Anastasia Antsiferova

Sber AI

MSU Institute for AI

Trusted AI Research Center Russian Academy of Sciences

12 years in Video Compression, Computer Vision, and Adversarial Robustness.

Experienced in leading research teams, developing state-of-the-art benchmarks, academia-industry collaboration, and startups. Published 10+ papers at top-tier conferences (NeurIPS, ICML, ICLR, AAAI).

Current research focus:

Robust and certified quality assessment — image and video quality metrics that withstand adversarial attacks, including certified defenses (FS-IQA, Stochastic BIQA), adversarial training (BiRQA), and robustness-by-design architectures.
Adversarial attacks and defenses — transferable image-to-video attacks on quality metrics, benchmarking defenses (ICML 2025), and anti-forensics attacks on image forgery detection.
Trusted GenAI — watermarking of AI-generated images: benchmarking (WIBE, ASE 2025) and attacks on watermarking schemes.
Neural compression — robustness of learned image codecs (NIC-RobustBench, JPEG AI), compression of multimodal LLMs, and datasets for compressed video quality assessment (LEHA-CVQAD).

Expertise in applying ML/AI techniques to real-world challenges, with contributions adopted by industry leaders such as Google and NETFLIX.

news

Sep 22, 2026	Spent two weeks in Shenzhen at our summer school "Multimodal Intelligence and AI Security" — the team I mentored won with an adversarial patch attack on a smart camera! 🏆
Mar 21, 2026	Presented our paper “From Pixels to Reality: Physical-Digital Patch Attacks on Real-World Camera” as a demo at IEEE International Conference on Pervasive Computing and Communications (PerCom 2026) in Pisa, Italy!
Nov 21, 2025	I was honored to receive the National “Leaders of AI” Award for top-3 young scientific leaders in Russia! 🥳 This award is given to young researchers (under 35) for breakthrough AI solutions, specifically focusing on those publishing at top-tier conferences. More about the award and the other winners here: https://ai-awards.ru/award/scientist.
Nov 19, 2025	Presented our paper about WIBE framework for image watermarking robustness evaluation as a demo at IEEE/ACM International Conference on Automated Software Engineering (ASE 2025) in Seoul, South Korea!
Nov 02, 2025	Our paper about LEHA-CVQAD dataset for video quality measurement was presented by my PhD student Aleksandr Guschin at ACM International Conference on Multimedia (ACM MM 2025) in Dublin, Ireland!

selected publications

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

Alexander Gushchin, Khaled Abud, Georgii Bychkov, and 7 more authors

In Forty-second International Conference on Machine Learning, 2025

Abs Bib HTML

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.
@inproceedings{antsiferovaGuardians2024, title = {{Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics}}, author = {Gushchin, Alexander and Abud, Khaled and Bychkov, Georgii and Shumitskaya, Ekaterina and Chistyakova, Anna and Lavrushkin, Sergey and Rasheed, Bader and Malyshev, Kirill and Vatolin, Dmitriy and Antsiferova, Anastasia}, year = {2025}, booktitle = {Forty-second International Conference on Machine Learning}, }
AAAI
Comparing the robustness of modern no-reference image-and video-quality metrics to adversarial attacks

Anastasia Antsiferova, Khaled Abud, Aleksandr Gushchin, and 3 more authors

In Proceedings of the AAAI Conference on Artificial Intelligence, 2024

Abs Bib HTML

Nowadays neural-network-based image- and video-quality metrics show better performance compared to traditional methods. However, they also became more vulnerable to adversarial attacks that increase metrics’ scores without improving visual quality. The existing benchmarks of quality metrics compare their performance in terms of correlation with subjective quality and calculation time. However, the adversarial robustness of image-quality metrics is also an area worth researching. In this paper, we analyse modern metrics’ robustness to different adversarial attacks. We adopted adversarial attacks from computer vision tasks and compared attacks’ efficiency against 15 no-reference image/video-quality metrics. Some metrics showed high resistance to adversarial attacks which makes their usage in benchmarks safer than vulnerable metrics. The benchmark accepts new metrics submissions for researchers who want to make their metrics more robust to attacks or to find such metrics for their needs. Try our benchmark using pip install robustness-benchmark.
@inproceedings{vatolinComparing2024, title = {{Comparing the robustness of modern no-reference image-and video-quality metrics to adversarial attacks}}, author = {Antsiferova, Anastasia and Abud, Khaled and Gushchin, Aleksandr and Shumitskaya, Ekaterina and Lavrushkin, Sergey and Vatolin, Dmitriy}, year = {2024}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, }
NeurIPS
Video compression dataset and benchmark of learning-based video-quality metrics

Anastasia Antsiferova, Sergey Lavrushkin, Maksim Smirnov, and 3 more authors

In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2022

Abs Bib HTML

Video-quality measurement is a critical task in video processing. Nowadays, many implementations of new encoding standards-such as AV1, VVC, and LCEVC-use deep-learning-based decoding algorithms with perceptual metrics that serve as optimization objectives. But investigations of the performance of modern video-and image-quality metrics commonly employ videos compressed using older standards, such as AVC. In this paper, we present a new benchmark for video-quality metrics that evaluates video compression. It is based on a new dataset consisting of about 2,500 streams encoded using different standards, including AVC, HEVC, AV1, VP9, and VVC. Subjective scores were collected using crowdsourced pairwise comparisons. The list of evaluated metrics includes recent ones based on machine learning and neural networks. The results demonstrate that new no-reference metrics exhibit high correlation with subjective quality and approach the capability of top full-reference metrics.
@inproceedings{kulikovVideo2022, title = {{Video compression dataset and benchmark of learning-based video-quality metrics}}, author = {Antsiferova, Anastasia and Lavrushkin, Sergey and Smirnov, Maksim and Gushchin, Aleksandr and Vatolin, Dmitriy and Kulikov, Dmitriy}, year = {2022}, booktitle = {Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track}, }