Imagen de Portada

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Nafi, Abdullah Al Nomaan, Suya, Fnu, Bhunia, Swarup, Chakraborty, Prabuddha
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
por: Nafi, Abdullah Al Nomaan, et al.
Publicado: (2025)

Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
por: Hoque, Shahinul, et al.
Publicado: (2026)

AJF: Adaptive Jailbreak Framework Based on the Comprehension Ability of Black-Box Large Language Models
por: Yu, Mingyu, et al.
Publicado: (2025)

X-DFS: Explainable Artificial Intelligence Guided Design-for-Security Solution Space Exploration
por: Mahfuz, Tanzim, et al.
Publicado: (2024)

Open Sesame! Universal Black Box Jailbreaking of Large Language Models
por: Lapid, Raz, et al.
Publicado: (2023)

HAMLOCK: HArdware-Model LOgically Combined attacK
por: Amgain, Sanskar, et al.
Publicado: (2025)

MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning
por: Zheng, Muyang, et al.
Publicado: (2025)

BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models
por: Wang, Xinyuan, et al.
Publicado: (2024)

Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models
por: Sun, Xiaobing, et al.
Publicado: (2026)

Knowledge Distillation of Black-Box Large Language Models
por: Chen, Hongzhan, et al.
Publicado: (2024)

SoK: Pitfalls in Evaluating Black-Box Attacks
por: Suya, Fnu, et al.
Publicado: (2023)

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

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
por: Ji, Jiabao, et al.
Publicado: (2024)

FregeLogic at SemEval 2026 Task 11: A Hybrid Neuro-Symbolic Architecture for Content-Robust Syllogistic Validity Prediction
por: Akinfaderin, Adewale, et al.
Publicado: (2026)

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

KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models
por: Mohbat, Fnu, et al.
Publicado: (2025)

Black-Box On-Policy Distillation of Large Language Models
por: Ye, Tianzhu, et al.
Publicado: (2025)

RPM: Reasoning-Level Personalization for Black-Box Large Language Models
por: Kim, Jieyong, et al.
Publicado: (2025)

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models
por: Nandi, Palash, et al.
Publicado: (2025)

Persona Jailbreaking in Large Language Models
por: Sandhan, Jivnesh, et al.
Publicado: (2026)

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
por: Akbar-Tajari, Mohammad, et al.
Publicado: (2025)

Beyond the Black Box: A Survey on the Theory and Mechanism of Large Language Models
por: Gan, Zeyu, et al.
Publicado: (2026)

Black Big Boxes: Tracing Adjective Order Preferences in Large Language Models
por: Jumelet, Jaap, et al.
Publicado: (2024)

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
por: Mehrotra, Anay, et al.
Publicado: (2023)

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
por: Cheng, Jiale, et al.
Publicado: (2023)

All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
por: Takemoto, Kazuhiro
Publicado: (2024)

Jailbreaking Large Language Models with Morality Attacks
por: Su, Ying, et al.
Publicado: (2026)

Weak-to-Strong Jailbreaking on Large Language Models
por: Zhao, Xuandong, et al.
Publicado: (2024)

Diversity Helps Jailbreak Large Language Models
por: Zhao, Weiliang, et al.
Publicado: (2024)

Multilingual Jailbreak Challenges in Large Language Models
por: Deng, Yue, et al.
Publicado: (2023)

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

SODA: Semi On-Policy Black-Box Distillation for Large Language Models
por: Chen, Xiwen, et al.
Publicado: (2026)

Hierarchical Text Classification Using Black Box Large Language Models
por: Yoshimura, Kosuke, et al.
Publicado: (2025)

Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
por: Mo, Wenjie, et al.
Publicado: (2023)

Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks
por: Gohil, Vasudev
Publicado: (2025)

SALTY: Explainable Artificial Intelligence Guided Structural Analysis for Hardware Trojan Detection
por: Mahfuz, Tanzim, et al.
Publicado: (2025)

POLARIS: Explainable Artificial Intelligence for Mitigating Power Side-Channel Leakage
por: Mahfuz, Tanzim, et al.
Publicado: (2025)

EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
por: Zhou, Weikang, et al.
Publicado: (2024)

Characterizing the Robustness of Black-Box LLM Planners Under Perturbed Observations with Adaptive Stress Testing
por: Chakraborty, Neeloy, et al.
Publicado: (2025)

When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models
por: Shamsi, Zafir, et al.
Publicado: (2026)