Cover Image

A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Oyarhoseini, Hosna, Lin, Jimmy, Karimi, Amir-Hossein
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unifying Adversarial Robustness and Training Across Text Scoring Models
by: Tamber, Manveer Singh, et al.
Published: (2026)

Position: Explainable AI is Causality in Disguise
by: Karimi, Amir-Hossein
Published: (2026)

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
by: Huang, Yangsibo, et al.
Published: (2025)

Prompt-to-Leaderboard
by: Frick, Evan, et al.
Published: (2025)

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
by: Suri, Anshuman, et al.
Published: (2025)

On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards
by: Zhao, Zhimin, et al.
Published: (2024)

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
by: Naseh, Ali, et al.
Published: (2025)

Temporal convolutional and fusional transformer model with Bi-LSTM encoder-decoder for multi-time-window remaining useful life prediction
by: Pour, Mohamadreza Akbari, et al.
Published: (2025)

Identifying Models Behind Text-to-Image Leaderboards
by: Naseh, Ali, et al.
Published: (2026)

Securing Healthcare with Deep Learning: A CNN-Based Model for medical IoT Threat Detection
by: Mohamadi, Alireza, et al.
Published: (2024)

The Leaderboard Illusion
by: Singh, Shivalika, et al.
Published: (2025)

Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation
by: Zhong, Xuyang, et al.
Published: (2024)

Predictive Maintenance of Electric Motors Using Supervised Learning Models: A Comparative Analysis
by: Baradaran, Amir Hossein
Published: (2025)

A Unified Framework for Analyzing Meta-algorithms in Online Convex Optimization
by: Pedramfar, Mohammad, et al.
Published: (2024)

Automating API Documentation with LLMs: A BERTopic Approach
by: Naghshzan, AmirHossein
Published: (2025)

MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation
by: Taji, Mehrshad, et al.
Published: (2026)

Bridging Brain with Foundation Models through Self-Supervised Learning
by: Altaheri, Hamdi, et al.
Published: (2025)

Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard
by: Liu, Si-Yang, et al.
Published: (2025)

RepairBench: Leaderboard of Frontier Models for Program Repair
by: Silva, André, et al.
Published: (2024)

LLM Robustness Leaderboard v1 --Technical report
by: Lefebvre, Pierre Peigné -, et al.
Published: (2025)

How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness
by: Gordienko, Polina, et al.
Published: (2026)

Measuring AI Progress in Drug Discovery: A Reproducible Leaderboard for the Tox21 Challenge
by: Ebner, Antonia, et al.
Published: (2025)

Quantifying User Coherence: A Unified Framework for Analyzing Recommender Systems Across Domains
by: Soumm, Michaël, et al.
Published: (2024)

Unified Explanations in Machine Learning Models: A Perturbation Approach
by: Dineen, Jacob, et al.
Published: (2024)

Robust Learnability of Sample-Compressible Distributions under Noisy or Adversarial Perturbations
by: Boushehrian, Arefe, et al.
Published: (2025)

DISCO-TAB: A Hierarchical Reinforcement Learning Framework for Privacy-Preserving Synthesis of Complex Clinical Data
by: Ilaty, Arshia, et al.
Published: (2026)

A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability
by: Fatemi, Pouria, et al.
Published: (2025)

Temporally Unified Adversarial Perturbations for Time Series Forecasting
by: Su, Ruixian, et al.
Published: (2026)

CLAIM: An Intent-Driven Multi-Agent Framework for Analyzing Manipulation in Courtroom Dialogues
by: Sheshanarayana, Disha, et al.
Published: (2025)

Analyzing Adversarial Inputs in Deep Reinforcement Learning
by: Corsi, Davide, et al.
Published: (2024)

Adaptability in Multi-Agent Reinforcement Learning: A Framework and Unified Review
by: Hu, Siyi, et al.
Published: (2025)

Is Algorithmic Stability Testable? A Unified Framework under Computational Constraints
by: Luo, Yuetian, et al.
Published: (2024)

Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks
by: Eilers, Florian, et al.
Published: (2026)

Unifying Adversarial Perturbation for Graph Neural Networks
by: Yang, Jinluan, et al.
Published: (2025)

DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation
by: Karimi, Amin, et al.
Published: (2025)

Leaderboard Incentives: Model Rankings under Strategic Post-Training
by: Chen, Yatong, et al.
Published: (2026)

Stability Evaluation via Distributional Perturbation Analysis
by: Blanchet, Jose, et al.
Published: (2024)

AMIR-GRPO: Inducing Implicit Preference Signals into GRPO
by: Yari, Amir Hossein, et al.
Published: (2026)

How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation
by: Singh, Prabhant, et al.
Published: (2025)

When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards
by: Alzahrani, Norah, et al.
Published: (2024)