Cover Image

Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Kai, Yu, Weichen, Li, Yining, Chen, Kai, Yao, Tianjun, Li, Xiang, Liu, Wenhe, Yu, Lijun, Shen, Zhiqiang, Fredrikson, Matt
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models
by: Hu, Kai, et al.
Published: (2026)

HieraMAS: Optimizing Intra-Node LLM Mixtures and Inter-Node Topology for Multi-Agent Systems
by: Yao, Tianjun, et al.
Published: (2026)

Transferable Adversarial Attacks on Black-Box Vision-Language Models
by: Hu, Kai, et al.
Published: (2025)

SecCodePRM: A Process Reward Model for Code Security
by: Yu, Weichen, et al.
Published: (2026)

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
by: Liu, Xiaoze, et al.
Published: (2025)

A Mixture of Linear Corrections Generates Secure Code
by: Yu, Weichen, et al.
Published: (2025)

Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
by: Hu, Kai, et al.
Published: (2025)

A Recipe for Improved Certifiable Robustness
by: Hu, Kai, et al.
Published: (2023)

Empowering Graph Invariance Learning with Deep Spurious Infomax
by: Yao, Tianjun, et al.
Published: (2024)

PrivCode: When Code Generation Meets Differential Privacy
by: Liu, Zheng, et al.
Published: (2025)

Adaptive Prompt Embedding Optimization for LLM Jailbreaking
by: Li, Miles Q., et al.
Published: (2026)

Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering
by: Yao, Tianjun, et al.
Published: (2025)

Is Your Text-to-Image Model Robust to Caption Noise?
by: Yu, Weichen, et al.
Published: (2024)

Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
by: Ji, Haoxuan, et al.
Published: (2024)

AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
by: Chen, Jiawei, et al.
Published: (2024)

DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning
by: Chen, Yicheng, et al.
Published: (2026)

Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning
by: Li, Chen, et al.
Published: (2025)

LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses
by: Lin, Weiran, et al.
Published: (2024)

Playing Language Game with LLMs Leads to Jailbreaking
by: Peng, Yu, et al.
Published: (2024)

ParamMem: Augmenting Language Agents with Parametric Reflective Memory
by: Yao, Tianjun, et al.
Published: (2026)

Multivariate Decoded Quantum Interferometry for Weighted Optimization
by: Bu, Kaifeng, et al.
Published: (2026)

Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression
by: Peng, Jingyu, et al.
Published: (2025)

MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space
by: Chen, Yicheng, et al.
Published: (2025)

Constrained mean-field control with singular controls: Existence, stochastic maximum principle and constrained FBSDE
by: Bo, Lijun, et al.
Published: (2025)

The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
by: Liu, Xiaoze, et al.
Published: (2026)

Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
by: Li, Xiangfang, et al.
Published: (2025)

An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
by: Jiang, Weipeng, et al.
Published: (2024)

One Last Attention for Your Vision-Language Model
by: Chen, Liang, et al.
Published: (2025)

Entropic van der Corput's Difference Theorem
by: Gu, Weichen, et al.
Published: (2024)

SAGE: Sequence-level Adaptive Gradient Evolution for Generative Recommendation
by: Xie, Yu, et al.
Published: (2026)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference
by: Lu, Yu-Chen, et al.
Published: (2025)

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

Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization
by: Yao, Tianjun, et al.
Published: (2025)

Adaptive Probe-based Steering for Robust LLM Jailbreaking
by: Chen, Junxi, et al.
Published: (2026)

EdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models
by: Huang, Mingqiang, et al.
Published: (2024)

Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks
by: Zhang, Yingjie, et al.
Published: (2025)

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
by: Li, Zheng, et al.
Published: (2025)

Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching
by: Pang, Bowen, et al.
Published: (2025)

Efficient Dynamic Ensembling for Multiple LLM Experts
by: Hu, Jinwu, et al.
Published: (2024)