24 matches found
CureIAM
CureIAM Автоматическая очистка чрезмерно привилегированных IAM-аккаунтов в GCP инфраструктуре CureIAM — это простой в использовании, надежный и производительный механизм для обеспечения принципа наименьших привилегий в облачной инфраструктуре GCP. Он позволяет командам DevOps и безопасности быстр...
AGAS
추천 시스템에 대한 효율적이고 효과적인 에이전트 그룹 셸링 공격 이것은 논문 "추천 시스템에 대한 효율적이고 효과적인 에이전트 그룹 셸링 공격"의 공식 코드입니다. 이 논문은 AGAS를 소개하는데, 이는 블랙박스 협업 필터링 추천 시스템에 대한 LLM 기반 셸링 공격입니다. 하나의 Coordinator 가 여러 라운드에 걸쳐 가짜 사용자 worker 풀을 조정합니다. 각 라운드에서 Coordinator는 여덟 가지 전략 중 하나를 선택하고 모든 worker에게 역할을 할당합니다. 그런 다음 worker는 자체적인 ReAct 스...
EUVD-2019-0120
Malware in sbrugna...
MAL-2025-25597 Malicious code in loopback4-example-recommender (npm)
The package loopback4-example-recommender was found to contain malicious code...
Malicious code in loopback4-example-recommender (npm)
The package loopback4-example-recommender was found to contain malicious code...
LLM4MEA: Data-Free Model Extraction Attacks on Sequential Recommenders Via Large Language Models
Recent studies have demonstrated the vulnerability of sequential recommender systems to Model Extraction Attacks MEAs. MEAs collect responses from recommender systems to replicate their functionality, enabling unauthorized deployments and posing critical privacy and security risks. Black-box...
Phantom Subgroup Poisoning: Stealth Attacks on Federated Recommender Systems
Federated recommender systems FedRec have emerged as a promising solution for delivering personalized recommendations while safeguarding user privacy. However, recent studies have demonstrated their vulnerability to poisoning attacks. Existing attacks typically target the entire user group, which...
ImpReSS: Implicit Recommender System for Support Conversations
Following recent advancements in large language models LLMs, LLM-based chatbots have transformed customer support by automating interactions and providing consistent, scalable service. While LLM-based conversational recommender systems CRSs have attracted attention for their ability to enhance th...
SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
Federated recommender system FedRec has emerged as a solution to protect user data through collaborative training techniques. A typical FedRec involves transmitting the full model and entire weight updates between edge devices and the server, causing significant burdens to devices with limited...
RAID: an In-Training Defense against Attribute Inference Attacks in Recommender Systems
In various networks and mobile applications, users are highly susceptible to attribute inference attacks, with particularly prevalent occurrences in recommender systems. Attackers exploit partially exposed user profiles in recommendation models, such as user embeddings, to infer private attribute...
Exploring Backdoor Attack and Defense for LLM-Empowered Recommendations
The fusion of Large Language Models LLMs with recommender systems RecSys has dramatically advanced personalized recommendations and drawn extensive attention. Despite the impressive progress, the safety of LLM-based RecSys against backdoor attacks remains largely under-explored. In this paper, we...
NuGet Package 'Microsoft.ML.Recommender' Detection
The remote host has a 'Microsoft.ML.Recommender' with a Verified NuGet package status and is installed on the remote host. Nessus has not tested for this issue but has instead relied only on the application's self-reported version number. %NASLMINLEVEL 80900 C Tenable, Inc. include'compat.inc'; i...
MaianAffiliate Cross-Site Scripting Vulnerability (CNVD-2022-62192)
MaianAffiliate v.1.0 is a free, simple but powerful php recommender system written in PHP. in the context of authenticated and unauthenticated users...
MaianAffiliate 跨站脚本漏洞
MaianAffiliate v.1.0 is a free, simple but powerful php recommender system written in PHP. in the context of authenticated and unauthenticated users...
Cross-site scripting in recommender-xblock
Recommender before 1.3.1 allows XSS. It is possible for a learner to craft a fake resource to recommender, that includes script which could possibly steal credentials from staff if they are lured into viewing the recommended resource...
GHSA-3J5X-7CCF-PPGM Cross-site scripting in recommender-xblock
Recommender before 1.3.1 allows XSS. It is possible for a learner to craft a fake resource to recommender, that includes script which could possibly steal credentials from staff if they are lured into viewing the recommended resource...
Recommender Cross-Site Scripting Vulnerability
Recommender is an information filtering system. The system recommends content to users by predicting their "ratings" or "preferences" for items. A cross-site scripting vulnerability exists in Recommender versions prior to 2018-07-18. The vulnerability stems from a lack of proper validation of...
CVE-2018-20858
Recommender before 2018-07-18 allows XSS...
