Imagen de Portada

SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Kaihong, Zhou, Huichi, Ma, Bin, Huang, Fangjun
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Moral Reasoning Across Languages: The Critical Role of Low-Resource Languages in LLMs
por: Zhou, Huichi, et al.
Publicado: (2025)

DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising
por: Li, Zhenhao, et al.
Publicado: (2024)

Smart Audit System Empowered by LLM
por: Yao, Xu, et al.
Publicado: (2024)

Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge
por: Mu, Wenhan, et al.
Publicado: (2025)

Exposing Product Bias in LLM Investment Recommendation
por: Zhi, Yuhan, et al.
Publicado: (2025)

MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks
por: Zhang, Fangyuan, et al.
Publicado: (2024)

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
por: Li, Xueyi, et al.
Publicado: (2026)

iAgent: LLM Agent as a Shield between User and Recommender Systems
por: Xu, Wujiang, et al.
Publicado: (2025)

LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems
por: Gu, Shengkang, et al.
Publicado: (2025)

Chain Association-based Attacking and Shielding Natural Language Processing Systems
por: Huang, Jiacheng, et al.
Publicado: (2024)

LLM-Agnostic Semantic Representation Attack
por: Lian, Jiawei, et al.
Publicado: (2026)

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework
por: Ma, Binhao, et al.
Publicado: (2025)

Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks
por: Iyer, Karthik Raghu, et al.
Publicado: (2026)

LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
por: Xu, Jundong, et al.
Publicado: (2025)

Semantics as a Shield: Label Disguise Defense (LDD) against Prompt Injection in LLM Sentiment Classification
por: Li, Yanxi, et al.
Publicado: (2025)

FinNuE: Exposing the Risks of Using BERTScore for Numerical Semantic Evaluation in Finance
por: Huang, Yu-Shiang, et al.
Publicado: (2025)

Purely Semantic Indexing for LLM-based Generative Recommendation and Retrieval
por: Zhang, Ruohan, et al.
Publicado: (2025)

Membership Inference Attacks on LLM-based Recommender Systems
por: He, Jiajie, et al.
Publicado: (2025)

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
por: Li, Xirui, et al.
Publicado: (2024)

Polarization by Default: Auditing Recommendation Bias in LLM-Based Content Curation
por: Pagan, Nicolò, et al.
Publicado: (2026)

Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization
por: Sawant, Yash Ganpat
Publicado: (2026)

Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
por: Zhang, Haoyu, et al.
Publicado: (2026)

Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
por: Xiong, Yuan, et al.
Publicado: (2025)

Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation
por: Wang, Minhao, et al.
Publicado: (2025)

DECOR: Auditing LLM Deception via Information Manipulation Theory
por: Cai, Linyue, et al.
Publicado: (2026)

How Small Transformation Expose the Weakness of Semantic Similarity Measures
por: Nikiema, Serge Lionel, et al.
Publicado: (2025)

Auditing LLM Benchmarks with Item Response Theory
por: Land, Sander, et al.
Publicado: (2026)

Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
por: Sun, Yanming, et al.
Publicado: (2025)

Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems
por: Li, Chuang, et al.
Publicado: (2024)

LLM-based User Profile Management for Recommender System
por: Bang, Seunghwan, et al.
Publicado: (2025)

Recursive Knowledge Synthesis for Multi-LLM Systems: Stability Analysis and Tri-Agent Audit Framework
por: Shigemura, Toshiyuki
Publicado: (2025)

EviSearch: A Human in the Loop System for Extracting and Auditing Clinical Evidence for Systematic Reviews
por: Ahuja, Naman, et al.
Publicado: (2026)

Semi-structured LLM Reasoners Can Be Rigorously Audited
por: Leng, Jixuan, et al.
Publicado: (2025)

TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling
por: Li, Jiaqian, et al.
Publicado: (2026)

Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
por: Yu, Haocheng, et al.
Publicado: (2025)

Input Order Shapes LLM Semantic Alignment in Multi-Document Summarization
por: Ma, Jing
Publicado: (2025)

Advancing Recommender Systems by mitigating Shilling attacks
por: Chichani, Aditya, et al.
Publicado: (2024)

AuditWen:An Open-Source Large Language Model for Audit
por: Huang, Jiajia, et al.
Publicado: (2024)

Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling
por: Xu, Qingyang, et al.
Publicado: (2026)

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
por: Xu, Naen, et al.
Publicado: (2026)