior works consider model hijacking a…