中文
相关论文

相关论文: Attacks and Mitigations for Distributed Governance…

200 篇论文

This paper addresses federated learning (FL) in the context of malicious Byzantine attacks and data heterogeneity. We introduce a novel Robust Average Gradient Algorithm (RAGA), which uses the geometric median for aggregation and {allows…

机器学习 · 计算机科学 2025-09-30 Shiyuan Zuo , Xingrun Yan , Rongfei Fan , Han Hu , Hangguan Shan , Tony Q. S. Quek , Puning Zhao

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…

密码学与安全 · 计算机科学 2026-03-25 Ali Dehghantanha , Sajad Homayoun

Implementations of SGD on distributed systems create new vulnerabilities, which can be identified and misused by one or more adversarial agents. Recently, it has been shown that well-known Byzantine-resilient gradient aggregation schemes…

机器学习 · 计算机科学 2022-09-26 Ali Ramezani-Kebrya , Iman Tabrizian , Fartash Faghri , Petar Popovski

Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also become a source of vulnerability, as unreliable or Byzantine agents may sway…

多智能体系统 · 计算机科学 2026-05-12 Haejoon Lee , Vincent-Daniel Yun , Hyeonho Oh , Dimitra Panagou , Sai Praneeth Karimireddy

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, but its robustness is threatened by Byzantine behaviors such as data and model poisoning. Existing defenses face fundamental…

密码学与安全 · 计算机科学 2025-09-12 Usama Zafar , André M. H. Teixeira , Salman Toor

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust…

机器学习 · 计算机科学 2023-06-06 Yuchen Liu , Chen Chen , Lingjuan Lyu , Fangzhao Wu , Sai Wu , Gang Chen

Recently emerged federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Compared with the traditional machine…

密码学与安全 · 计算机科学 2022-10-10 Junyu Shi , Wei Wan , Shengshan Hu , Jianrong Lu , Leo Yu Zhang

Recent advancements in machine learning have improved performance while also increasing computational demands. While federated and distributed setups address these issues, their structures remain vulnerable to malicious influences. In this…

Privacy-preserving federated averaging is a central approach for protecting client privacy in federated learning. In this paper, we study this problem in an asynchronous communications setting with malicious aggregators. We propose a new…

分布式、并行与集群计算 · 计算机科学 2026-01-09 Antonella Del Pozzo , Achille Desreumaux , Mathieu Gestin , Alexandre Rapetti , Sara Tucci-Piergiovanni

The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build integrity mechanisms cannot be used anymore. The available frameworks like SLSA, SBOM and in…

密码学与安全 · 计算机科学 2025-12-30 Toqeer Ali Syed , Mohammad Riyaz Belgaum , Salman Jan , Asadullah Abdullah Khan , Saad Said Alqahtani

The rapid adoption of agentic AI, powered by large language models (LLMs), is transforming enterprise ecosystems with autonomous agents that execute complex workflows. Yet we observe several key security vulnerabilities in LLM-driven…

密码学与安全 · 计算机科学 2025-09-23 Zhenhua Zou , Zhuotao Liu , Lepeng Zhao , Qiuyang Zhan

Federated learning (FL) becomes vulnerable to Byzantine attacks where some of participators tend to damage the utility or discourage the convergence of the learned model via sending their malicious model updates. Previous works propose to…

密码学与安全 · 计算机科学 2024-08-13 Fangyuan Zhao , Yuexiang Xie , Xuebin Ren , Bolin Ding , Shusen Yang , Yaliang Li

Current network protection systems use a collection of intelligent components - e.g. classifiers or rule-based firewall systems to detect intrusions and anomalies and to secure a network against viruses, worms, or trojans. However, these…

密码学与安全 · 计算机科学 2008-05-08 Michael Hilker , Christoph Schommer

Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent…

密码学与安全 · 计算机科学 2025-06-24 Sunil Kumar Jang Bahadur , Gopala Dhar

Modern distributed systems face growing security threats, as attackers continuously enhance their skills and vulnerabilities span across the entire system stack, from hardware to the application layer. In the system design phase, fault…

分布式、并行与集群计算 · 计算机科学 2025-11-07 Silvia Bonomi , Giovanni Farina , Roy Friedman , Eviatar B. Procaccia , Sebastien Tixeuil

This research paper explores the privacy and security threats posed to an Agentic AI system with direct access to database systems. Such access introduces significant risks, including unauthorized retrieval of sensitive information,…

密码学与安全 · 计算机科学 2024-12-10 Raihan Khan , Sayak Sarkar , Sainik Kumar Mahata , Edwin Jose

This paper introduces the Agentic AI Governance Assurance & Trust Engine (AAGATE), a Kubernetes-native control plane designed to address the unique security and governance challenges posed by autonomous, language-model-driven agents in…

Recent advances in generative AI have enabled sophisticated multi-agent architectures for healthcare, where large language models power collaborative clinical decision-making. However, these distributed systems face critical challenges in…

分布式、并行与集群计算 · 计算机科学 2025-12-23 Nihir Chadderwala

Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking a transition from reactive content generation into…

软件工程 · 计算机科学 2025-12-29 Brian Bowers , Smita Khapre , Jugal Kalita

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…

机器学习 · 计算机科学 2026-04-07 Ninghui Li , Kaiyuan Zhang , Kyle Polley , Jerry Ma