Image de couverture de livre

Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Xinhai, Fu, Shaopeng, Yang, Shu, Wang, Liangyu, Zheng, Tianhang, Wang, Di
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence 68T07 I.2.7
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible
par: Zhao, Lepeng, et autres
Publié: (2026)

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy
par: Dang, Kieu, et autres
Publié: (2025)

GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis
par: Huang, Kaibo, et autres
Publié: (2025)

BreakFun: Jailbreaking LLMs via Schema Exploitation
par: Oskooei, Amirkia Rafiei, et autres
Publié: (2025)

MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
par: Pan, Leyi, et autres
Publié: (2025)

Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously
par: Adiletta, Andrew, et autres
Publié: (2025)

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs
par: Hill, Brennen, et autres
Publié: (2025)

RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection
par: Buonocore, Tommaso Mario, et autres
Publié: (2025)

How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks
par: Wang, Yanshu, et autres
Publié: (2026)

Generative AI Models: Opportunities and Risks for Industry and Authorities
par: Alt, Tobias, et autres
Publié: (2024)

MarkLLM: An Open-Source Toolkit for LLM Watermarking
par: Pan, Leyi, et autres
Publié: (2024)

A Semantic Invariant Robust Watermark for Large Language Models
par: Liu, Aiwei, et autres
Publié: (2023)

Can Watermarked LLMs be Identified by Users via Crafted Prompts?
par: Liu, Aiwei, et autres
Publié: (2024)

SCARA: A Semantics-Constrained Autonomous Remediation Agent for Opaque Industrial Software Vulnerabilities
par: Ning, Bowei, et autres
Publié: (2026)

Advancing Expert Specialization for Better MoE
par: Guo, Hongcan, et autres
Publié: (2025)

One Size Fits All? A Modular Adaptive Sanitization Kit (MASK) for Customizable Privacy-Preserving Phone Scam Detection
par: Wang, Kangzhong, et autres
Publié: (2025)

Cache-to-Cache: Direct Semantic Communication Between Large Language Models
par: Fu, Tianyu, et autres
Publié: (2025)

CLMN: Concept based Language Models via Neural Symbolic Reasoning
par: Yang, Yibo
Publié: (2025)

Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
par: Young, Richard J.
Publié: (2025)

DWFS-Obfuscation: Dynamic Weighted Feature Selection for Robust Malware Familial Classification under Obfuscation
par: Wei, Xingyuan, et autres
Publié: (2025)

POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
par: Shao, Yangguang, et autres
Publié: (2025)

Data-driven Circuit Discovery for Interpretability of Language Models
par: Rai, Daking, et autres
Publié: (2026)

Scalify: scale propagation for efficient low-precision LLM training
par: Balança, Paul, et autres
Publié: (2024)

Extending $μ$P: Spectral Conditions for Feature Learning Across Optimizers
par: Gupta, Akshita, et autres
Publié: (2026)

GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
par: Zhang, Peiyan, et autres
Publié: (2025)

MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
par: Wang, Yihao, et autres
Publié: (2026)

KGMark: A Diffusion Watermark for Knowledge Graphs
par: Peng, Hongrui, et autres
Publié: (2025)

CRUPL: A Semi-Supervised Cyber Attack Detection with Consistency Regularization and Uncertainty-aware Pseudo-Labeling in Smart Grid
par: Dash, Smruti P., et autres
Publié: (2025)

Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments
par: Nathanson, Samuel, et autres
Publié: (2025)

Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
par: Xie, Xiaopeng, et autres
Publié: (2024)

Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
par: Xin, Yuan, et autres
Publié: (2025)

UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
par: Geng, Runpeng, et autres
Publié: (2025)

On-Device Generative AI for GDPR-Compliant Visual Monitoring: Natural Language Alerts from Local Object Detection
par: Schappacher-Tilp, Gudrun, et autres
Publié: (2026)

AlignDP: Hybrid Differential Privacy with Rarity-Aware Protection for LLMs
par: Gaikwad, Madhava
Publié: (2025)

Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness
par: Sun, Weisong, et autres
Publié: (2025)

ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
par: Danieli, Federico, et autres
Publié: (2025)

When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models
par: Basu, Abhinaba
Publié: (2026)

MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence
par: Giannini, Federico, et autres
Publié: (2026)

NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution
par: Breneur, Oleksandr Marchenko, et autres
Publié: (2026)

Rethinking the Multilingual Reasoning Gap with Layer Swap
par: Lasbordes, Maxence, et autres
Publié: (2026)