Image de couverture de livre

Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Alshaalan, Mohammed, Rodrigues, Miguel R. D.
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Generative Adversarial Model-Based Optimization via Source Critic Regularization
par: Yao, Michael S., et autres
Publié: (2024)

LIME-LLM: Probing Models with Fluent Counterfactuals, Not Broken Text
par: Mihaila, George, et autres
Publié: (2026)

Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective
par: Hao, Zhezheng, et autres
Publié: (2025)

PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection
par: Camarato, Steffen J., et autres
Publié: (2026)

Enhancing Adversarial Training via Reweighting Optimization Trajectory
par: Huang, Tianjin, et autres
Publié: (2023)

Generative Sequential Notification Optimization via Multi-Objective Decision Transformers
par: Ocejo, Borja, et autres
Publié: (2025)

SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking
par: Yang, Wenyuan, et autres
Publié: (2025)

Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization
par: Liu, Zongkai, et autres
Publié: (2024)

Query-Based Adversarial Prompt Generation
par: Hayase, Jonathan, et autres
Publié: (2024)

The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
par: Sharma, Aman, et autres
Publié: (2025)

EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropy
par: Huang, Yihong, et autres
Publié: (2024)

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
par: Xu, Huimin, et autres
Publié: (2026)

Sequential Difference Maximization: Generating Adversarial Examples via Multi-Stage Optimization
par: Liu, Xinlei, et autres
Publié: (2025)

SCOPE: Sequential Causal Optimization of Process Interventions
par: De Moor, Jakob, et autres
Publié: (2025)

Sequential Policy Gradient for Adaptive Hyperparameter Optimization
par: Li, Zheng, et autres
Publié: (2025)

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
par: Li, Donghao, et autres
Publié: (2026)

FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits
par: Lu, Pingchen, et autres
Publié: (2025)

Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation
par: Kim, Donghwan, et autres
Publié: (2026)

Adversarial Imitation Learning via Boosting
par: Chang, Jonathan D., et autres
Publié: (2024)

Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
par: Zhang, Xiaoying, et autres
Publié: (2024)

Prompt Optimization with Human Feedback
par: Lin, Xiaoqiang, et autres
Publié: (2024)

Automatic Prompt Optimization with Prompt Distillation
par: Dyagin, Ernest A., et autres
Publié: (2025)

MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
par: Bal-Ghaoui, Mohamed, et autres
Publié: (2025)

Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
par: Abdulsamad, Hany, et autres
Publié: (2025)

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
par: Le, Thanh-Long V., et autres
Publié: (2025)

Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts
par: Wu, Yuanwei, et autres
Publié: (2023)

When Maximum Entropy Misleads Policy Optimization
par: Zhang, Ruipeng, et autres
Publié: (2025)

ESPO: Entropy Importance Sampling Policy Optimization
par: Sheng, Yuepeng, et autres
Publié: (2025)

Sequential Large Language Model-Based Hyper-parameter Optimization
par: Mahammadli, Kanan, et autres
Publié: (2024)

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
par: Choi, Yunseon, et autres
Publié: (2024)

MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks
par: Hong, Zhi, et autres
Publié: (2026)

Generative Adversarial Networks for Imputing Sparse Learning Performance
par: Zhang, Liang, et autres
Publié: (2024)

Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation
par: Choe, Jean Seong Bjorn, et autres
Publié: (2024)

When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
par: Hatgis-Kessell, Stephane, et autres
Publié: (2026)

Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning
par: Feng, Xinsong, et autres
Publié: (2025)

From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection
par: Wang, Luzhi, et autres
Publié: (2026)

Towards Interpretable Adversarial Examples via Sparse Adversarial Attack
par: Lin, Fudong, et autres
Publié: (2025)

Latent Adversarial Regularization for Offline Preference Optimization
par: Jiang, Enyi, et autres
Publié: (2026)

Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation
par: Yin, Xuwang, et autres
Publié: (2025)

SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
par: Saiem, Bijoy Ahmed, et autres
Publié: (2024)