Copertina

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Yue, Li, Xiao, Wu, Hao, Zhang, Yue, Xu, Fengyuan, Cheng, Xiuzhen, Zhong, Sheng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

If LLMs Would Just Look: Simple Line-by-line Checking Improves Vulnerability Localization
di: Li, Yue, et al.
Pubblicazione: (2024)

Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask
di: Li, Yue, et al.
Pubblicazione: (2025)

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
di: Li, Yue, et al.
Pubblicazione: (2026)

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
di: Zhang, Shuoming, et al.
Pubblicazione: (2025)

A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection
di: Li, Xiao, et al.
Pubblicazione: (2025)

"MCP Does Not Stand for Misuse Cryptography Protocol": Uncovering Cryptographic Misuse in Model Context Protocol at Scale
di: Yan, Biwei, et al.
Pubblicazione: (2025)

On Protecting the Data Privacy of Large Language Models (LLMs): A Survey
di: Yan, Biwei, et al.
Pubblicazione: (2024)

OverThink: Slowdown Attacks on Reasoning LLMs
di: Kumar, Abhinav, et al.
Pubblicazione: (2025)

SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection
di: Shan, Zhengyang, et al.
Pubblicazione: (2026)

What You Code Is What We Prove: Translating BLE App Logic into Formal Models with LLMs for Vulnerability Detection
di: Yan, Biwei, et al.
Pubblicazione: (2025)

Dataset Ownership in the Era of Large Language Models
di: Li, Kun, et al.
Pubblicazione: (2025)

Excessive Reasoning Attack on Reasoning LLMs
di: Si, Wai Man, et al.
Pubblicazione: (2025)

Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems
di: Dong, Yueyan, et al.
Pubblicazione: (2026)

Contiguous Zero-Copy for Encrypted Transport Protocols
di: Rochet, Florentin
Pubblicazione: (2024)

Revealing Adversarial Smart Contracts through Semantic Interpretation and Uncertainty Estimation
di: Liu, Yating, et al.
Pubblicazione: (2025)

ConneX: Automatically Resolving Transaction Opacity of Cross-Chain Bridges for Security Analysis
di: Liang, Hanzhong, et al.
Pubblicazione: (2025)

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
di: Zeng, Yizhe, et al.
Pubblicazione: (2026)

CopyQNN: Quantum Neural Network Extraction Attack under Varying Quantum Noise
di: Fu, Zhenxiao, et al.
Pubblicazione: (2025)

Multi-Copy Security in Unclonable Cryptography
di: Çakan, Alper, et al.
Pubblicazione: (2025)

GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs
di: Wu, Lichao, et al.
Pubblicazione: (2025)

LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks
di: Wang, Ruoxi, et al.
Pubblicazione: (2025)

TPPR: APT Tactic / Technique Pattern Guided Attack Path Reasoning for Attack Investigation
di: Sheng, Qi
Pubblicazione: (2025)

Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
di: Zhong, Yinan, et al.
Pubblicazione: (2025)

Less is More: On Copy Complexity in Quantum Cryptography
di: Ananth, Prabhanjan, et al.
Pubblicazione: (2025)

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions
di: Qi, Minfeng, et al.
Pubblicazione: (2026)

RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
di: Liu, Mingrui, et al.
Pubblicazione: (2026)

AgentDID: Trustless Identity Authentication for AI Agents
di: Xu, Minghui, et al.
Pubblicazione: (2026)

RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models
di: Meng, Fanchao, et al.
Pubblicazione: (2025)

A Practical Trigger-Free Backdoor Attack on Neural Networks
di: Wang, Jiahao, et al.
Pubblicazione: (2024)

FlipAttack: Jailbreak LLMs via Flipping
di: Liu, Yue, et al.
Pubblicazione: (2024)

I'm Spartacus, No, I'm Spartacus: Measuring and Understanding LLM Identity Confusion
di: Li, Kun, et al.
Pubblicazione: (2024)

Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models
di: Ward, Joshua, et al.
Pubblicazione: (2024)

How to Copy-Protect Malleable-Puncturable Cryptographic Functionalities Under Arbitrary Challenge Distributions
di: Çakan, Alper, et al.
Pubblicazione: (2025)

Redefining Website Fingerprinting Attacks With Multiagent LLMs
di: Song, Chuxu, et al.
Pubblicazione: (2025)

Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach
di: Li, Yuanheng, et al.
Pubblicazione: (2025)

When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack
di: Sun, Zehan, et al.
Pubblicazione: (2026)

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
di: Wang, Kai, et al.
Pubblicazione: (2025)

Revocable Encryption, Programs, and More: The Case of Multi-Copy Security
di: Ananth, Prabhanjan, et al.
Pubblicazione: (2024)

Analyzing the Impact of Copying-and-Pasting Vulnerable Solidity Code Snippets from Question-and-Answer Websites
di: Weiss, Konrad, et al.
Pubblicazione: (2024)

Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement
di: Li, Chenghao, et al.
Pubblicazione: (2023)