Cover Image

On The Fragility of Benchmark Contamination Detection in Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Han, Li, Haoyu, Ko, Brian, Zhang, Huan
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM Benchmark Datasets Should Be Contamination-Resistant
by: Al-Lawati, Ali, et al.
Published: (2026)

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
by: Wang, Erchi, et al.
Published: (2026)

OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection
by: Jiang, Haoyu, et al.
Published: (2023)

Beyond Detection: A Comprehensive Benchmark and Study on Representation Learning for Fine-Grained Webshell Family Classification
by: Han, Feijiang
Published: (2025)

Evading Data Contamination Detection for Language Models is (too) Easy
by: Dekoninck, Jasper, et al.
Published: (2024)

Conditional Adversarial Fragility in Financial Machine Learning under Macroeconomic Stress
by: Baviskar, Samruddhi
Published: (2025)

Attention Tracker: Detecting Prompt Injection Attacks in LLMs
by: Hung, Kuo-Han, et al.
Published: (2024)

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
by: Fang, Junfeng, et al.
Published: (2025)

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
by: Zhang, Mohan, et al.
Published: (2025)

Magnitude-based Neuron Pruning for Backdoor Defens
by: Li, Nan, et al.
Published: (2024)

A Customer Level Fraudulent Activity Detection Benchmark for Enhancing Machine Learning Model Research and Evaluation
by: Jing, Phoebe, et al.
Published: (2024)

Large Language Models in Wireless Application Design: In-Context Learning-enhanced Automatic Network Intrusion Detection
by: Zhang, Han, et al.
Published: (2024)

A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
by: Dai, Jiazhu, et al.
Published: (2025)

Effective backdoor attack on graph neural networks in link prediction tasks
by: Dai, Jiazhu, et al.
Published: (2024)

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data
by: Zhou, Andy, et al.
Published: (2024)

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
by: Poppi, Samuele, et al.
Published: (2024)

Detecting Benchmark Contamination Through Watermarking
by: Sander, Tom, et al.
Published: (2025)

Membership Inference Attack with Partial Features
by: Wang, Xurun, et al.
Published: (2025)

Exploring Robust Intrusion Detection: A Benchmark Study of Feature Transferability in IoT Botnet Attack Detection
by: Guerra-Manzanares, Alejandro, et al.
Published: (2026)

Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models
by: Wang, Jeffrey G., et al.
Published: (2024)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
by: Srivastava, Saksham Sahai, et al.
Published: (2025)

GuardReasoner: Towards Reasoning-based LLM Safeguards
by: Liu, Yue, et al.
Published: (2025)

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
by: Huang, Tiansheng, et al.
Published: (2025)

AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
by: Li, Fengpeng, et al.
Published: (2026)

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
by: Zhang, Guangsheng, et al.
Published: (2022)

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
by: Zhang, Jiawei, et al.
Published: (2025)

A Generative Approach to Surrogate-based Black-box Attacks
by: Moraffah, Raha, et al.
Published: (2024)

Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries
by: Çolhak, Furkan, et al.
Published: (2025)

Explainable AI for Comparative Analysis of Intrusion Detection Models
by: Corea, Pap M., et al.
Published: (2024)

Data Valuation and Detections in Federated Learning
by: Li, Wenqian, et al.
Published: (2023)

VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
by: Yu, Simon, et al.
Published: (2025)

Time Travel in LLMs: Tracing Data Contamination in Large Language Models
by: Golchin, Shahriar, et al.
Published: (2023)

Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models
by: Krishna, Arjun, et al.
Published: (2025)

Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection
by: Guo, Yihao, et al.
Published: (2025)

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

LAN: Learning Adaptive Neighbors for Real-Time Insider Threat Detection
by: Cai, Xiangrui, et al.
Published: (2024)

PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
by: Li, Wei, et al.
Published: (2024)

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
by: Jiang, Fengqing, et al.
Published: (2025)

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
by: Zhang, Heyi, et al.
Published: (2025)

Finetuning Large Language Models for Vulnerability Detection
by: Shestov, Alexey, et al.
Published: (2024)