Elamur Research⌕
☰
home / authors / Ahmed Salem

Ahmed Salem

Ahmed Salem has 3 papers in our library, in 2023–2025, most of them on Language models & pretraining, Bias, fairness & safety; often with Boyang Zhang, Mark Russinovich, Michael Backes.

3 papers in our library · 2023–2025

OpenAlex · ORCID · h-index 14 · 33 works · 1,957 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 177 times in our library · ⭐ Paper Stars ranking: #5160

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢MicrosoftRedmond · United States2022–2025 · 7 paperscurrent🔬Helmholtz Center for Information SecuritySaarbrücken · Germany2018–2022 · 11 papers🎓Xidian UniversityXi'an · China2016–2018 · 7 papers🎓Future University HakodateHakodate · Japan2021–2024 · 3 papers

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.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksComputer Science · 3 worksSocial Sciences · 1 workSociology and Political Science · 1 workArts and Humanities · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 2 worksBias, fairness & safety · 2 works

 Works by year

2020s

20251 paper20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Analyzing Leakage of Personally Identifiable Information in Language Models (2023 · 252 citations)
    Fine-tuned language models can memorize and expose personal data. Many practitioners assume that NER-based scrubbing or differential privacy removes this risk, but that assumption has rarely been tested. Lukas et al. define three levels of PII leakage through black-box API access as formal security games. In…
  2. Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack (2024 · 71 citations)
    Safety-aligned LLMs are usually tested against single-turn jailbreaks. Those attacks tend to contain recognizable malicious text that input filters can block once the attack becomes known. The authors present Crescendo, a black-box attack that spreads the jailbreak across a conversation. It opens with a harmless…
  3. Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification (2025 · 29 citations)
    Most safety studies of LLM agents look for overtly harmful behaviour, such as stealing data or moving money.

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 177 times (of the 149,439 papers whose bibliographies we read); 57 citing papers with a page here →.

Updated

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