Zifan (Sail) Wang
Source-listed: Research Scientist · Meta
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Universal and Transferable Adversarial Attacks on Aligned Language ModelsSaved credit: Contributor · 2023Explore people connected to this work →
- Representation Engineering: A Top-Down Approach to AI TransparencySaved credit: Contributor · 2023Explore people connected to this work →
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust RefusalSaved credit: Contributor · 2024Explore people connected to this work →
- The WMDP Benchmark: Measuring and Reducing Malicious Use With UnlearningSaved credit: Contributor · 2024Explore people connected to this work →
- Reliable Weak-to-Strong Monitoring of LLM AgentsSaved credit: Contributor · 2025Explore people connected to this work →