Avi Schwarzschild

956 total citations · 1 hit paper
6 papers, 204 citations indexed

About

Avi Schwarzschild is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Signal Processing. According to data from OpenAlex, Avi Schwarzschild has authored 6 papers receiving a total of 204 indexed citations (citations by other indexed papers that have themselves been cited), including 5 papers in Artificial Intelligence, 1 paper in Computer Vision and Pattern Recognition and 1 paper in Signal Processing. Recurrent topics in Avi Schwarzschild's work include Adversarial Robustness in Machine Learning (5 papers), Anomaly Detection Techniques and Applications (3 papers) and Domain Adaptation and Few-Shot Learning (2 papers). Avi Schwarzschild is often cited by papers focused on Adversarial Robustness in Machine Learning (5 papers), Anomaly Detection Techniques and Applications (3 papers) and Domain Adaptation and Few-Shot Learning (2 papers). Avi Schwarzschild collaborates with scholars based in United States and Germany. Avi Schwarzschild's co-authors include Tom Goldstein, Micah Goldblum, Aleksander Mądry, Dawn Song, Xinyun Chen, Bo Li, Dimitris Tsipras, Chulin Xie, Arpit Bansal and Soumyadip Sengupta and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, arXiv (Cornell University) and International Conference on Machine Learning.

In The Last Decade

Avi Schwarzschild

6 papers receiving 199 citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses

2022 134 citations Micah Goldblum, Dimitris Tsipras et al. IEEE Transactions on Pattern Analysis and Machine Intelligence profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Avi Schwarzschild United States	3	120	59	41	32	19	6	204
Emre Aksu Finland	7	67 0.6×	145 2.5×	63 1.5×	22 0.7×	4 0.2×	32	208
Jiayuan Mao China	8	110 0.9×	108 1.8×	7 0.2×	16 0.5×	10 0.5×	25	197
Mohammad Babaeizadeh United States	7	65 0.5×	56 0.9×	16 0.4×	16 0.5×	4 0.2×	10	128
Prafulla Dhariwal	3	92 0.8×	54 0.9×	16 0.4×	5 0.2×	9 0.5×	3	127
Difei Gao Singapore	8	139 1.2×	213 3.6×	17 0.4×	9 0.3×	6 0.3×	22	263
Pengyu Cheng China	7	123 1.0×	37 0.6×	37 0.9×	55 1.7×	20 1.1×	19	178
Khalid Chougdali Morocco	7	100 0.8×	56 0.9×	66 1.6×	106 3.3×	31 1.6×	59	198
Vadim Sheinin United States	7	95 0.8×	63 1.1×	25 0.6×	27 0.8×	33 1.7×	28	174
Ruohan Meng China	8	59 0.5×	210 3.6×	39 1.0×	19 0.6×	28 1.5×	16	291

Countries citing papers authored by Avi Schwarzschild

Since Specialization

Citations

This map shows the geographic impact of Avi Schwarzschild's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Avi Schwarzschild with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Avi Schwarzschild more than expected).

Fields of papers citing papers by Avi Schwarzschild

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Avi Schwarzschild. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Avi Schwarzschild. The network helps show where Avi Schwarzschild may publish in the future.

Co-authorship network of co-authors of Avi Schwarzschild

This figure shows the co-authorship network connecting the top 25 collaborators of Avi Schwarzschild. A scholar is included among the top collaborators of Avi Schwarzschild based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Avi Schwarzschild. Avi Schwarzschild is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

6 of 6 papers shown

1.

Schwarzschild, Avi, et al.. (2023). Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective. 662–678. 3 indexed citations

2.

Bansal, Arpit, Hongmin Chu, Avi Schwarzschild, et al.. (2023). Universal Guidance for Diffusion Models. 843–852. 62 indexed citations

3.

Goldblum, Micah, Dimitris Tsipras, Chulin Xie, et al.. (2022). Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses. IEEE Transactions on Pattern Analysis and Machine Intelligence. 45(2). 1563–1580. 134 indexed citations breakdown →

4.

Schwarzschild, Avi, Micah Goldblum, Arjun K. Gupta, John P. Dickerson, & Tom Goldstein. (2021). Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks. International Conference on Machine Learning. 9389–9398. 1 indexed citations

5.

Goldblum, Micah, Jonas Geiping, Avi Schwarzschild, Michael Moeller, & Tom Goldstein. (2020). Truth or backpropaganda? An empirical investigation of deep learning theory. International Conference on Learning Representations. 2 indexed citations

6.

Fowl, Liam, et al.. (2020). Headless Horseman: Adversarial Attacks on Transfer Learning Models. arXiv (Cornell University). 3087–3091. 2 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact