Imagen de Portada

Life-Cycle Routing Vulnerabilities of LLM Router

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Qiqi, Ji, Xiaoyang, Zhai, Shengfang, Shen, Qingni, Zhang, Zhi, Fang, Yuejian, Gao, Yansong
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch
por: Zhao, Qichen, et al.
Publicado: (2026)

Discovering Universal Semantic Triggers for Text-to-Image Synthesis
por: Zhai, Shengfang, et al.
Publicado: (2024)

SecureRouter: Encrypted Routing for Efficient Secure Inference
por: Zhang, Yukuan, et al.
Publicado: (2026)

BadDLM: Backdooring Diffusion Language Models with Diverse Targets
por: Zhai, Shengfang, et al.
Publicado: (2026)

IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
por: Guo, Yanpei, et al.
Publicado: (2026)

LLM Agents can Autonomously Exploit One-day Vulnerabilities
por: Fang, Richard, et al.
Publicado: (2024)

Privacy-Preserving LLMs Routing
por: Wu, Xidong, et al.
Publicado: (2026)

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
por: Liu, Yue, et al.
Publicado: (2025)

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries
por: Wang, Yuhao, et al.
Publicado: (2025)

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
por: Zhai, Shengfang, et al.
Publicado: (2024)

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

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
por: Zhi, Yuhan, et al.
Publicado: (2025)

SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code
por: Li, Xinghang, et al.
Publicado: (2025)

DMark: Order-Agnostic Watermarking for Diffusion Large Language Models
por: Wu, Linyu, et al.
Publicado: (2025)

GuardReasoner: Towards Reasoning-based LLM Safeguards
por: Liu, Yue, et al.
Publicado: (2025)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
por: Qi, Senmao, et al.
Publicado: (2025)

Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts
por: Zhang, Xing, et al.
Publicado: (2026)

LProtector: An LLM-driven Vulnerability Detection System
por: Sheng, Ze, et al.
Publicado: (2024)

Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
por: Fu, Anmin, et al.
Publicado: (2025)

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
por: Zhang, Zhixiang, et al.
Publicado: (2026)

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
por: Nie, Yuzhou, et al.
Publicado: (2025)

Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
por: Meng, Yuqiao, et al.
Publicado: (2025)

LLM-based Vulnerable Code Augmentation: Generate or Refactor?
por: Ouchebara, Dyna Soumhane, et al.
Publicado: (2025)

MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
por: Wang, Yuhao, et al.
Publicado: (2026)

What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
por: Ma, Boyang, et al.
Publicado: (2026)

PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
por: Lin, Zhihao, et al.
Publicado: (2024)

AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents
por: Henke, Julius
Publicado: (2025)

LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement
por: Lin, Yu-Zheng, et al.
Publicado: (2025)

VerilogLAVD: LLM-Aided Rule Generation for Vulnerability Detection in Verilog
por: Long, Xiang, et al.
Publicado: (2025)

Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities
por: Ferrag, Mohamed Amine, et al.
Publicado: (2024)

Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software
por: Kordonsky, Tomer, et al.
Publicado: (2026)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
por: Li, Na, et al.
Publicado: (2025)

Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing
por: Langiu, Alessio
Publicado: (2026)

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents
por: Xiao, Wenjie, et al.
Publicado: (2026)

Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
por: Lilienthal, Derek, et al.
Publicado: (2025)

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
por: Sehwag, Udari Madhushani, et al.
Publicado: (2026)

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems
por: Balashov, Andrii, et al.
Publicado: (2025)

SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework
por: Zaazaa, Oualid, et al.
Publicado: (2024)

ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense
por: Lau, Nancy, et al.
Publicado: (2026)

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms
por: Gasmi, Tarek, et al.
Publicado: (2025)