🧑‍🔬 Prateek Mittal

🏛️ Affiliations

🎓Princeton UniversityPrinceton · United States2013–2026 · 149 papersEmployment since 2013 · Professorcurrent🎓University of Illinois Urbana-ChampaignUrbana · United States2007–2012 · 17 papersEducation until 2012🎓University of California, BerkeleyBerkeley · United States2011–2012 · 7 papers🎓Indian Institute of Technology GuwahatiGuwahati · India2006Education until 2006

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions 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. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! (2023 · 355 citations)
   Current safety alignment methods, such as instruction tuning and RLHF, constrain how a model behaves at inference time.
2. Visual Adversarial Examples Jailbreak Aligned Large Language Models (2023 · 240 citations)
   Adding image inputs to large language models creates new security risks. The authors argue that images are continuous and high-dimensional, which makes them much easier to manipulate adversarially than discrete text. Because these models can do so many things, a successful attack can do more than cause a…
3. Safety Alignment Should Be Made More Than Just a Few Tokens Deep (2024 · 97 citations)
   The paper asks why safety-aligned LLMs are so easy to break, whether through adversarial suffixes, prefilling, tweaked decoding parameters, or a few steps of fine-tuning.
4. Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications (2024 · 66 citations)
   Aligned LLMs can be jailbroken or lose their safeguards even after harmless fine-tuning. The authors ask whether this fragility can be traced to specific parts of the weights. Using the Llama2-chat family, they attribute behaviour to individual neurons and to low-rank components of weight matrices. They use two…
5. Red-Teaming NSFW Image Classifiers as Text-to-Image Safeguards (2026)
   This paper examines a weakness in NSFW image classifiers that act as output filters for text-to-image (T2I) generators.

All works

15 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. Analyzing Federated Learning through an Adversarial Lens ↗International Conference on Machine Learning · no summary yetArjun Nitin Bhagoji et al.2019 · 388 citations
2. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!arXiv:2310.03693Xiangyu Qi, Yi Zeng, Tinghao Xie, et al.2023 · 355 citations
3. Visual Adversarial Examples Jailbreak Aligned Large Language ModelsProceedings of the AAAI Conference on Artificial IntelligenceXiangyu Qi, Kaixuan Huang, Ashwinee Panda, et al.2023 · 240 citations
4. Evolution of social-attribute networks ↗Internet Measurement Conference · no summary yetNeil Zhenqiang Gong et al.2012 · 170 citations
5. Safety Alignment Should Be Made More Than Just a Few Tokens DeeparXiv:2406.05946Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, et al.2024 · 97 citations
6. Preserving Link Privacy in Social Network Based Systems ↗arXiv (Cornell University) · no summary yetPrateek Mittal, Charalampos Papamanthou, Dawn Xiaodong Song2012 · 91 citations
7. Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank ModificationsarXiv:2402.05162Boyi Wei, Kaixuan Huang, Yangsibo Huang, et al.2024 · 66 citations
8. Certifiably Robust RAG against Retrieval Corruption ↗IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · no summary yetChong Xiang et al.2024 · 39 citations
9. Evolution of Social-Attribute Networks: Measurements, Modeling, and Implications using Google+ ↗arXiv (Cornell University) · no summary yetNeil Zhenqiang Gong et al.2012 · 38 citations
10. New Directions in Social Authentication ↗no summary yetSakshi Jain et al.2015 · 7 citations
11. AI Risk Management Should Incorporate Both Safety and Security ↗arXiv (Cornell University) · no summary yetXiangyu Qi et al.2024 · 3 citations
12. ASPIRE: iterative specification synthesis for security ↗Workshop on Hot Topics in Operating Systems · no summary yetKevin Zhijie Chen et al.2015 · 3 citations
13. The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege ↗Proceedings of the AAAI/ACM Conference on AI Ethics and Society · no summary yetLuxi He et al.2025 · 1 citation
14. VFIX: Facilitating Software Maintenance of Smart Contracts via Automatically Fixing Vulnerabilities ↗IEEE International Conference on Software Maintenance and Evolution (ICSME) · no summary yetPengcheng Fang et al.2024 · 1 citation
15. Red-Teaming NSFW Image Classifiers as Text-to-Image SafeguardsFindings of the Association for Computational LinguisticsTinghao Xie, Yueqi Xie, Alireza Zareian, et al.2026

🤝 Co-authors here

12 of 16 co-authors with a page, the most papers together first.

• Peter Henderson ×4
• Xiangyu Qi ×4
• Tinghao Xie ×3
• Ashwinee Panda ×2
• Kaixuan Huang ×2
• Mengdi Wang ×2
• Boyi Wei
• Li Chen
• Mengzhou Xia
• Pin-Yu Chen
• Ruoxi Jia
• Xiao Ma

Venues

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

• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Proceedings of the AAAI Conference on Artificial Intelligence: Proceedings of the AAAI Conference on Artificial Intelligence 2023
• IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
• IEEE International Conference on Software Maintenance and Evolution (ICSME)
• International Conference on Machine Learning
• Internet Measurement Conference
• Proceedings of the AAAI/ACM Conference on AI Ethics and Society
• Workshop on Hot Topics in Operating Systems

🔗 Cited by

Papers of our library cite their works 700 times (of the 149,439 papers whose bibliographies we read); 155 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/prateek-mittal/