3 citations · 5 across the 8 of their papers we have counts for
5 papers · 1 filter
Can Native Safety Travel? Reusing Safety Pretraining Across Models via On-Policy Distillation
Bingqi Shang, Yang Zhang, Yiwei Chen +4
Safety pretraining has emerged as a promising paradigm for embedding safety deeply into a model during pretraining, yielding robustness to subsequent fine-tuning that conventional…
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
Bingqi Shang, Yiwei Chen, Yihua Zhang +2
Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while retaining their general utility. Yet, with…
One Small Step with Fingerprints, One Giant Leap for De Novo Molecule Generation from Mass Spectra
Neng Kai Nigel Neo, Lim Jing, Ngoui Yong Zhau Preston +2
A common approach to the de novo molecular generation problem from mass spectra involves a two-stage pipeline: (1) encoding mass spectra into molecular fingerprints, followed by (2…
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…
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
Zhuoshi Pan, Yuguang Yao, Gaowen Liu +4
While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisonin…