🧑‍🔬 Micah Goldblum

🏛️ Affiliations

🎓Columbia UniversityNew York · United States2024–2026 · 18 paperscurrent🔬Lawrence Livermore National LaboratoryLivermore · United States2026 · 1 papercurrent🎓University of Illinois Urbana-ChampaignUrbana · United States2026 · 1 papercurrent🎓New York UniversityNew York · United States2020–2024 · 30 papers🎓University of Maryland, College ParkCollege Park · United States2019–2023 · 27 papersEducation

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Baseline Defenses for Adversarial Attacks Against Aligned Language Models (2023 · 236 citations)
   Optimization-based jailbreaks, especially the universal, transferable suffix attack (GCG) of Zou et al. (2023), can automatically generate prompts that bypass the safety alignment of chat LLMs. These prompts can be crafted on open models and then used against API-only systems. The authors ask whether standard defense…
2. Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery (2023 · 141 citations)
   Prompts are the main way to steer large generative models. Readable ("hard") prompts are usually written by hand. Learned continuous ("soft") prompts are opaque, tied to a single model, and unusable through text-only APIs. The authors introduce PEZ, a gradient-based procedure that learns discrete token prompts. It…
3. Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text (2024 · 120 citations)
   The paper addresses how to tell machine-written text from human writing when no examples from the generating model are available.
4. On the Reliability of Watermarks for Large Language Models (2023 · 103 citations)
   Spotting machine-generated text helps limit spam, bot activity and contamination of future training data. Earlier watermark evaluations, however, mostly assumed the detector receives unmodified model output. This paper tests whether the green-list watermark of Kirchenbauer et al. (2023) survives realistic handling…

All works

8 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetMicah Goldblum et al.2020 · 361 citations
2. Baseline Defenses for Adversarial Attacks Against Aligned Language ModelsarXiv:2309.00614Neel Jain, Avi Schwarzschild, Yuxin Wen, et al.2023 · 236 citations
3. Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetGowthami Somepalli et al.2023 · 217 citations
4. Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and DiscoveryConference on Neural Information Processing Systems (NeurIPS)Yuxin Wen, Neel Jain, John Kirchenbauer, et al.2023 · 141 citations
5. Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated TextarXiv:2401.12070Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, et al.2024 · 120 citations
6. On the Reliability of Watermarks for Large Language ModelsarXiv:2306.04634John Kirchenbauer, Jonas Geiping, Yuxin Wen, et al.2023 · 103 citations
7. End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking ↗arXiv:2202.05826 · no summary yetArpit Bansal et al.2022 · 12 citations
8. Perspectives on the State and Future of Deep Learning - 2023 ↗arXiv (Cornell University) · no summary yetMicah Goldblum et al.2023 · 5 citations

🤝 Co-authors here

8 co-authors with a page, the most papers together first.

• Jonas Geiping ×4
• Tom Goldstein ×4
• Aniruddha Saha ×3
• John Kirchenbauer ×3
• Yuxin Wen ×3
• Avi Schwarzschild ×2
• Neel Jain ×2
• Kezhi Kong

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2023
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings
• IEEE Transactions on Pattern Analysis and Machine Intelligence

🔗 Cited by

Papers of our library cite their works 516 times (of the 149,439 papers whose bibliographies we read); 122 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/micah-goldblum/