Image de couverture de livre

How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liang, Zi, Yu, Liantong, Zhang, Shiyu, Ye, Qingqing, Hu, Haibo
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language 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

Dual Utilization of Perturbation for Stream Data Publication under Local Differential Privacy
par: Du, Rong, et autres
Publié: (2025)

From Randomized Response to Randomized Index: Answering Subset Counting Queries with Local Differential Privacy
par: Ye, Qingqing, et autres
Publié: (2025)

Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models
par: Liang, Zi, et autres
Publié: (2024)

PrivShape: Extracting Shapes in Time Series under User-Level Local Differential Privacy
par: Mao, Yulian, et autres
Publié: (2024)

PrivDPR: Synthetic Graph Publishing with Deep PageRank under Differential Privacy
par: Zhang, Sen, et autres
Publié: (2025)

PriPL-Tree: Accurate Range Query for Arbitrary Distribution under Local Differential Privacy
par: Wang, Leixia, et autres
Publié: (2024)

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
par: Bai, Li, et autres
Publié: (2025)

Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
par: Liang, Zi, et autres
Publié: (2025)

Federated Heavy Hitter Analytics with Local Differential Privacy
par: Zhang, Yuemin, et autres
Publié: (2024)

Non-Degenerate One-Time Pad and the integrity of perfectly secret messages
par: Shafarenko, Alex
Publié: (2024)

Multi-class Item Mining under Local Differential Privacy
par: Mao, Yulian, et autres
Publié: (2025)

Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection
par: Liang, Zi, et autres
Publié: (2026)

Privacy for Free: Leveraging Local Differential Privacy Perturbed Data from Multiple Services
par: Du, Rong, et autres
Publié: (2025)

"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation
par: Liang, Zi, et autres
Publié: (2024)

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
par: Xu, Xiaoyu, et autres
Publié: (2025)

A Sample-Level Evaluation and Generative Framework for Model Inversion Attacks
par: Li, Haoyang, et autres
Publié: (2025)

Data Poisoning Attacks to Local Differential Privacy Protocols for Graphs
par: He, Xi, et autres
Publié: (2024)

Interactive Trimming against Evasive Online Data Manipulation Attacks: A Game-Theoretic Approach
par: Fu, Yue, et autres
Publié: (2024)

How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuning
par: Salerno, Fabio, et autres
Publié: (2025)

WiFinger: Fingerprinting Noisy IoT Event Traffic Using Packet-level Sequence Matching
par: Li, Ronghua, et autres
Publié: (2025)

MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective
par: Zhang, Xinwei, et autres
Publié: (2025)

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
par: Liang, Zi, et autres
Publié: (2025)

AdvSGM: Differentially Private Graph Learning via Adversarial Skip-gram Model
par: Zhang, Sen, et autres
Publié: (2025)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
par: Zhang, Xinwei, et autres
Publié: (2026)

From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
par: Xu, Xiaoyu, et autres
Publié: (2026)

United We Defend: Collaborative Membership Inference Defenses in Federated Learning
par: Bai, Li, et autres
Publié: (2026)

Membership Inference Attacks and Defenses in Federated Learning: A Survey
par: Bai, Li, et autres
Publié: (2024)

A Thorough Study of State Leakage Mitigation in Quantum Computing with One-Time Pad
par: Xu, Chuanqi, et autres
Publié: (2024)

Cross-Modal Backdoors in Multimodal Large Language Models
par: Wang, Runhe, et autres
Publié: (2026)

One-time Pad Encryption Model for Non-local Correlations
par: Sidhardh, Govind Lal, et autres
Publié: (2023)

LDPRecover: Recovering Frequencies from Poisoning Attacks against Local Differential Privacy
par: Sun, Xinyue, et autres
Publié: (2024)

On the Reliability of Biometric Datasets: How Much Test Data Ensures Reliability?
par: Fallahi, Matin, et autres
Publié: (2025)

A Systematic Review of Technical Defenses Against Software-Based Cheating in Online Multiplayer Games
par: Alangari, Adwa, et autres
Publié: (2025)

SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
par: Ying, Zonghao, et autres
Publié: (2024)

Padding Matters -- Exploring Function Detection in PE Files
par: Springer, Raphael, et autres
Publié: (2025)

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
par: Xiao, Yaxin, et autres
Publié: (2025)

Cheat-Penalised Quantum Weak Coin-Flipping
par: Arora, Atul Singh, et autres
Publié: (2025)

Synopticon: Consensus-Based Cheating Detection System for Competitive Games
par: Kang, Jeuk, et autres
Publié: (2025)

FIT to Forget: Robust Continual Unlearning for Large Language Models
par: Xu, Xiaoyu, et autres
Publié: (2026)

Addressing Network Packet-based Cheats in Multiplayer Games: A Secret Sharing Approach
par: Cai, Yaqi, et autres
Publié: (2025)