Image de couverture de livre

Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Krishna, Arjun, Galinkin, Erick, Derczynski, Leon, Martin, Jeffrey
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computation and Language Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

garak: A Framework for Security Probing Large Language Models
par: Derczynski, Leon, et autres
Publié: (2024)

Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models
par: Krishna, Arjun, et autres
Publié: (2025)

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings
par: Galinkin, Erick, et autres
Publié: (2024)

Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs
par: Price, Sara, et autres
Publié: (2024)

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
par: Chaudhari, Harsh, et autres
Publié: (2024)

Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming
par: Inie, Nanna, et autres
Publié: (2023)

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
par: Guo, Wenkai, et autres
Publié: (2025)

Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs
par: Liu, Ruixuan, et autres
Publié: (2026)

How Vulnerable Are Edge LLMs?
par: Ding, Ao, et autres
Publié: (2026)

Training a General Purpose Automated Red Teaming Model
par: Padmakumar, Aishwarya, et autres
Publié: (2026)

Towards Type Agnostic Cyber Defense Agents
par: Galinkin, Erick, et autres
Publié: (2024)

SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
par: Liang, Buyun, et autres
Publié: (2025)

LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning
par: Spracklen, Joseph, et autres
Publié: (2026)

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
par: Liang, Buyun, et autres
Publié: (2026)

Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs
par: Sivapiromrat, Sanhanat, et autres
Publié: (2025)

Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability
par: García-Carrasco, Jorge, et autres
Publié: (2024)

Exploring Vulnerabilities and Protections in Large Language Models: A Survey
par: Liu, Frank Weizhen, et autres
Publié: (2024)

Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures
par: Benjamin, Victoria, et autres
Publié: (2024)

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
par: Zhao, Andrew, et autres
Publié: (2025)

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
par: Shetty, Anudeex, et autres
Publié: (2024)

In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement
par: Shetty, Anudeex, et autres
Publié: (2026)

The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
par: Makroo, Owais, et autres
Publié: (2025)

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
par: Vinod, Vishnu, et autres
Publié: (2025)

Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses
par: Ahmed, Mohamed, et autres
Publié: (2025)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
par: Xiong, Alexander, et autres
Publié: (2025)

LLM Unlearning Should Be Form-Independent
par: Ye, Xiaotian, et autres
Publié: (2025)

GCG Attack On A Diffusion LLM
par: Neyroud, Ruben, et autres
Publié: (2025)

Localizing Malicious Outputs from CodeLLM
par: Borana, Mayukh, et autres
Publié: (2025)

LLMGuard: Guarding Against Unsafe LLM Behavior
par: Goyal, Shubh, et autres
Publié: (2024)

Sparse Autoencoders are Capable LLM Jailbreak Mitigators
par: Assogba, Yannick, et autres
Publié: (2026)

Using Hallucinations to Bypass GPT4's Filter
par: Lemkin, Benjamin
Publié: (2024)

Improving LLM Safety Alignment with Dual-Objective Optimization
par: Zhao, Xuandong, et autres
Publié: (2025)

PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
par: Duan, Haohua, et autres
Publié: (2025)

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
par: Wang, Tianchun, et autres
Publié: (2024)

Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
par: Zhang, Boyang, et autres
Publié: (2026)

User Inference Attacks on Large Language Models
par: Kandpal, Nikhil, et autres
Publié: (2023)

Evaluation of LLM Chatbots for OSINT-based Cyber Threat Awareness
par: Shafee, Samaneh, et autres
Publié: (2024)

Watermark under Fire: A Robustness Evaluation of LLM Watermarking
par: Liang, Jiacheng, et autres
Publié: (2024)

LLM Dataset Inference: Did you train on my dataset?
par: Maini, Pratyush, et autres
Publié: (2024)

On Calibration of LLM-based Guard Models for Reliable Content Moderation
par: Liu, Hongfu, et autres
Publié: (2024)