Imagen de Portada

N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Zheyu, Yang, Jirui, Qiu, Yukui, Guo, Hengqi, Bao, Yubing, Guan, Yao
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

UIFV: Data Reconstruction Attack in Vertical Federated Learning
por: Yang, Jirui, et al.
Publicado: (2024)

Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges
por: Eiras, Francisco, et al.
Publicado: (2025)

CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation
por: Yang, Jirui, et al.
Publicado: (2025)

AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing
por: Zhou, Tong, et al.
Publicado: (2024)

Prefix Probing: Lightweight Harmful Content Detection for Large Language Models
por: Yang, Jirui, et al.
Publicado: (2025)

The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation
por: Jia, Hengrui, et al.
Publicado: (2025)

SPECIAL: Synopsis Assisted Secure Collaborative Analytics
por: Wang, Chenghong, et al.
Publicado: (2024)

TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments
por: Liu, Ziyu, et al.
Publicado: (2024)

Improved Generation of Adversarial Examples Against Safety-aligned LLMs
por: Li, Qizhang, et al.
Publicado: (2024)

Probing the Robustness of Large Language Models Safety to Latent Perturbations
por: Gu, Tianle, et al.
Publicado: (2025)

SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud
por: Duan, Shijin, et al.
Publicado: (2024)

Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation
por: Iwahana, Kazuki, et al.
Publicado: (2025)

Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space
por: Roy, Padmaksha, et al.
Publicado: (2023)

Differentially Private Learned Indexes
por: Du, Jianzhang, et al.
Publicado: (2024)

An Efficient Private GPT Never Autoregressively Decodes
por: Li, Zhengyi, et al.
Publicado: (2025)

DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
por: Qiu, Han, et al.
Publicado: (2020)

NeST: Neuron Selective Tuning for LLM Safety
por: Behrouzi, Sasha, et al.
Publicado: (2026)

Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms
por: Wendlinger, Maximilian, et al.
Publicado: (2026)

TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation
por: Kumar, Mayank, et al.
Publicado: (2025)

LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation
por: Lazo, Luis, et al.
Publicado: (2026)

Colluding LoRA: A Compositional Vulnerability in LLM Safety Alignment
por: Ding, Sihao
Publicado: (2026)

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
por: Wang, Zhuoshang, et al.
Publicado: (2026)

WorldCup Sampling for Multi-bit LLM Watermarking
por: Wang, Yidan, et al.
Publicado: (2026)

EASE: Practical and Efficient Safety Alignment for Small Language Models
por: Shi, Haonan, et al.
Publicado: (2025)

Backdoor Attack on Vertical Federated Graph Neural Network Learning
por: Yang, Jirui, et al.
Publicado: (2024)

Improving LLM Safety Alignment with Dual-Objective Optimization
por: Zhao, Xuandong, et al.
Publicado: (2025)

Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack
por: Yue, Murong, et al.
Publicado: (2025)

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
por: He, Sinan, et al.
Publicado: (2025)

TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation
por: Cui, Tianyu, et al.
Publicado: (2025)

Efficient LLM Moderation with Multi-Layer Latent Prototypes
por: Chrabąszcz, Maciej, et al.
Publicado: (2025)

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
por: Lin, Shuyi, et al.
Publicado: (2025)

Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
por: Wang, Ziyao, et al.
Publicado: (2025)

DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
por: Guo, Zhen, et al.
Publicado: (2025)

PAE MobiLLM: Privacy-Aware and Efficient LLM Fine-Tuning on the Mobile Device via Additive Side-Tuning
por: Yang, Xingke, et al.
Publicado: (2025)

Evaluating Tabular Representation Learning for Network Intrusion Detection
por: Butt, Muhammad Usman, et al.
Publicado: (2026)

CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation
por: Yang, Xin, et al.
Publicado: (2025)

Token-Efficient Change Detection in LLM APIs
por: Chauvin, Timothée, et al.
Publicado: (2026)

Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
por: Khine, Ei Hmue, et al.
Publicado: (2026)

HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor
por: Wu, Zihui, et al.
Publicado: (2025)

Disguised Copyright Infringement of Latent Diffusion Models
por: Lu, Yiwei, et al.
Publicado: (2024)