:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Ruikai, Yang, Kang, Chen, Xun, Wang, Wendy Hui, Tao, Guanhong, Xu, Jun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	https://arxiv.org/abs/2507.03619
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Alleviating the Fear of Losing Alignment in LLM Fine-tuning
di: Yang, Kang, et al.
Pubblicazione: (2025)

HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines
di: Yang, Kang, et al.
Pubblicazione: (2025)

Rethinking the Evaluation of Secure Code Generation
di: Dai, Shih-Chieh, et al.
Pubblicazione: (2025)

AdvAgent: Controllable Blackbox Red-teaming on Web Agents
di: Xu, Chejian, et al.
Pubblicazione: (2024)

BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks
di: Zheng, Meixi, et al.
Pubblicazione: (2023)

Curator Attack: When Blackbox Differential Privacy Auditing Loses Its Power
di: Wang, Shiming, et al.
Pubblicazione: (2024)

Dataset Poisoning Attacks on Behavioral Cloning Policies
di: Kalra, Akansha, et al.
Pubblicazione: (2025)

Safeguarding Graph Neural Networks against Topology Inference Attacks
di: Fu, Jie, et al.
Pubblicazione: (2025)

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
di: Fu, Jie, et al.
Pubblicazione: (2026)

A Sentence Relation-Based Approach to Sanitizing Malicious Instructions
di: Datta, Soumil, et al.
Pubblicazione: (2026)

Opening A Pandora's Box: Things You Should Know in the Era of Custom GPTs
di: Tao, Guanhong, et al.
Pubblicazione: (2023)

How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
di: Kalra, Akansha, et al.
Pubblicazione: (2025)

Evaluate and Guard the Wisdom of Crowds: Zero Knowledge Proofs for Crowdsourcing Truth Inference
di: Liu, Xuanming, et al.
Pubblicazione: (2023)

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
di: Zeng, Wenxuan, et al.
Pubblicazione: (2025)

CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference
di: Luo, Jinglong, et al.
Pubblicazione: (2024)

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
di: Chen, Xuan, et al.
Pubblicazione: (2025)

No Free Lunch Theorem for Privacy-Preserving LLM Inference
di: Zhang, Xiaojin, et al.
Pubblicazione: (2024)

Differentially Private Federated Learning: A Systematic Review
di: Fu, Jie, et al.
Pubblicazione: (2024)

An Automated Blackbox Noncompliance Checker for QUIC Server Implementations
di: Ang, Kian Kai, et al.
Pubblicazione: (2025)

Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
di: Zhu, Rui, et al.
Pubblicazione: (2023)

Watermarking Text Data on Large Language Models for Dataset Copyright
di: Liu, Yixin, et al.
Pubblicazione: (2023)

Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models
di: Zhang, Xiaomei, et al.
Pubblicazione: (2026)

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
di: Naderloui, Nima, et al.
Pubblicazione: (2025)

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
di: Zhong, Zhiyuan, et al.
Pubblicazione: (2025)

Why does weak-OOD help? A Further Step Towards Understanding Jailbreaking VLMs
di: Zhou, Yuxuan, et al.
Pubblicazione: (2025)

White-box Membership Inference Attacks against Diffusion Models
di: Pang, Yan, et al.
Pubblicazione: (2023)

Watermarking LLM-Generated Datasets in Downstream Tasks
di: Liu, Yugeng, et al.
Pubblicazione: (2025)

A Survey on Private Transformer Inference
di: Li, Yang, et al.
Pubblicazione: (2024)

Private Transformer Inference in MLaaS: A Survey
di: Li, Yang, et al.
Pubblicazione: (2025)

FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference
di: Lin, Chenqi, et al.
Pubblicazione: (2024)

PostMark: A Robust Blackbox Watermark for Large Language Models
di: Chang, Yapei, et al.
Pubblicazione: (2024)

LightDE: A Lightweight Method for Eliminating Dangling Pointers
di: An, Xun
Pubblicazione: (2024)

PersonaFingerprint: Measuring Persona Inference on Modern Websites with LLM-Driven Browsing
di: Song, Chuxu, et al.
Pubblicazione: (2026)

LLM Dataset Inference: Did you train on my dataset?
di: Maini, Pratyush, et al.
Pubblicazione: (2024)

Ward: Provable RAG Dataset Inference via LLM Watermarks
di: Jovanović, Nikola, et al.
Pubblicazione: (2024)

LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge
di: Li, Songze, et al.
Pubblicazione: (2025)

Kangaroo: A Private and Amortized Inference Framework over WAN for Large-Scale Decision Tree Evaluation
di: Xu, Wei, et al.
Pubblicazione: (2025)

Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
di: Kang, Mintong, et al.
Pubblicazione: (2025)

Label Inference Attacks against Federated Unlearning
di: Wang, Wei, et al.
Pubblicazione: (2025)

PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN
di: Zheng, Fei, et al.
Pubblicazione: (2024)