Image de couverture de livre

The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Bocheng, Guo, Hanqing, Wang, Guangjing, Wang, Yuanda, Yan, Qiben
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems
par: Wang, Guangjing, et autres
Publié: (2023)

Protecting Activity Sensing Data Privacy Using Hierarchical Information Dissociation
par: Wang, Guangjing, et autres
Publié: (2024)

ClearMask: Noise-Free and Naturalness-Preserving Protection Against Voice Deepfake Attacks
par: Wang, Yuanda, et autres
Publié: (2025)

FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
par: Chen, Bocheng, et autres
Publié: (2024)

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
par: Wang, Jiongxiao, et autres
Publié: (2023)

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
par: Fu, Tingchen, et autres
Publié: (2024)

Privacy-Preserving Diffusion Model Using Homomorphic Encryption
par: Chen, Yaojian, et autres
Publié: (2024)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
par: Xu, Zihao, et autres
Publié: (2024)

SoK: How Robust is Audio Watermarking in Generative AI models?
par: Wen, Yizhu, et autres
Publié: (2025)

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection
par: Li, Zongze, et autres
Publié: (2025)

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
par: Wu, Zihui, et autres
Publié: (2024)

Universal Jailbreak Backdoors from Poisoned Human Feedback
par: Rando, Javier, et autres
Publié: (2023)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
par: Zhao, Shiji, et autres
Publié: (2025)

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
par: Zhao, Shuai, et autres
Publié: (2025)

Distract Large Language Models for Automatic Jailbreak Attack
par: Xiao, Zeguan, et autres
Publié: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
par: Jiang, Tanqiu, et autres
Publié: (2024)

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts
par: Gong, Yichen, et autres
Publié: (2023)

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
par: Wu, Zongru, et autres
Publié: (2024)

Resource Consumption Threats in Large Language Models
par: Zhang, Yuanhe, et autres
Publié: (2026)

Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond
par: Wang, Xuhong, et autres
Publié: (2024)

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
par: Cao, Yuanpu, et autres
Publié: (2023)

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
par: Zou, Qingsong, et autres
Publié: (2025)

CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering
par: Chen, Baicheng, et autres
Publié: (2026)

Watermarking Language Models for Many Adaptive Users
par: Cohen, Aloni, et autres
Publié: (2024)

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
par: Gu, Tianle, et autres
Publié: (2024)

STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models
par: Wang, Xunguang, et autres
Publié: (2025)

Imperceptible Jailbreaking against Large Language Models
par: Gao, Kuofeng, et autres
Publié: (2025)

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
par: Wang, Yanbo, et autres
Publié: (2025)

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
par: Liang, Zi, et autres
Publié: (2025)

PRISON: Unmasking the Criminal Potential of Large Language Models
par: Wu, Xinyi, et autres
Publié: (2025)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
par: Wang, Libo
Publié: (2024)

SoK: Large Language Model Copyright Auditing via Fingerprinting
par: Shao, Shuo, et autres
Publié: (2025)

Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models
par: Zhong, Yisheng, et autres
Publié: (2025)

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
par: Tu, Shangqing, et autres
Publié: (2024)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
par: Yu, Miao, et autres
Publié: (2024)

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
par: Wang, Haoran, et autres
Publié: (2023)

Internal Safety Collapse in Frontier Large Language Models
par: Wu, Yutao, et autres
Publié: (2026)

Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging
par: Cong, Tianshuo, et autres
Publié: (2024)

Is the System Message Really Important to Jailbreaks in Large Language Models?
par: Zou, Xiaotian, et autres
Publié: (2024)

Measuring Copyright Risks of Large Language Model via Partial Information Probing
par: Zhao, Weijie, et autres
Publié: (2024)