Image de couverture de livre

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Luoyu, Wang, Weiqi, Tian, Zhiyi, Wu, Feng, Asiri, Ahmed, Yu, Shui
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
par: Chen, Luoyu, et autres
Publié: (2026)

TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning
par: Wang, Weiqi, et autres
Publié: (2025)

Machine Unlearning: A Comprehensive Survey
par: Wang, Weiqi, et autres
Publié: (2024)

SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications
par: Wang, Weiqi, et autres
Publié: (2025)

CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
par: Wang, Weiqi, et autres
Publié: (2025)

BlindU: Blind Machine Unlearning without Revealing Erasing Data
par: Wang, Weiqi, et autres
Publié: (2026)

from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
par: Yan, Yu, et autres
Publié: (2025)

Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
par: Wu, Yu-Hang, et autres
Publié: (2025)

Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
par: Xiong, Chen, et autres
Publié: (2024)

AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens
par: Lu, Lin, et autres
Publié: (2024)

Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
par: Xie, Zhixin, et autres
Publié: (2025)

TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning
par: Xie, Zhixin, et autres
Publié: (2026)

FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
par: Yan, Xinhai, et autres
Publié: (2025)

Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
par: Xiong, Chen, et autres
Publié: (2026)

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
par: Yang, Guangyu, et autres
Publié: (2025)

Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense
par: Chen, Zejian, et autres
Publié: (2026)

Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense
par: Hao, Shuyang, et autres
Publié: (2025)

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
par: Wang, Xi, et autres
Publié: (2026)

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
par: Zhong, Xingwei, et autres
Publié: (2025)

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
par: Lin, Zheng, et autres
Publié: (2026)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
par: Zeng, Yifan, et autres
Publié: (2024)

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
par: Yoon, Sangyeon, et autres
Publié: (2026)

$\textit{MMJ-Bench}$: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models
par: Weng, Fenghua, et autres
Publié: (2024)

Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses
par: Derya, Kemal, et autres
Publié: (2026)

TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
par: Du, Mengyao, et autres
Publié: (2026)

Defending Buffer Overflows in WebAssembly: A Transpiler Approach
par: Feng, Weiqi
Publié: (2026)

SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision-Language Models
par: Zeng, Xiyu, et autres
Publié: (2025)

DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
par: Wang, Yi, et autres
Publié: (2025)

Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles
par: Wang, Zhilong, et autres
Publié: (2024)

BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger
par: Chen, Yulin, et autres
Publié: (2024)

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
par: Wang, Yanyun, et autres
Publié: (2026)

Jailbreaking Generative AI: Multivector Phishing Threats and Transformer based Defenses
par: Mishra, Rina, et autres
Publié: (2025)

Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection
par: Wang, Zhilong, et autres
Publié: (2024)

Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
par: Yang, Xianglin, et autres
Publié: (2025)

Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs
par: Xiang, Shiyu, et autres
Publié: (2025)

T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models
par: Liang, Siyuan, et autres
Publié: (2025)

LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution
par: Yang, Zhuoran, et autres
Publié: (2025)

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations
par: Li, Xiaohu, et autres
Publié: (2025)

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

You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense
par: Mai, Wuyuao, et autres
Publié: (2025)