Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips
arXiv preprint, 2024.
Zachary Coalson, Jeonghyun Woo, Shiyang Chen, Yu Sun, Lishan Yang, Prashant Nair, Bo Fang, and Sanghyun Hong.
Preprints
Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search
arXiv preprint, 2024.
Zachary Coalson, Huazheng Wang, Qingyun Wu, and Sanghyun Hong.
2023
BERT Lost Patience Won't Be Robust to Adversarial Slowdown
NeurIPS, 2023.
Zachary Coalson, Gabriel Ritter, Rakesh Bobba, Sanghyun Hong.