Copertina

Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Guo, Zhenyuan, Shi, Yi, Meng, Wenlong, Gong, Chen, Wei, Chengkun, Chen, Wenzhi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion
di: Shi, Yi, et al.
Pubblicazione: (2025)

R.R.: Unveiling LLM Training Privacy through Recollection and Ranking
di: Meng, Wenlong, et al.
Pubblicazione: (2025)

Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation
di: Meng, Wenlong, et al.
Pubblicazione: (2025)

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
di: Guo, Zhenyuan, et al.
Pubblicazione: (2026)

Teach LLMs to Phish: Stealing Private Information from Language Models
di: Panda, Ashwinee, et al.
Pubblicazione: (2024)

GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors
di: Meng, Wenlong, et al.
Pubblicazione: (2025)

Watermarking LLM Agent Trajectories
di: Meng, Wenlong, et al.
Pubblicazione: (2026)

Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Tasks
di: Shen, Chen, et al.
Pubblicazione: (2026)

PRSA: Prompt Stealing Attacks against Real-World Prompt Services
di: Yang, Yong, et al.
Pubblicazione: (2024)

RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior
di: Yang, Junyao, et al.
Pubblicazione: (2025)

SCAN: Structured Capability Assessment and Navigation for LLMs
di: Wang, Zongqi, et al.
Pubblicazione: (2025)

ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs
di: Yang, Yan, et al.
Pubblicazione: (2025)

AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging
di: Chen, Kesheng, et al.
Pubblicazione: (2025)

The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities
di: Research, MediaTek, et al.
Pubblicazione: (2025)

Cautious Next Token Prediction
di: Wang, Yizhou, et al.
Pubblicazione: (2025)

When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
di: Li, Yayuan, et al.
Pubblicazione: (2026)

Unfamiliar Finetuning Examples Control How Language Models Hallucinate
di: Kang, Katie, et al.
Pubblicazione: (2024)

Cautious Optimizers: Improving Training with One Line of Code
di: Liang, Kaizhao, et al.
Pubblicazione: (2024)

ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
di: Yang, Junyao, et al.
Pubblicazione: (2026)

From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models
di: Zhang, Ruiqi, et al.
Pubblicazione: (2026)

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
di: Farn, Hua, et al.
Pubblicazione: (2024)

ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails
di: Wen, Xiaofei, et al.
Pubblicazione: (2025)

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
di: Cao, Bochuan, et al.
Pubblicazione: (2025)

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
di: Yoon, Do-hyeon, et al.
Pubblicazione: (2025)

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
di: Wu, Yurong, et al.
Pubblicazione: (2025)

A Novel Paradigm Boosting Translation Capabilities of Large Language Models
di: Guo, Jiaxin, et al.
Pubblicazione: (2024)

Using Source-Side Confidence Estimation for Reliable Translation into Unfamiliar Languages
di: Sible, Kenneth J., et al.
Pubblicazione: (2025)

Personalized Language Models via Privacy-Preserving Evolutionary Model Merging
di: Kim, Kyuyoung, et al.
Pubblicazione: (2025)

Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
di: Lu, Zhenyi, et al.
Pubblicazione: (2024)

EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs
di: Xu, Wanghan, et al.
Pubblicazione: (2025)

Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization
di: Zhang, Zhaohan, et al.
Pubblicazione: (2024)

Debate-Driven Multi-Agent LLMs for Phishing Email Detection
di: Nguyen, Ngoc Tuong Vy, et al.
Pubblicazione: (2025)

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
di: Wang, Zheng, et al.
Pubblicazione: (2024)

Stolen Subwords: Importance of Vocabularies for Machine Translation Model Stealing
di: Zouhar, Vilém
Pubblicazione: (2024)

PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare
di: Moreno, Jose G., et al.
Pubblicazione: (2025)

Supervised Optimism Correction: Be Confident When LLMs Are Sure
di: Zhang, Junjie, et al.
Pubblicazione: (2025)

ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction
di: Guo, Zichun, et al.
Pubblicazione: (2026)

FEEL: A Framework for Evaluating Emotional Support Capability with Large Language Models
di: Zhang, Huaiwen, et al.
Pubblicazione: (2024)

Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability
di: Zhang, Leizhen, et al.
Pubblicazione: (2026)

How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models
di: Jiang, Jiyue, et al.
Pubblicazione: (2024)