Cover Image

Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Yiyi, Li, Qiongxiu, Biswas, Russa, Bjerva, Johannes
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security I.1.2; I.1.5
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks
by: Chen, Yiyi, et al.
Published: (2024)

Semantic Leakage from Image Embeddings
by: Chen, Yiyi, et al.
Published: (2026)

SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) Applications
by: Lee, Joshua, et al.
Published: (2025)

Towards Modeling Cybersecurity Behavior of Humans in Organizations
by: Kürtz, Klaas Ole
Published: (2026)

ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation
by: Chen, Yiyi, et al.
Published: (2025)

CSI2Dig: Recovering Digit Content from Smartphone Loudspeakers Using Channel State Information
by: Gu, Yangyang, et al.
Published: (2025)

Semantic Superiority vs. Forensic Efficiency: A Comparative Analysis of Deep Learning and Psycholinguistics for Business Email Compromise Detection
by: Adjei, Yaw Osei, et al.
Published: (2025)

Kernel-Based ReLU Approximation for Homomorphic Encryption-Compatible Privacy-preserving Deep Learning Models
by: Sygletos, Dimitrios, et al.
Published: (2026)

ZK-SenseLM: Verifiable Large-Model Wireless Sensing with Selective Abstention and Zero-Knowledge Attestation
by: Akgul, Hasan, et al.
Published: (2025)

Impact of Data Snooping on Deep Learning Models for Locating Vulnerabilities in Lifted Code
by: McCully, Gary A., et al.
Published: (2024)

Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code
by: McCully, Gary A., et al.
Published: (2024)

The LLMbda Calculus: AI Agents, Conversations, and Information Flow
by: Garby, Zac, et al.
Published: (2026)

Reducing Information Overload: Because Even Security Experts Need to Blink
by: Kuehn, Philipp, et al.
Published: (2022)

Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective
by: Lavrinovics, Ernests, et al.
Published: (2024)

Toward Secure and Compliant AI: Organizational Standards and Protocols for NLP Model Lifecycle Management
by: Arora, Sunil, et al.
Published: (2025)

CANAL -- Cyber Activity News Alerting Language Model: Empirical Approach vs. Expensive LLM
by: Patel, Urjitkumar, et al.
Published: (2024)

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks
by: Feng, Zhou, et al.
Published: (2025)

Bi-Directional Transformers vs. word2vec: Discovering Vulnerabilities in Lifted Compiled Code
by: McCully, Gary A., et al.
Published: (2024)

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
by: Chen, Renmiao, et al.
Published: (2025)

LLMLogAnalyzer: A Clustering-Based Log Analysis Chatbot using Large Language Models
by: Cai, Peng, et al.
Published: (2025)

Accelerating Language Model Workflows with Prompt Choreography
by: Bai, TJ, et al.
Published: (2025)

Sensitivity Uncertainty Alignment in Large Language Models
by: Hiremath, Prakul Sunil, et al.
Published: (2026)

SoK: Security Evaluation of Wi-Fi CSI Biometrics: Attacks, Metrics, and Open Challenges
by: Braga, Gioliano de Oliveira, et al.
Published: (2025)

Text Embedding Inversion Security for Multilingual Language Models
by: Chen, Yiyi, et al.
Published: (2024)

Improving Consistency in Large Language Models through Chain of Guidance
by: Raj, Harsh, et al.
Published: (2025)

Reliability and Admissibility of AI-Generated Forensic Evidence in Criminal Trials
by: Singh, Sahibpreet, et al.
Published: (2025)

Binary Image-Based Intrusion Detection for Operational Technology Networks: Extending the SPHBI Methodology from IoT to Modbus TCP
by: Omar, Aamir
Published: (2026)

Enhancing Federated Learning Convergence with Dynamic Data Queue and Data Entropy-driven Participant Selection
by: Herath, Charuka, et al.
Published: (2024)

Developing a Strong CPS Defender: An Evolutionary Approach
by: Hu, Qingyuan, et al.
Published: (2025)

TRIGS: Trojan Identification from Gradient-based Signatures
by: Hussein, Mohamed E., et al.
Published: (2023)

Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors
by: Ma, Chen, et al.
Published: (2025)

LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization
by: Yu, Wenrui, et al.
Published: (2025)

Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey
by: Chung, Jonghyun, et al.
Published: (2026)

ConfusionPrompt: Practical Private Inference for Online Large Language Models
by: Mai, Peihua, et al.
Published: (2023)

Tool Receipts, Not Zero-Knowledge Proofs: Practical Hallucination Detection for AI Agents
by: Basu, Abhinaba
Published: (2026)

Countermind: A Multi-Layered Security Architecture for Large Language Models
by: Schwarz, Dominik
Published: (2025)

Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints
by: Reddy, Sandeep, et al.
Published: (2025)

NeuroLog: Reasoning You Can Audit -- Neuro-Symbolic Vulnerability Discovery via LLM Facts, Datalog, and SMT
by: Rawat, Sanjay
Published: (2026)

SCAFDS: Edge-Feature Graph Attention for Interbank Fraud Detection with Attribution-Grounded SAR Generation
by: Uddin, Mohammad Nasir
Published: (2026)

Learning the Signature of Memorization in Autoregressive Language Models
by: Ilić, David, et al.
Published: (2026)