:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Nguyen, Tuan, Tran-Thanh, Long
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2510.09330
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Black-Box Behavioral Distillation Breaks Safety Alignment in Medical LLMs
by: Jahan, Sohely, et al.
Published: (2025)

Curvature-Aware Safety Restoration In LLMs Fine-Tuning
by: Bach, Thong, et al.
Published: (2025)

CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift
by: Nguyen, Anh T, et al.
Published: (2023)

Kernel Learning for Sample Constrained Black-Box Optimization
by: Rajagopalan, Rajalaxmi, et al.
Published: (2025)

Continual Safety Alignment via Gradient-Based Sample Selection
by: Bach, Thong, et al.
Published: (2026)

Feature Optimization for Time Series Forecasting via Novel Randomized Uphill Climbing
by: Van Thanh, Nguyen
Published: (2025)

BSO: Safety Alignment Is Density Ratio Matching
by: Nguyen, Tien-Phat, et al.
Published: (2026)

Sample-Constrained Black Box Optimization for Audio Personalization
by: Rajagopalan, Rajalaxmi, et al.
Published: (2025)

Statistical Inference for Autoencoder-based Anomaly Detection after Representation Learning-based Domain Adaptation
by: Kiet, Tran Tuan, et al.
Published: (2025)

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
by: Ghosal, Soumya Suvra, et al.
Published: (2024)

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization
by: Li, Xinyu, et al.
Published: (2025)

Black Box Causal Inference: Effect Estimation via Meta Prediction
by: Bynum, Lucius E. J., et al.
Published: (2025)

Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Tasks
by: Fadhel, Azza, et al.
Published: (2026)

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
by: Chu, Jaewon, et al.
Published: (2025)

Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
by: Niu, Yifan, et al.
Published: (2025)

HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization
by: Tran, Trinh, et al.
Published: (2026)

No-Regret Learning of Nash Equilibrium for Black-Box Games via Gaussian Processes
by: Han, Minbiao, et al.
Published: (2024)

MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
by: Kan, Chun Yan Ryan, et al.
Published: (2026)

Boundary Point Jailbreaking of Black-Box LLMs
by: Davies, Xander, et al.
Published: (2026)

Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
by: Souček, Tomáš, et al.
Published: (2025)

Unveiling the Black Box: A Multi-Layer Framework for Explaining Reinforcement Learning-Based Cyber Agents
by: Goel, Diksha, et al.
Published: (2025)

Surrogate-based Optimization via Clustering for Box-Constrained Problems
by: Ahmad, Maaz, et al.
Published: (2026)

Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization
by: Om, Kiyoung, et al.
Published: (2025)

Enhancing Time Series Forecasting via a Parallel Hybridization of ARIMA and Polynomial Classifiers
by: Nguyen, Thanh Son, et al.
Published: (2025)

Stepwise Alignment for Constrained Language Model Policy Optimization
by: Wachi, Akifumi, et al.
Published: (2024)

Evaluating Black-Box Vulnerabilities with Wasserstein-Constrained Data Perturbations
by: Monteiro, Adriana Laurindo, et al.
Published: (2026)

Efficient Mixture Learning in Black-Box Variational Inference
by: Hotti, Alexandra, et al.
Published: (2024)

Robust SDE Parameter Estimation Under Missing Time Information Setting
by: Van Tran, Long, et al.
Published: (2026)

Reward Shaping for Inference-Time Alignment: A Stackelberg Game Perspective
by: Wang, Haichuan, et al.
Published: (2026)

Revisiting LARS for Large Batch Training Generalization of Neural Networks
by: Do, Khoi, et al.
Published: (2023)

Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
by: Tran, Nam Phuong, et al.
Published: (2024)

Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
by: Bakman, Yavuz, et al.
Published: (2026)

Agnostic Sharpness-Aware Minimization
by: Nguyen, Van-Anh, et al.
Published: (2024)

On the Convergence of Black-Box Variational Inference
by: Kim, Kyurae, et al.
Published: (2023)

Auditing Training Data in Generative Music Models via Black-Box Membership Inference
by: Liu, Yi Chen, et al.
Published: (2026)

Guardrails in Logit Space: Safety Token Regularization for LLM Alignment
by: Bach, Thong, et al.
Published: (2026)

Black Box Variational Inference with a Deterministic Objective: Faster, More Accurate, and Even More Black Box
by: Giordano, Ryan, et al.
Published: (2023)

Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
by: Zhai, Zhiyuan, et al.
Published: (2026)

Empirical Comparison of Lightweight Forecasting Models for Seasonal and Non-Seasonal Time Series
by: Nguyen, Thanh Son, et al.
Published: (2025)

GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
by: Galichin, Andrey V., et al.
Published: (2024)