Imagen de Portada

EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yanting, Jia, Jinyuan
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models
por: Wang, Yanting, et al.
Publicado: (2024)

AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
por: Wang, Yanting, et al.
Publicado: (2025)

TracLLM: A Generic Framework for Attributing Long Context LLMs
por: Wang, Yanting, et al.
Publicado: (2025)

AgentWatcher: A Rule-based Prompt Injection Monitor
por: Wang, Yanting, et al.
Publicado: (2026)

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
por: Wang, Yanting, et al.
Publicado: (2026)

TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning
por: Liu, Yupei, et al.
Publicado: (2025)

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
por: Yang, Yuxin, et al.
Publicado: (2024)

TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
por: Wang, Yanting, et al.
Publicado: (2025)

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
por: Yin, Chenlong, et al.
Publicado: (2026)

Certifiably Robust Image Watermark
por: Jiang, Zhengyuan, et al.
Publicado: (2024)

SecInfer: Preventing Prompt Injection via Inference-time Scaling
por: Liu, Yupei, et al.
Publicado: (2025)

MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
por: Wang, Yanting, et al.
Publicado: (2024)

UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
por: Geng, Runpeng, et al.
Publicado: (2025)

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
por: Li, Jiate, et al.
Publicado: (2025)

PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features
por: Zou, Wei, et al.
Publicado: (2025)

RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Masking
por: Liu, Jiawei, et al.
Publicado: (2025)

Ideal Attribution and Faithful Watermarks for Language Models
por: Song, Min Jae, et al.
Publicado: (2025)

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
por: Lyu, Saiyue, et al.
Publicado: (2024)

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
por: Yang, Yuxin, et al.
Publicado: (2024)

Registered Attribute-Based Encryption with Publicly Verifiable Certified Deletion, Everlasting Security, and More
por: Murshid, Shayeef, et al.
Publicado: (2026)

Interpretable Ensemble Learning for Network Traffic Anomaly Detection: A SHAP-based Explainable AI Framework for Embedded Systems Security
por: Shao, Wanru
Publicado: (2026)

Explainable Threat Attribution for IoT Networks Using Conditional SHAP and Flow Behavior Modelling
por: Ozechi, Samuel, et al.
Publicado: (2026)

A Certified Robust Watermark For Large Language Models
por: Feng, Xianheng, et al.
Publicado: (2024)

A Robust Certified Machine Unlearning Method Under Distribution Shift
por: Guo, Jinduo, et al.
Publicado: (2026)

PIArena: A Platform for Prompt Injection Evaluation
por: Geng, Runpeng, et al.
Publicado: (2026)

Towards Strong Certified Defense with Universal Asymmetric Randomization
por: Hong, Hanbin, et al.
Publicado: (2025)

Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble
por: Dong, Chang, et al.
Publicado: (2024)

Evaluating LLM-based Personal Information Extraction and Countermeasures
por: Liu, Yupei, et al.
Publicado: (2024)

Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing
por: Fu, Chengyan, et al.
Publicado: (2024)

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing
por: Gibert, Daniel, et al.
Publicado: (2024)

Getting a-Round Guarantees: Floating-Point Attacks on Certified Robustness
por: Jin, Jiankai, et al.
Publicado: (2022)

AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
por: Huang, Zhuoqun, et al.
Publicado: (2025)

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation
por: Ye, Hengkai, et al.
Publicado: (2026)

Provably Robust Multi-bit Watermarking for AI-generated Text
por: Qu, Wenjie, et al.
Publicado: (2024)

On the Equivalence between Classical Position Verification and Certified Randomness
por: Kaleoglu, Fatih, et al.
Publicado: (2024)

Privacy-Optimized Randomized Response for Sharing Multi-Attribute Data
por: Yamamoto, Akito, et al.
Publicado: (2024)

On Using Certified Training towards Empirical Robustness
por: De Palma, Alessandro, et al.
Publicado: (2024)

Certified Causal Attribution for Real-Time Attack Forensics in 6G Network Slicing
por: Quan, Minh K., et al.
Publicado: (2026)

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
por: Geng, Runpeng, et al.
Publicado: (2025)

Interpretable Anomaly Detection in Encrypted Traffic Using SHAP with Machine Learning Models
por: Singh, Kalindi, et al.
Publicado: (2025)