Copertina

Towards the Worst-case Robustness of Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Huanran, Dong, Yinpeng, Wei, Zeming, Su, Hang, Zhu, Jun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Unveiling the Basin-Like Loss Landscape in Large Language Models
di: Chen, Huanran, et al.
Pubblicazione: (2025)

Your Diffusion Model is Secretly a Certifiably Robust Classifier
di: Chen, Huanran, et al.
Pubblicazione: (2024)

Robust Classification via a Single Diffusion Model
di: Chen, Huanran, et al.
Pubblicazione: (2023)

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
di: Wu, Chengcan, et al.
Pubblicazione: (2025)

Alignment Dynamics in LLM Fine-Tuning
di: Huang, Yuhan, et al.
Pubblicazione: (2026)

MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
di: Zhang, Yichi, et al.
Pubblicazione: (2024)

Scaling Laws for Black box Adversarial Attacks
di: Liu, Chuan, et al.
Pubblicazione: (2024)

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
di: Zhang, Yichi, et al.
Pubblicazione: (2024)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
di: Huang, Yao, et al.
Pubblicazione: (2025)

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
di: Chen, Huanran, et al.
Pubblicazione: (2026)

Decoding Large Language Diffusion Models with Foreseeing Movement
di: Mo, Yichuan, et al.
Pubblicazione: (2025)

On the Duality Between Sharpness-Aware Minimization and Adversarial Training
di: Zhang, Yihao, et al.
Pubblicazione: (2024)

Diffusion Models as Dataset Distillation Priors
di: Su, Duo, et al.
Pubblicazione: (2025)

Adversarial Training for Robust Coverage Network under Worst-case Facility Losses
di: Miao, Changhao, et al.
Pubblicazione: (2026)

Rethinking Model Ensemble in Transfer-based Adversarial Attacks
di: Chen, Huanran, et al.
Pubblicazione: (2023)

MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models
di: Ai, Mengting, et al.
Pubblicazione: (2023)

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
di: Zhang, Yihao, et al.
Pubblicazione: (2024)

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
di: Yu, Yunrui, et al.
Pubblicazione: (2026)

Worst-case generation via minimax optimization in Wasserstein space
di: Cheng, Xiuyuan, et al.
Pubblicazione: (2025)

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
di: Wei, Xingxing, et al.
Pubblicazione: (2024)

Evaluating Model Performance Under Worst-case Subpopulations
di: Li, Mike, et al.
Pubblicazione: (2024)

Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
di: Ying, Chengyang, et al.
Pubblicazione: (2022)

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
di: Liu, Xiangyu, et al.
Pubblicazione: (2024)

PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
di: Zhu, Kaijie, et al.
Pubblicazione: (2023)

Improving Full Waveform Inversion in Large Model Era
di: Feng, Yinan, et al.
Pubblicazione: (2026)

Toward Availability Attacks in 3D Point Clouds
di: Zhu, Yifan, et al.
Pubblicazione: (2024)

Worst-case low-rank approximations
di: Fries, Anya, et al.
Pubblicazione: (2026)

Noise Contrastive Alignment of Language Models with Explicit Rewards
di: Chen, Huayu, et al.
Pubblicazione: (2024)

Towards a General Framework for Continual Learning with Pre-training
di: Wang, Liyuan, et al.
Pubblicazione: (2023)

Towards Multimodal Graph Large Language Model
di: Wang, Xin, et al.
Pubblicazione: (2025)

Towards Versatile Graph Learning Approach: from the Perspective of Large Language Models
di: Wei, Lanning, et al.
Pubblicazione: (2024)

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
di: Kang, Caixin, et al.
Pubblicazione: (2023)

A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models
di: Cai, Yinpeng, et al.
Pubblicazione: (2025)

Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models
di: Cui, Peng, et al.
Pubblicazione: (2024)

R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability
di: Lu, Runyu, et al.
Pubblicazione: (2025)

Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning
di: Su, Guangxin, et al.
Pubblicazione: (2024)

Automata-Based Steering of Large Language Models for Diverse Structured Generation
di: Luan, Xiaokun, et al.
Pubblicazione: (2025)

Towards Generation-Efficient Uncertainty Estimation in Large Language Models
di: Zhu, Mingcheng, et al.
Pubblicazione: (2026)

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
di: Chen, Huayu, et al.
Pubblicazione: (2024)

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
di: Chen, Huayu, et al.
Pubblicazione: (2024)