Copertina

EVA: Editing for Versatile Alignment against Jailbreaks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Yi, Qiu, Hongye, Xu, Yue, Yang, Sibei, Qin, Zhan, Huang, Minlie, Wang, Wenjie
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

DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
di: Wang, Yi, et al.
Pubblicazione: (2025)

Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models
di: Yang, Yiqi, et al.
Pubblicazione: (2024)

Untargeted Jailbreak Attack
di: Huang, Xinzhe, et al.
Pubblicazione: (2025)

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
di: Yang, Junxiao, et al.
Pubblicazione: (2025)

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures
di: Zhou, Yukai, et al.
Pubblicazione: (2025)

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
di: Nian, Yi, et al.
Pubblicazione: (2025)

RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
di: Chen, Jianhao, et al.
Pubblicazione: (2025)

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
di: Wang, Xunguang, et al.
Pubblicazione: (2024)

SoK: Robustness in Large Language Models against Jailbreak Attacks
di: Xu, Feiyue, et al.
Pubblicazione: (2026)

Activation-Guided Local Editing for Jailbreaking Attacks
di: Wang, Jiecong, et al.
Pubblicazione: (2025)

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
di: Cunningham, Hoagy, et al.
Pubblicazione: (2026)

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks
di: Wu, ChenYu, et al.
Pubblicazione: (2025)

DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization
di: Huang, Xinzhe, et al.
Pubblicazione: (2025)

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
di: Wang, Youze, et al.
Pubblicazione: (2025)

ShallowJail: Steering Jailbreaks against Large Language Models
di: Liu, Shang, et al.
Pubblicazione: (2026)

Imperceptible Jailbreaking against Large Language Models
di: Gao, Kuofeng, et al.
Pubblicazione: (2025)

User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data
di: Yang, Haowei, et al.
Pubblicazione: (2025)

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs
di: Li, Hongyi, et al.
Pubblicazione: (2024)

KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs
di: Liu, Shuyuan, et al.
Pubblicazione: (2025)

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
di: Ma, Jiachen, et al.
Pubblicazione: (2024)

Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
di: Huang, Xun, et al.
Pubblicazione: (2026)

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
di: Yuan, Leitao, et al.
Pubblicazione: (2026)

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
di: Hu, Yuke, et al.
Pubblicazione: (2023)

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
di: Park, Junyoung, et al.
Pubblicazione: (2026)

AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
di: Song, Weiming, et al.
Pubblicazione: (2026)

ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs
di: Yang, Yuchen, et al.
Pubblicazione: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
di: Jiang, Tanqiu, et al.
Pubblicazione: (2024)

A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
di: Xu, Zihao, et al.
Pubblicazione: (2024)

SoK: Evaluating Jailbreak Guardrails for Large Language Models
di: Wang, Xunguang, et al.
Pubblicazione: (2025)

Defending against Jailbreak through Early Exit Generation of Large Language Models
di: Zhao, Chongwen, et al.
Pubblicazione: (2024)

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
di: Yin, Qingyu, et al.
Pubblicazione: (2025)

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
di: Wang, Ziwei, et al.
Pubblicazione: (2026)

FPEdit: Robust LLM Fingerprinting through Localized Parameter Editing
di: Wang, Shida, et al.
Pubblicazione: (2025)

FlipAttack: Jailbreak LLMs via Flipping
di: Liu, Yue, et al.
Pubblicazione: (2024)

Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling
di: Zhang, Deyue, et al.
Pubblicazione: (2025)

LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper
di: Wu, Daoyuan, et al.
Pubblicazione: (2024)

Enhancing Jailbreak Attacks on LLMs via Persona Prompts
di: Zhang, Zheng, et al.
Pubblicazione: (2025)

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
di: Li, Jie, et al.
Pubblicazione: (2024)

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
di: Cheng, Ruoxi, et al.
Pubblicazione: (2024)

Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation
di: Zhang, Wenhui, et al.
Pubblicazione: (2025)