paper-with-me

홈 › Papers

Selective Adversarial Attacks on LLM Benchmarks

2025-10-15 · Ivan Dubrovsky, Anastasia Orlova, Illarion Iov, Nina Gubina, Irena Gureeva, Alexey Zaytsev arxiv

Benchmarking outcomes increasingly govern trust, selection, and deployment of LLMs, yet these evaluations remain vulnerable to semantically equivalent adversarial perturbations. Prior work on adversarial robustness in NLP has emphasized text attacks that affect many models equally, leaving open the question of whether it is possible to selectively degrade or enhance performance while minimally affecting other models. We formalize this problem and study selective adversarial attacks on MMLU - a widely used benchmark designed to measure a language model's broad general knowledge and reasoning ability across different subjects. Using canonical attacks integrated into TextAttack framework, we introduce a protocol for selectivity assessment, develop a custom constraint to increase selectivity of attacks and propose a surrogate-LLM pipeline that generates selective perturbations. Empirically, we find that selective adversarial attacks exist and can materially alter relative rankings, challenging the fairness, reproducibility, and transparency of leaderboard-driven evaluation. Our results motivate perturbation-aware reporting and robustness diagnostics for LLM evaluation and demonstrate that even subtle edits can shift comparative judgments.

📄 PDF Abstract BibTeX arXiv:2510.13570

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessGeneral Knowledge

Similar Papers 제목 키워드 기반

Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders

2018-05-31 · Partha Ghosh, Arpan Losalka, Michael J. Black

Susceptibility of deep neural networks to adversarial attacks poses a major theoretical and practical challenge. All efforts to harden classifiers against such attacks have seen limited success. Two distinct categories o…

Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective

2022-08-20 · Gihyun Kim, Juyeop Kim, Jong-Seok Lee

The Vision Transformer has emerged as a powerful tool for image classification tasks, surpassing the performance of convolutional neural networks (CNNs). Recently, many researchers have attempted to understand the robust…

Adversarial Robustnessimage-classificationImage Classification

INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression

2026-04-13 · Gamze Kirman Tokgoz, Onat Gungor, Tajana Rosing, Baris Aksanli arxiv

Time-series forecasting aims to predict future values by modeling temporal dependencies in historical observations. It is a critical component of many real-world systems, where accurate forecasts improve operational effi…

Adversarial Attack

Keep on Going: Learning Robust Humanoid Motion Skills via Selective Adversarial Training

2025-07-11 · Yang Zhang, Zhanxiang Cao, Buqing Nie, Haoyang Li 외 arxiv

Humanoid robots are expected to operate reliably over long horizons while executing versatile whole-body skills. Yet Reinforcement Learning (RL) motion policies typically lose stability under prolonged operation, sensor/…

Reinforcement LearningAdversarial Attack

Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection

2021-03-09 · Ahmed Aldahdooh, Wassim Hamidouche, Olivier Déforges

Security-sensitive applications that rely on Deep Neural Networks (DNNs) are vulnerable to small perturbations that are crafted to generate Adversarial Examples(AEs). The AEs are imperceptible to humans and cause DNN to …

Multi-Task LearningTransfer Learning