Image de couverture de livre

FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Yanting, Zou, Wei, Jia, Jinyuan
Format:	Preprint
Publié:	2024
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method
par: Wang, Yanting, et autres
Publié: (2026)

AgentWatcher: A Rule-based Prompt Injection Monitor
par: Wang, Yanting, et autres
Publié: (2026)

MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
par: Wang, Yanting, et autres
Publié: (2024)

TracLLM: A Generic Framework for Attributing Long Context LLMs
par: Wang, Yanting, et autres
Publié: (2025)

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
par: Wang, Yanting, et autres
Publié: (2026)

TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning
par: Liu, Yupei, et autres
Publié: (2025)

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
par: Yang, Yuxin, et autres
Publié: (2024)

PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features
par: Zou, Wei, et autres
Publié: (2025)

TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
par: Wang, Yanting, et autres
Publié: (2025)

AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
par: Wang, Yanting, et autres
Publié: (2025)

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
par: Yin, Chenlong, et autres
Publié: (2026)

Certifiably Robust Image Watermark
par: Jiang, Zhengyuan, et autres
Publié: (2024)

PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
par: Zou, Wei, et autres
Publié: (2024)

SecInfer: Preventing Prompt Injection via Inference-time Scaling
par: Liu, Yupei, et autres
Publié: (2025)

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models
par: Nie, Yuzhou., et autres
Publié: (2024)

UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
par: Geng, Runpeng, et autres
Publié: (2025)

Provably Robust Multi-bit Watermarking for AI-generated Text
par: Qu, Wenjie, et autres
Publié: (2024)

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
par: Li, Jiate, et autres
Publié: (2025)

A Certified Robust Watermark For Large Language Models
par: Feng, Xianheng, et autres
Publié: (2024)

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
par: Jin, Weifei, et autres
Publié: (2026)

A Classification-by-Retrieval Framework for Few-Shot Anomaly Detection to Detect API Injection Attacks
par: Aharon, Udi, et autres
Publié: (2024)

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
par: Yang, Yuxin, et autres
Publié: (2024)

PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
par: Zhang, Jianqing, et autres
Publié: (2025)

Robust Privacy: Inference-Time Privacy through Certified Robustness
par: Jin, Jiankai, et autres
Publié: (2026)

PIArena: A Platform for Prompt Injection Evaluation
par: Geng, Runpeng, et autres
Publié: (2026)

Evaluating LLM-based Personal Information Extraction and Countermeasures
par: Liu, Yupei, et autres
Publié: (2024)

MalMixer: Few-Shot Malware Classification with Retrieval-Augmented Semi-Supervised Learning
par: Li, Jiliang, et autres
Publié: (2024)

Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble
par: Dong, Chang, et autres
Publié: (2024)

CERT-ED: Certifiably Robust Text Classification for Edit Distance
par: Huang, Zhuoqun, et autres
Publié: (2024)

Getting a-Round Guarantees: Floating-Point Attacks on Certified Robustness
par: Jin, Jiankai, et autres
Publié: (2022)

RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Masking
par: Liu, Jiawei, et autres
Publié: (2025)

Risks of Practicing Large Language Models in Smart Grid: Threat Modeling and Validation
par: Li, Jiangnan, et autres
Publié: (2024)

Position: Certified Robustness Does Not (Yet) Imply Model Security
par: Cullen, Andrew C., et autres
Publié: (2025)

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation
par: Ye, Hengkai, et autres
Publié: (2026)

Few-Shot Learning-Based Cyber Incident Detection with Augmented Context Intelligence
par: Zuo, Fei, et autres
Publié: (2025)

On Using Certified Training towards Empirical Robustness
par: De Palma, Alessandro, et autres
Publié: (2024)

Distributed Intrusion Detection in Dynamic Networks of UAVs using Few-Shot Federated Learning
par: Ceviz, Ozlem, et autres
Publié: (2025)

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
par: Geng, Runpeng, et autres
Publié: (2025)

Certified Causal Defense with Generalizable Robustness
par: Qiao, Yiran, et autres
Publié: (2024)

Dataset Ownership in the Era of Large Language Models
par: Li, Kun, et autres
Publié: (2025)