Selected scholarly work.

1. 2026

   Attention Smoothing Is All You Need For Unlearning

   Zare Zade, S., Zhou, X., Liu, S., Zhu, D.

   International Conference on Learning Representations (ICLR), 2026

   Paper ↗
   Conference
2. 2026

   Not All Tokens Are Meant to Be Forgotten

   Zhou, X., Qiang, Y., Zare Zade, S., Zytko, D., Khanduri, P., Zhu, D.

   AAAI Conference on Artificial Intelligence (AAAI), 2026

   Paper ↗
   Conference
3. 2026

   Hijacking Large Language Models via Adversarial In-Context Learning

   Zhou, X., Qiang, Y., Zare Zade, S., Khanduri, P., Zhu, D.

   European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2026

   Paper ↗
   Conference
4. 2025

   Automatic Calibration for Membership Inference Attack on Large Language Models

   Zare Zade, S., Qiang, Y., Zhou, X., Zhu, H., Roshani, M. A., Khanduri, P., Zhu, D.

   European Conference on Artificial Intelligence (ECAI), 2025

   Paper ↗Code ↗
   Conference
5. 2026

   Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models

   Zhou, X., Zare Zade, S., Sultan, R. I., Kotov, A., Zhu, D.

   Under review at the Conference on Neural Information Processing Systems (NeurIPS), 2026

   Under review
6. 2027

   BOS Summary: The First Token Matters

   Zhu, H., Zare Zade, S., Sultan, R. I., Pan, D., Zhu, D.

   Under review at the AAAI Conference on Artificial Intelligence (AAAI), 2027

   Under review
7. 2027

   Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure

   Zhou, X., Zare Zade, S., Zhu, D.

   Under review at the AAAI Conference on Artificial Intelligence (AAAI), 2027

   Under review
8. 2026

   Learning to Poison Large Language Models for Downstream Manipulation

   Zhou, X., Qiang, Y., Zare Zade, S., Roshani, M. A., Khanduri, P., Zytko, D., Zhu, D.

   Under review at IEEE BigData, 2026.

   Paper ↗
   Under review

For citation records and updates, visit Google Scholar.