6 papers
Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
Zhichao Hou, Weizhi Gao, Xiaorui Liu
This work tackles a critical challenge in AI safety research under limited compute: given a fixed computation budget, how can one maximize the strength of iterative adversarial att…
Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
Weizhi Gao, Xiaorui Liu, Feiyi Wang +2
Large language models (LLMs) have demonstrated impressive performance in both research and real-world applications, but they still struggle with hallucination. Existing hallucinati…
Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization
Weizhi Gao, Zhichao Hou, Junqi Yin +3
Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-…
Boosting Adversarial Robustness and Generalization with Structural Prior
Zhichao Hou, Weizhi Gao, Hamid Krim +1
This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models. Specifically,…
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
Weizhi Gao, Zhichao Hou, Han Xu +1
Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Their certified robustness has gained inc…
ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
Zhichao Hou, Weizhi Gao, Yuchen Shen +2
Transformer-based architectures have dominated various areas of machine learning in recent years. In this paper, we introduce a novel robust attention mechanism designed to enhance…