Buchumschlag

Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Liu, Hongfu, Xie, Yuxi, Wang, Ye, Shieh, Michael
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Cryptography and Security Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
von: Brown, Hannah, et al.
Veröffentlicht: (2024)

On Calibration of LLM-based Guard Models for Reliable Content Moderation
von: Liu, Hongfu, et al.
Veröffentlicht: (2024)

PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
von: Zhu, Kaijie, et al.
Veröffentlicht: (2023)

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
von: Tang, Haochun, et al.
Veröffentlicht: (2026)

Hijacking Large Language Models via Adversarial In-Context Learning
von: Zhou, Xiangyu, et al.
Veröffentlicht: (2023)

On Adversarial Robustness of Language Models in Transfer Learning
von: Turbal, Bohdan, et al.
Veröffentlicht: (2024)

Adversarial Attack on Large Language Models using Exponentiated Gradient Descent
von: Biswas, Sajib, et al.
Veröffentlicht: (2025)

MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction
von: Hu, Xiao, et al.
Veröffentlicht: (2025)

Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting
von: Liu, Fuqiang, et al.
Veröffentlicht: (2024)

Adversarial Text Purification: A Large Language Model Approach for Defense
von: Moraffah, Raha, et al.
Veröffentlicht: (2024)

Learning to Poison Large Language Models for Downstream Manipulation
von: Zhou, Xiangyu, et al.
Veröffentlicht: (2024)

The Resurgence of GCG Adversarial Attacks on Large Language Models
von: Tan, Yuting, et al.
Veröffentlicht: (2025)

Privacy Preserving In-Context-Learning Framework for Large Language Models
von: Bhusal, Bishnu, et al.
Veröffentlicht: (2025)

Composite Backdoor Attacks Against Large Language Models
von: Huang, Hai, et al.
Veröffentlicht: (2023)

Digger: Detecting Copyright Content Mis-usage in Large Language Model Training
von: Li, Haodong, et al.
Veröffentlicht: (2024)

Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
von: Huo, Mingjia, et al.
Veröffentlicht: (2024)

Exploring Vulnerabilities and Protections in Large Language Models: A Survey
von: Liu, Frank Weizhen, et al.
Veröffentlicht: (2024)

CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models
von: Lou, Qian, et al.
Veröffentlicht: (2024)

Token-Modification Adversarial Attacks for Natural Language Processing: A Survey
von: Roth, Tom, et al.
Veröffentlicht: (2021)

MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector
von: Fu, Wenjie, et al.
Veröffentlicht: (2024)

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
von: Yin, Haoteng, et al.
Veröffentlicht: (2024)

Network Traffic Classification Using Machine Learning, Transformer, and Large Language Models
von: Antari, Ahmad, et al.
Veröffentlicht: (2025)

What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference
von: Fan, Mingyuan, et al.
Veröffentlicht: (2026)

Detecting Pretraining Data from Large Language Models
von: Shi, Weijia, et al.
Veröffentlicht: (2023)

SOS! Soft Prompt Attack Against Open-Source Large Language Models
von: Yang, Ziqing, et al.
Veröffentlicht: (2024)

Model Provenance Testing for Large Language Models
von: Nikolic, Ivica, et al.
Veröffentlicht: (2025)

A Watermark for Large Language Models
von: Kirchenbauer, John, et al.
Veröffentlicht: (2023)

On the Reliability of Watermarks for Large Language Models
von: Kirchenbauer, John, et al.
Veröffentlicht: (2023)

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
von: Jia, Xiaojun, et al.
Veröffentlicht: (2024)

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
von: Liu, Xiaoze, et al.
Veröffentlicht: (2025)

Malware Classification from Memory Dumps Using Machine Learning, Transformers, and Large Language Models
von: Dweib, Areej, et al.
Veröffentlicht: (2025)

Sanitize Your Responses: Mitigating Privacy Leakage in Large Language Models
von: Fu, Wenjie, et al.
Veröffentlicht: (2025)

RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models
von: Chugh, Rishit
Veröffentlicht: (2026)

Adversarial Suffix Filtering: a Defense Pipeline for LLMs
von: Khachaturov, David, et al.
Veröffentlicht: (2025)

Topic-Based Watermarks for Large Language Models
von: Nemecek, Alexander, et al.
Veröffentlicht: (2024)

Representation Bending for Large Language Model Safety
von: Yousefpour, Ashkan, et al.
Veröffentlicht: (2025)

User Inference Attacks on Large Language Models
von: Kandpal, Nikhil, et al.
Veröffentlicht: (2023)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
von: Yuan, Hongbang, et al.
Veröffentlicht: (2024)

Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
von: Fu, Wenjie, et al.
Veröffentlicht: (2023)

Debiasing Watermarks for Large Language Models via Maximal Coupling
von: Xie, Yangxinyu, et al.
Veröffentlicht: (2024)