Image de couverture de livre

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Zhixiang, Liu, Zesen, Xie, Yuchong, Huang, Quanfeng, She, Dongdong
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
par: Liu, Zesen, et autres
Publié: (2025)

When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
par: Luo, Mingyu, et autres
Publié: (2026)

Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
par: Xie, Yuchong, et autres
Publié: (2025)

QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents
par: Xie, Yuchong, et autres
Publié: (2025)

On Protecting Agentic Systems' Intellectual Property via Watermarking
par: Wang, Liwen, et autres
Publié: (2026)

ZTaint-Havoc: From Havoc Mode to Zero-Execution Fuzzing-Driven Taint Inference
par: Xie, Yuchong, et autres
Publié: (2025)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
par: Qi, Senmao, et autres
Publié: (2025)

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
par: Zhi, Yuhan, et autres
Publié: (2025)

Conflicts Make Large Reasoning Models Vulnerable to Attacks
par: Liu, Honghao, et autres
Publié: (2026)

Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
par: Song, Baogang, et autres
Publié: (2025)

The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities
par: Litvak, Ron
Publié: (2026)

Whose Narrative is it Anyway? A KV Cache Manipulation Attack
par: Ganesh, Mukkesh, et autres
Publié: (2025)

Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models
par: Hossain, Elias, et autres
Publié: (2025)

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
par: Li, Xueyi, et autres
Publié: (2026)

Life-Cycle Routing Vulnerabilities of LLM Router
par: Lin, Qiqi, et autres
Publié: (2025)

Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack
par: Yue, Murong, et autres
Publié: (2025)

Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applications
par: Mia, Maraz, et autres
Publié: (2025)

Explainer-guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models
par: Chen, Mingjie, et autres
Publié: (2025)

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
par: Zhang, Shuoming, et autres
Publié: (2025)

Optimization-based Prompt Injection Attack to LLM-as-a-Judge
par: Shi, Jiawen, et autres
Publié: (2024)

Rethinking the Vulnerability of Concept Erasure and a New Method
par: Richardson, Alex D., et autres
Publié: (2025)

Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts
par: Zhang, Xing, et autres
Publié: (2026)

Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
par: Cotroneo, Domenico, et autres
Publié: (2023)

Vulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS
par: Ennaji, Sabrine, et autres
Publié: (2025)

LProtector: An LLM-driven Vulnerability Detection System
par: Sheng, Ze, et autres
Publié: (2024)

Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
par: Chen, Tianxin, et autres
Publié: (2026)

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks
par: Liu, Zesen, et autres
Publié: (2024)

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
par: Fei, Zekun, et autres
Publié: (2024)

Privacy Attack in Federated Learning is Not Easy: An Experimental Study
par: Zhu, Hangyu, et autres
Publié: (2024)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
par: Ning, Liang-bo, et autres
Publié: (2025)

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills
par: Li, Ying, et autres
Publié: (2026)

Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
par: Shen, Huanming, et autres
Publié: (2025)

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
par: Ai, Zhenxin, et autres
Publié: (2026)

Esim: EVM Bytecode Similarity Detection Based on Stable-Semantic Graph
par: Chen, Zhuo, et autres
Publié: (2025)

Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks
par: Guo, Pengxin, et autres
Publié: (2025)

AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
par: Wu, Yixin, et autres
Publié: (2025)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
par: Wang, Zhilong, et autres
Publié: (2025)

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
par: Nie, Yuzhou, et autres
Publié: (2025)

Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
par: Meng, Yuqiao, et autres
Publié: (2025)

LLM-based Vulnerable Code Augmentation: Generate or Refactor?
par: Ouchebara, Dyna Soumhane, et autres
Publié: (2025)