Buchumschlag

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Yu, Hou, Yuenan, Wei, Yingmei, Guo, Yanming, Lu, Chaochao
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Cryptography and Security Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
von: Chen, Bocheng, et al.
Veröffentlicht: (2024)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
von: Yi, Biao, et al.
Veröffentlicht: (2025)

Privacy in Large Language Models: Attacks, Defenses and Future Directions
von: Li, Haoran, et al.
Veröffentlicht: (2023)

Data Defenses Against Large Language Models
von: Agnew, William, et al.
Veröffentlicht: (2024)

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack
von: Li, Hao, et al.
Veröffentlicht: (2025)

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
von: Yang, Guangyu, et al.
Veröffentlicht: (2025)

Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
von: Chowdhury, Arijit Ghosh, et al.
Veröffentlicht: (2024)

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
von: Zhang, Xiaozhe, et al.
Veröffentlicht: (2026)

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
von: Zhao, Shuai, et al.
Veröffentlicht: (2024)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
von: Zhao, Haodong, et al.
Veröffentlicht: (2024)

One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models
von: Gu, Haoran, et al.
Veröffentlicht: (2025)

SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
von: Afane, Mohamed, et al.
Veröffentlicht: (2025)

DINA: A Dual Defense Framework Against Internal Noise and External Attacks in Natural Language Processing
von: Chuang, Ko-Wei, et al.
Veröffentlicht: (2025)

Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models
von: Chen, Zhuo, et al.
Veröffentlicht: (2024)

Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
von: Fu, Yu, et al.
Veröffentlicht: (2024)

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
von: Yu, Yongcan, et al.
Veröffentlicht: (2025)

$PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models
von: Zhang, Yuanhe, et al.
Veröffentlicht: (2025)

BadActs: A Universal Backdoor Defense in the Activation Space
von: Yi, Biao, et al.
Veröffentlicht: (2024)

Jailbreak Attacks and Defenses Against Large Language Models: A Survey
von: Yi, Sibo, et al.
Veröffentlicht: (2024)

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models
von: Meng, Xiangtao, et al.
Veröffentlicht: (2026)

AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models
von: Wang, Yiming, et al.
Veröffentlicht: (2024)

EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense
von: Huang, Wei, et al.
Veröffentlicht: (2025)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
von: Zeng, Yifan, et al.
Veröffentlicht: (2024)

Auto-Tuning Safety Guardrails for Black-Box Large Language Models
von: Abdulkadir, Perry
Veröffentlicht: (2025)

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models
von: Ruzzetti, Elena Sofia, et al.
Veröffentlicht: (2025)

Adversarial Text Purification: A Large Language Model Approach for Defense
von: Moraffah, Raha, et al.
Veröffentlicht: (2024)

A Watermark for Black-Box Language Models
von: Bahri, Dara, et al.
Veröffentlicht: (2024)

Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
von: Ye, Rui, et al.
Veröffentlicht: (2024)

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
von: Zhong, Xingwei, et al.
Veröffentlicht: (2025)

From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection
von: Li, Hao, et al.
Veröffentlicht: (2025)

Enhancing Security and Strengthening Defenses in Automated Short-Answer Grading Systems
von: Yarmohammadtoosky, Sahar, et al.
Veröffentlicht: (2025)

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
von: Zhang, Chiyu, et al.
Veröffentlicht: (2025)

FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
von: Wang, Jiongxiao, et al.
Veröffentlicht: (2024)

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
von: Li, Yucheng, et al.
Veröffentlicht: (2025)

Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense Perspective
von: Tshimula, Jean Marie, et al.
Veröffentlicht: (2024)

AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
von: Kim, Jaehee, et al.
Veröffentlicht: (2026)

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
von: Wang, Zhuoshang, et al.
Veröffentlicht: (2026)

Jatmo: Prompt Injection Defense by Task-Specific Finetuning
von: Piet, Julien, et al.
Veröffentlicht: (2023)

BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS
von: Li, Ye, et al.
Veröffentlicht: (2025)

Contextualized Privacy Defense for LLM Agents
von: Wen, Yule, et al.
Veröffentlicht: (2026)