Copertina

Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	You, Ziyang, He, Huilong, Yang, Xiaoke, Lu, Xuxing
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
di: You, Ziyang, et al.
Pubblicazione: (2026)

Seed Hijacking of LLM Sampling and Quantum Random Number Defense
di: You, Ziyang, et al.
Pubblicazione: (2026)

Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
di: Shen, Huanming, et al.
Pubblicazione: (2025)

An Undetectable Watermark for Generative Image Models
di: Gunn, Sam, et al.
Pubblicazione: (2024)

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior
di: Lian, Zhuotao, et al.
Pubblicazione: (2025)

Make Split, not Hijack: Preventing Feature-Space Hijacking Attacks in Split Learning
di: Khan, Tanveer, et al.
Pubblicazione: (2024)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
di: Wang, Hongtao, et al.
Pubblicazione: (2026)

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
di: Ai, Zhenxin, et al.
Pubblicazione: (2026)

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models
di: Zhang, Yucheng, et al.
Pubblicazione: (2024)

AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
di: Wu, Yixin, et al.
Pubblicazione: (2025)

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
di: Fei, Zekun, et al.
Pubblicazione: (2024)

Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders
di: Noever, David, et al.
Pubblicazione: (2024)

AgentMark: Utility-Preserving Behavioral Watermarking for Agents
di: Huang, Kaibo, et al.
Pubblicazione: (2026)

Character-Level Perturbations Disrupt LLM Watermarks
di: Zhang, Zhaoxi, et al.
Pubblicazione: (2025)

Watermark Overwriting Attack on StegaStamp algorithm
di: Serzhenko, I. F., et al.
Pubblicazione: (2025)

LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks
di: Zhang, Qingzhao, et al.
Pubblicazione: (2024)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
di: Wang, Zhilong, et al.
Pubblicazione: (2025)

Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration
di: Tsmindashvili, Tatia, et al.
Pubblicazione: (2025)

Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks
di: Dahiya, Pranav, et al.
Pubblicazione: (2023)

Optimizing Adaptive Attacks against Watermarks for Language Models
di: Diaa, Abdulrahman, et al.
Pubblicazione: (2024)

Sequential Behavioral Watermarking for LLM Agents
di: An, Hyeseon, et al.
Pubblicazione: (2026)

Attacks and Defenses Against LLM Fingerprinting
di: Kurian, Kevin, et al.
Pubblicazione: (2025)

Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion
di: Zhu, Hongyu, et al.
Pubblicazione: (2024)

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
di: Chen, Sizhe, et al.
Pubblicazione: (2025)

LLM Watermark Evasion via Bias Inversion
di: Hwang, Jeongyeon, et al.
Pubblicazione: (2025)

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
di: Zhang, Dongsen, et al.
Pubblicazione: (2025)

Membership Inference Attacks Against Vision-Language Models
di: Hu, Yuke, et al.
Pubblicazione: (2025)

Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
di: Xu, Yixiao, et al.
Pubblicazione: (2025)

DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
di: An, Hyeseon, et al.
Pubblicazione: (2025)

Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications
di: Suo, Xuchen
Pubblicazione: (2024)

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
di: Kang, Mintong, et al.
Pubblicazione: (2023)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
di: Zhu, Kaijie, et al.
Pubblicazione: (2025)

MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks
di: Zhou, Tong, et al.
Pubblicazione: (2025)

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
di: Belkhiter, Yannis, et al.
Pubblicazione: (2026)

Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection
di: Liu, Qingyu, et al.
Pubblicazione: (2026)

CLASP: Training-Free LLM-Assisted Source Code Watermarking via Semantic-Preserving Transformations
di: Xu, Rui, et al.
Pubblicazione: (2025)

Design and Implementation of a Secure RAG-Enhanced AI Chatbot for Smart Tourism Customer Service: Defending Against Prompt Injection Attacks -- A Case Study of Hsinchu, Taiwan
di: Shih, Yu-Kai, et al.
Pubblicazione: (2025)

Vocabulary Attack to Hijack Large Language Model Applications
di: Levi, Patrick, et al.
Pubblicazione: (2024)

Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks
di: Tong, Haibo, et al.
Pubblicazione: (2025)

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
di: Zhang, Jiawei, et al.
Pubblicazione: (2025)