Image de couverture de livre

AJF: Adaptive Jailbreak Framework Based on the Comprehension Ability of Black-Box Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Mingyu, Wang, Wei, Wei, Yanjie, Qin, Sujuan, Gao, Fei, Li, Wenmin
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models
par: Nafi, Abdullah Al Nomaan, et autres
Publié: (2026)

Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs
par: Yu, Mingyu, et autres
Publié: (2026)

Open Sesame! Universal Black Box Jailbreaking of Large Language Models
par: Lapid, Raz, et autres
Publié: (2023)

Black-Box On-Policy Distillation of Large Language Models
par: Ye, Tianzhu, et autres
Publié: (2025)

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
par: Li, Yu, et autres
Publié: (2026)

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
par: Liu, Yilun, et autres
Publié: (2026)

EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
par: Zhou, Weikang, et autres
Publié: (2024)

BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models
par: Wang, Xinyuan, et autres
Publié: (2024)

Persona Jailbreaking in Large Language Models
par: Sandhan, Jivnesh, et autres
Publié: (2026)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
par: Wang, Libo
Publié: (2024)

TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
par: Chu, Zheng, et autres
Publié: (2023)

Disentangling Memory and Reasoning Ability in Large Language Models
par: Jin, Mingyu, et autres
Publié: (2024)

BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
par: Sun, Haotian, et autres
Publié: (2024)

Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models
par: Li, Jiahui, et autres
Publié: (2024)

JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models
par: Feng, Yingchaojie, et autres
Publié: (2024)

AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models
par: Shu, Dong, et autres
Publié: (2024)

Diversity Helps Jailbreak Large Language Models
par: Zhao, Weiliang, et autres
Publié: (2024)

Knowledge Distillation of Black-Box Large Language Models
par: Chen, Hongzhan, et autres
Publié: (2024)

Weak-to-Strong Jailbreaking on Large Language Models
par: Zhao, Xuandong, et autres
Publié: (2024)

FedDTPT: Federated Discrete and Transferable Prompt Tuning for Black-Box Large Language Models
par: Wu, Jiaqi, et autres
Publié: (2024)

ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models
par: Cheng, Siyang, et autres
Publié: (2025)

Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
par: Mo, Wenjie, et autres
Publié: (2023)

Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
par: Xu, Nan, et autres
Publié: (2023)

Beyond the Black Box: A Survey on the Theory and Mechanism of Large Language Models
par: Gan, Zeyu, et autres
Publié: (2026)

Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models
par: Xu, Yue, et autres
Publié: (2024)

TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
par: Xu, Zhi, et autres
Publié: (2026)

InFoBench: Evaluating Instruction Following Ability in Large Language Models
par: Qin, Yiwei, et autres
Publié: (2024)

AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models
par: Zhu, Qin, et autres
Publié: (2025)

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
par: Zhang, Chiyu, et autres
Publié: (2025)

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
par: Zhao, Wei, et autres
Publié: (2024)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
par: Zhang, Zhexin, et autres
Publié: (2023)

Imperceptible Jailbreaking against Large Language Models
par: Gao, Kuofeng, et autres
Publié: (2025)

Jailbreaking Large Language Models with Morality Attacks
par: Su, Ying, et autres
Publié: (2026)

Entropy-Based Adaptive Weighting for Self-Training
par: Wang, Xiaoxuan, et autres
Publié: (2025)

Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models
par: Hao, Teqi, et autres
Publié: (2025)

Distilling Reasoning Ability from Large Language Models with Adaptive Thinking
par: Chen, Xiaoshu, et autres
Publié: (2024)

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
par: Cheng, Jiale, et autres
Publié: (2023)

RPM: Reasoning-Level Personalization for Black-Box Large Language Models
par: Kim, Jieyong, et autres
Publié: (2025)

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
par: Gu, Jia-Chen, et autres
Publié: (2024)

SODA: Semi On-Policy Black-Box Distillation for Large Language Models
par: Chen, Xiwen, et autres
Publié: (2026)