paper-with-me

Papers

SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning

2023-01-11 · Maxwell Standen, Junae Kim, Claudia Szabo

Multi-Agent Reinforcement Learning (MARL) is vulnerable to Adversarial Machine Learning (AML) attacks and needs adequate defences before it can be used in real world applications. We have conducted a survey into the use of execution-time AML attacks against MARL and the defences against those attacks. We surveyed related work in the application of AML in Deep Reinforcement Learning (DRL) and Multi-Agent Learning (MAL) to inform our analysis of AML for MARL. We propose a novel perspective to understand the manner of perpetrating an AML attack, by defining Attack Vectors. We develop two new frameworks to address a gap in current modelling frameworks, focusing on the means and tempo of an AML attack against MARL, and identify knowledge gaps and future avenues of research.

📄 PDF Abstract BibTeX arXiv:2301.04299

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Preventing Adversarial AI Attacks Against Autonomous Situational Awareness: A Maritime Case Study

2025-05-27 · Mathew J. Walter, Aaron Barrett, Kimberly Tam

Adversarial artificial intelligence (AI) attacks pose a significant threat to autonomous transportation, such as maritime vessels, that rely on AI components. Malicious actors can exploit these systems to deceive and man…

Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges

2022-01-20 · Nuria Rodríguez-Barroso, Daniel Jiménez López, M. Victoria Luzón, Francisco Herrera 외

Federated learning is a machine learning paradigm that emerges as a solution to the privacy-preservation demands in artificial intelligence. As machine learning, federated learning is threatened by adversarial attacks ag…

Adversarial AttackFederated Learning

Adversarial purification for no-reference image-quality metrics: applicability study and new methods

2024-04-10 · Aleksandr Gushchin, Anna Chistyakova, Vladislav Minashkin, Anastasia Antsiferova 외

Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability o…

Adversarial PurificationDenoising

Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey

2022-06-16 · Abhijith Sharma, Yijun Bian, Phil Munz, Apurva Narayan

Adversarial attacks in deep learning models, especially for safety-critical systems, are gaining more and more attention in recent years, due to the lack of trust in the security and robustness of AI models. Yet the more…

Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs

2025-02-21 · Giulio Zizzo, Giandomenico Cornacchia, Kieran Fraser, Muhammad Zaid Hameed 외

As large language models (LLMs) become integrated into everyday applications, ensuring their robustness and security is increasingly critical. In particular, LLMs can be manipulated into unsafe behaviour by prompts known…

Benchmarking