David Huang

david.huang [at] princeton [dot] edu
[scholar] [github] [linkedin]

I’m a researcher at Anthropic and a PhD student (on leave) at Princeton, advised by Prof. Prateek Mittal. I work on the safety and security of large language models.

Selected Publications

1. Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework
   ICML 2026 (Spotlight, top 2.2%)
   David Huang, Jaewon Chang, Avidan Shah, Prateek Mittal, Chawin Sitawarin
   pdf
2. Measuring General Intelligence with Generated Games
   Under submission, ICLR 2026
   Vivek Verma, David Huang, William Chen, Dan Klein, Nicholas Tomlin
   pdf code
3. Improving LLM Safety Alignment with Dual-Objective Optimization
   ICML 2025
   Xuandong Zhao*, Will Cai*, Tianneng Shi, David Huang, Licong Lin, Song Mei, Dawn Song
   pdf code
4. Stronger Universal and Transfer Attacks by Suppressing Refusals
   NAACL 2025
   David Huang, Avidan Shah, Alexandre Araujo, David Wagner, Chawin Sitawarin
   pdf video
5. Robo-DM: Data Management for Large Robot Datasets
   ICRA 2025 (Best Paper Award, Robot Learning)
   Kaiyuan Chen, Letian Fu, David Huang*, Yiming Zhang*, et al.
   pdf code
6. PubDef: Defending against Transfer Attacks from Public Models
   ICLR 2024
   Chawin Sitawarin, Jaewon Chang*, David Huang*, Wesson Altoyan, David Wagner
   pdf code site