2 citations · 5 across the 10 of their papers we have counts for
7 papers · 1 filter
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
Sijia Liu, Yicheng Lang, Soumyadeep Pal +6
Zeroth-order (ZO) optimization, learning from finite differences of function evaluations without backpropagation, has recently regained attention in deep learning due to its memory…
Leak@: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
Hadi Reisizadeh, Jiajun Ruan, Yiwei Chen +3
Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or cop…
LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
Chongyu Fan, Changsheng Wang, Yancheng Huang +2
Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model…
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
Yiwei Chen, Soumyadeep Pal, Yimeng Zhang +2
Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while…
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
Changsheng Wang, Yihua Zhang, Jinghan Jia +6
Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. H…
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
Soumyadeep Pal, Yuguang Yao, Ren Wang +2
Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisonin…
Towards Understanding How Self-training Tolerates Data Backdoor Poisoning
Soumyadeep Pal, Ren Wang, Yuguang Yao +1
Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poison…