paper-with-me

Papers

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics

2024-08-02 · Alexander Gushchin, Khaled Abud, Georgii Bychkov, Ekaterina Shumitskaya, Anna Chistyakova, Sergey Lavrushkin, Bader Rasheed, Kirill Malyshev, Dmitriy Vatolin, Anastasia Antsiferova

In the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics poses a critical concern. This paper presents a comprehensive benchmarking study of various defense mechanisms in response to the rise in adversarial attacks on IQA. We systematically evaluate 25 defense strategies, including adversarial purification, adversarial training, and certified robustness methods. We applied 14 adversarial attack algorithms of various types in both non-adaptive and adaptive settings and tested these defenses against them. We analyze the differences between defenses and their applicability to IQA tasks, considering that they should preserve IQA scores and image quality. The proposed benchmark aims to guide future developments and accepts submissions of new methods, with the latest results available online: https://videoprocessing.ai/benchmarks/iqa-defenses.html.

📄 PDF Abstract BibTeX arXiv:2408.01541

Code (1)

msu-video-group/adversarial-defenses-for-iqa 공식 구현 pytorch

Tasks

Adversarial AttackAdversarial PurificationAdversarial RobustnessBenchmarkingImage Quality Assessment

Similar Papers 제목 키워드 기반

Benchmarking adversarial attacks and defenses for time-series data

2020-08-30 · Shoaib Ahmed Siddiqui, Andreas Dengel, Sheraz Ahmed

The adversarial vulnerability of deep networks has spurred the interest of researchers worldwide. Unsurprisingly, like images, adversarial examples also translate to time-series data as they are an inherent weakness of t…

Adversarial DefenseBenchmarkingTime SeriesTime Series Analysis

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents

2026-06-01 · Yoshinari Fujinuma, Varun Gangal, Traian Rebedea, Makesh Narsimhan Sreedhar 외 arxiv

Large language model (LLM) agents increasingly rely on reusable skills i.e. documents describing task-specific procedures. However, this introduces a new attack surface for agents to manage. We study two complementary di…

Benchmarking Misuse Mitigation Against Covert Adversaries

2025-06-06 · Davis Brown, Mahdi Sabbaghi, Luze Sun, Alexander Robey 외

Existing language model safety evaluations focus on overt attacks and low-stakes tasks. Realistic attackers can subvert current safeguards by requesting help on small, benign-seeming tasks across many independent queries…

BenchmarkingLanguage ModelingLanguage Modelling

MultiRobustBench: Benchmarking Robustness Against Multiple Attacks

2023-02-21 · Sihui Dai, Saeed Mahloujifar, Chong Xiang, Vikash Sehwag 외

The bulk of existing research in defending against adversarial examples focuses on defending against a single (typically bounded Lp-norm) attack, but for a practical setting, machine learning (ML) models should be robust…

Benchmarking

Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks

2021-05-18 · NeurIPS 2021 12 · Dequan Wang, An Ju, Evan Shelhamer, David Wagner 외

Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should fight back, and optimize their defenses…