Copertina

Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Wang, Chunxiao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence Computation and Language Information Retrieval Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
di: Gong, Yuyang, et al.
Pubblicazione: (2026)

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
di: Liu, Kangwei, et al.
Pubblicazione: (2025)

EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
di: Lin, Sam, et al.
Pubblicazione: (2024)

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?
di: Shah, Syed Huma
Pubblicazione: (2026)

Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning
di: Guo, Junfeng, et al.
Pubblicazione: (2025)

User-Side Realization
di: Sato, Ryoma
Pubblicazione: (2024)

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
di: Naseh, Ali, et al.
Pubblicazione: (2025)

TableGuard -- Securing Structured & Unstructured Data
di: Sharma, Anantha, et al.
Pubblicazione: (2024)

BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
di: Xue, Jiaqi, et al.
Pubblicazione: (2024)

Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
di: Liu, Yu-An, et al.
Pubblicazione: (2024)

Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations
di: Salemi, Alireza, et al.
Pubblicazione: (2026)

One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness
di: Deguchi, Hiroyuki, et al.
Pubblicazione: (2026)

SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
di: Mishra, Saroj, et al.
Pubblicazione: (2026)

Token-wise Influential Training Data Retrieval for Large Language Models
di: Lin, Huawei, et al.
Pubblicazione: (2024)

PII-Bench: Evaluating Query-Aware Privacy Protection Systems
di: Shen, Hao, et al.
Pubblicazione: (2025)

TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence
di: Simoni, Marco, et al.
Pubblicazione: (2025)

Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems
di: Yao, Mengyu, et al.
Pubblicazione: (2026)

Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems
di: Lilienthal, Derek, et al.
Pubblicazione: (2023)

LSTM Recurrent Neural Networks for Cybersecurity Named Entity Recognition
di: Gasmi, Houssem, et al.
Pubblicazione: (2024)

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

Know Your Neighborhood: General and Zero-Shot Capable Binary Function Search Powered by Call Graphlets
di: Collyer, Joshua, et al.
Pubblicazione: (2024)

PhishLang: A Real-Time, Fully Client-Side Phishing Detection Framework Using MobileBERT
di: Roy, Sayak Saha, et al.
Pubblicazione: (2024)

RAID: An In-Training Defense against Attribute Inference Attacks in Recommender Systems
di: Feng, Xiaohua, et al.
Pubblicazione: (2025)

A Robust Cybersecurity Topic Classification Tool
di: Pelofske, Elijah, et al.
Pubblicazione: (2021)

Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training
di: Zhao, Shuai, et al.
Pubblicazione: (2024)

Exploiting Class Probabilities for Black-box Sentence-level Attacks
di: Moraffah, Raha, et al.
Pubblicazione: (2024)

PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding
di: Nakka, Krishna Kanth, et al.
Pubblicazione: (2024)

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
di: Chen, Zhaorun, et al.
Pubblicazione: (2024)

Preserving Privacy and Utility in LLM-Based Product Recommendations
di: Khezresmaeilzadeh, Tina, et al.
Pubblicazione: (2025)

Towards Contextual Sensitive Data Detection
di: Telkamp, Liang, et al.
Pubblicazione: (2025)

Toward Autonomous SOC Operations: End-to-End LLM Framework for Threat Detection, Query Generation, and Resolution in Security Operations
di: Saju, Md Hasan, et al.
Pubblicazione: (2026)

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
di: Wang, Yifei, et al.
Pubblicazione: (2024)

Federated In-Context LLM Agent Learning
di: Wu, Panlong, et al.
Pubblicazione: (2024)

Persona-Model Collapse in Emergent Misalignment
di: Costa, Davi Bastos, et al.
Pubblicazione: (2026)

ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
di: Zhang, Lingxi, et al.
Pubblicazione: (2024)

AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
di: Du, Yuntao, et al.
Pubblicazione: (2026)

Forgetting-MarI: LLM Unlearning via Marginal Information Regularization
di: Xu, Shizhou, et al.
Pubblicazione: (2025)

SQuaD: The Software Quality Dataset
di: Robredo, Mikel, et al.
Pubblicazione: (2025)

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents
di: Yang, Shiyi, et al.
Pubblicazione: (2025)