Image de couverture de livre

Watermark Smoothing Attacks against Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chang, Hongyan, Hassani, Hamed, Shokri, Reza
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
par: Chang, Hongyan, et autres
Publié: (2024)

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
par: Robey, Alexander, et autres
Publié: (2023)

Watermarking Language Models with Error Correcting Codes
par: Chao, Patrick, et autres
Publié: (2024)

Range Membership Inference Attacks
par: Tao, Jiashu, et autres
Publié: (2024)

Low-Cost High-Power Membership Inference Attacks
par: Zarifzadeh, Sajjad, et autres
Publié: (2023)

Generalization Properties of Adversarial Training for $\ell_0$-Bounded Adversarial Attacks
par: Delgosha, Payam, et autres
Publié: (2024)

(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs
par: Tao, Jiashu, et autres
Publié: (2025)

Machine Learning from Explanations
par: Tao, Jiashu, et autres
Publié: (2025)

Evaluating the Performance of Large Language Models via Debates
par: Moniri, Behrad, et autres
Publié: (2024)

Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
par: Moniri, Behrad, et autres
Publié: (2026)

On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
par: Moniri, Behrad, et autres
Publié: (2025)

MEA-Defender: A Robust Watermark against Model Extraction Attack
par: Lv, Peizhuo, et autres
Publié: (2024)

Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models
par: Moniri, Behrad, et autres
Publié: (2024)

Asymptotics of Linear Regression with Linearly Dependent Data
par: Moniri, Behrad, et autres
Publié: (2024)

The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
par: Hassani, Hamed, et autres
Publié: (2022)

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
par: Ji, Jiabao, et autres
Publié: (2024)

Smaller Language Models are Better Black-box Machine-Generated Text Detectors
par: Mireshghallah, Niloofar, et autres
Publié: (2023)

Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity
par: Ganesh, Prakhar, et autres
Publié: (2026)

Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing
par: Zhong, Xuyang, et autres
Publié: (2025)

Conformal Information Pursuit for Interactively Guiding Large Language Models
par: Chan, Kwan Ho Ryan, et autres
Publié: (2025)

Conformal Prediction with Learned Features
par: Kiyani, Shayan, et autres
Publié: (2024)

BrainLeaks: On the Privacy-Preserving Properties of Neuromorphic Architectures against Model Inversion Attacks
par: Poursiami, Hamed, et autres
Publié: (2024)

Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
par: Noorani, Sima, et autres
Publié: (2025)

Leave-one-out Distinguishability in Machine Learning
par: Ye, Jiayuan, et autres
Publié: (2023)

Semantic Membership Inference Attack against Large Language Models
par: Mozaffari, Hamid, et autres
Publié: (2024)

Jailbreaking Black Box Large Language Models in Twenty Queries
par: Chao, Patrick, et autres
Publié: (2023)

Length Optimization in Conformal Prediction
par: Kiyani, Shayan, et autres
Publié: (2024)

A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
par: Moniri, Behrad, et autres
Publié: (2023)

Provable tradeoffs in adversarially robust classification
par: Dobriban, Edgar, et autres
Publié: (2020)

InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting
par: Sabbaghi, Mahdi, et autres
Publié: (2026)

Multi-Round Human-AI Collaboration with User-Specified Requirements
par: Noorani, Sima, et autres
Publié: (2026)

MultiRisk: Multiple Risk Control via Iterative Score Thresholding
par: Joshi, Sunay, et autres
Publié: (2025)

Robust Policy Optimization to Prevent Catastrophic Forgetting
par: Sabbaghi, Mahdi, et autres
Publié: (2026)

Neural Estimation of the Rate-Distortion Function With Applications to Operational Source Coding
par: Lei, Eric, et autres
Publié: (2022)

Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff
par: Lei, Eric, et autres
Publié: (2025)

Provable Watermarking for Data Poisoning Attacks
par: Zhu, Yifan, et autres
Publié: (2025)

BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks
par: Li, Zhuang, et autres
Publié: (2025)

Generalization in LLM Problem Solving: The Case of the Shortest Path
par: Tong, Yao, et autres
Publié: (2026)

Adversarial Evasion Attack Efficiency against Large Language Models
par: Vitorino, João, et autres
Publié: (2024)

Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing
par: Feng, Ryan, et autres
Publié: (2022)