5 citations · 8 across the 8 of their papers we have counts for
8 papers
Backdooring Masked Diffusion Language Models
Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou +3
Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdo…
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
Chengyu Huang, Sheng-Yen Chou, Zhengxin Zhang +1
Self-play has recently emerged as a promising paradigm for post-training Large Language Models (LLMs). In self-play, the target LLM creates the task input (e.g., a question), which…
Token-weighted Direct Preference Optimization with Attention
Chengyu Huang, Zhuohang Li, Sheng-Yen Chou +1
Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses e…
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang +8
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training. However,…
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
Ming-Yu Chung, Sheng-Yen Chou, Chia-Mu Yu +3
Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original tr…
VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
Sheng-Yen Chou, Pin-Yu Chen, Tsung-Yi Ho
Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many…
How to Backdoor Diffusion Models?
Sheng-Yen Chou, Pin-Yu Chen, Tsung-Yi Ho
Diffusion models are state-of-the-art deep learning empowered generative models that are trained based on the principle of learning forward and reverse diffusion processes via prog…
Single-level Adversarial Data Synthesis based on Neural Tangent Kernels
Yu-Rong Zhang, Ruei-Yang Su, Sheng Yen Chou +1
Abstract Generative adversarial networks (GANs) have achieved impressive performance in data synthesis and have driven the development of many applications. However, GANs are known…