About

Hao Cheng, Ph.D., is an Associate Professor in the Department of Animal Science at the University of California, Davis. His research focuses on the development of statistical methods, computational algorithms, and software tools for quantitative and statistical genetics. His work includes comparative genomics and epigenomics of transcriptional regulation, microbiome-enabled genomic selection to improve prediction accuracy for nitrogen-related traits in maize, and interpreting genomic evaluations through neural network models. Dr. Cheng's contributions extend to collaborative genomic analyses that maintain data confidentiality and deciphering evolutionary mechanisms underlying gene expression and complex traits by learning functional conservation between humans and pigs.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Computer Security
• Engineering
• Transport engineering
• Mathematics
• Statistics

Selected publications

• Suppressing Gradient Conflict for Generalizable Deepfake Detection

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-01-01

  article

  Robust deepfake detection models must be capable of generalizing to ever-evolving manipulation techniques beyond training data. A promising strategy is to augment the training data with online synthesized fake images containing broadly generalizable artifacts. However, in the context of deepfake detection, it is surprising that jointly training on both original and online synthesized forgeries may result in degraded performance. This contradicts the common belief that incorporating more source-domain data should enhance detection accuracy. Through empirical analysis, we trace this degradation to gradient conflicts during backpropagation which force a trade-off between source domain accuracy and target domain generalization. To overcome this issue, we propose a Conflict-Suppressed Deepfake Detection (CS-DFD) framework that explicitly mitigates the gradient conflict via two synergistic modules. First, an Update Vector Search (UVS) module searches for an alternative update vector near the initial gradient vector to reconcile the disparities of the original and online synthesized forgeries. By further transforming the search process into an extremum optimization problem, UVS yields the uniquely update vector, which maximizes the simultaneous loss reductions for each data type. Second, a Conflict Gradient Reduction (CGR) module enforces a low-conflict feature embedding space through a novel Conflict Descent Loss. This loss penalizes misaligned gradient directions and guides the learning of representations with aligned, non-conflicting gradients. The synergy of UVS and CGR alleviates gradient interference in both parameter optimization and representation learning. Experiments on multiple deepfake benchmarks demonstrate that CS-DFD achieves state-of-the-art performance in both in-domain detection accuracy and cross-domain generalization.

  PublisherDOI

• ZSORN: Language-Driven Object-Centric Zero-Shot Object Retrieval and Navigation

  2025-05-19 · 4 citations

  article
  PublisherDOI

• Towards Generalizable Deepfake Detection by Primary Region Regularization

  ACM Transactions on Multimedia Computing Communications and Applications · 2025-11-19 · 1 citations

  article1st authorCorresponding

  The existing deepfake detection methods have reached a bottleneck in generalizing to unseen forgeries and manipulation approaches. Based on the observation that the deepfake detectors exhibit a preference for overfitting specific primary regions in input, this article enhances the generalization capability from a novel regularization perspective. This can be simply achieved by augmenting the images through primary region removal, thereby preventing the detector from over-relying on data bias. Our method consists of two stages, namely the static localization for primary region maps, as well as the dynamic exploitation of primary region masks. The proposed method can be seamlessly integrated into different backbones without affecting their inference efficiency. We conduct extensive experiments over five widely used deepfake datasets—DFDC, DF-1.0, Celeb-DF, WildDF, and FFIW with seven backbones. Our method demonstrates an average performance improvement of 6% across different backbones and performs competitively with several state-of-the-art baselines.

  PublisherDOI

• Mathebotics: Integrated Education on Mathematics With Computing and Robotics

  2025-08-17

  article1st authorCorresponding

  Abstract Mathebotics, the integration of mathematics with computing and robotics for hands-on, interdisciplinary learning, is presented in this article along with an effective implementation model called SHINE. The integrated Mathebotics approach aims not only to improve K-12 students’ mathematics achievement but also to enhance their communication, collaboration, and critical thinking skills. Furthermore, Mathebotics offers comprehensive computer science education for all K-12 students without requiring the addition of new courses. The UC Davis C-STEM program is used as a case study to illustrate how Mathebotics, combined with the SHINE learning model, can be successfully implemented in schools. By making mathematics learning fun, engaging, and playful, Mathebotics transforms students’ educational experiences. This article also discusses lessons learned, challenges encountered, opportunities identified, and priorities for future research in Mathebotics education.

  PublisherDOI

• Social Debiasing for Fair Multi-Modal LLMs

  2025-10-19

  preprintOpen access1st authorCorresponding

  Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models often inherit deep-rooted social biases from their training data, leading to uncomfortable responses with respect to attributes such as race and gender. This paper addresses the issue of social biases in MLLMs by i) introducing a comprehensive counterfactual dataset with multiple social concepts (CMSC), which complements existing datasets by providing 18 diverse and balanced social concepts; and ii) proposing a counter-stereotype debiasing (CSD) strategy that mitigates social biases in MLLMs by leveraging the opposites of prevalent stereotypes. CSD incorporates both a novel bias-aware data sampling method and a loss rescaling method, enabling the model to effectively reduce biases. We conduct extensive experiments with four prevalent MLLM architectures. The results demonstrate the advantage of the CMSC dataset and the edge of CSD strategy in reducing social biases compared to existing competing methods, without compromising the overall performance on general multi-modal reasoning benchmarks.

  PublisherOA PDFDOI

• FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks

  2025-10-25 · 5 citations

  preprintOpen access

  Proactive Deepfake detection via robust watermarks has seen interest ever since passive Deepfake detectors encountered challenges in identifying high-quality synthetic images. However, while demonstrating reasonable detection performance, they lack localization functionality and explainability in detection results. Additionally, the unstable robustness of watermarks can significantly affect the detection performance. In this study, we propose novel fractal watermarks for proactive Deepfake detection and localization, namely FractalForensics. Benefiting from the characteristics of fractals, we devise a parameter-driven watermark generation pipeline that derives fractal-based watermarks and performs one-way encryption of the selected parameters. Subsequently, we propose a semi-fragile watermarking framework for watermark embedding and recovery, trained to be robust against benign image processing operations and fragile when facing Deepfake manipulations in a black-box setting. Moreover, we introduce an entry-to-patch strategy that implicitly embeds the watermark matrix entries into image patches at corresponding positions, achieving localization of Deepfake manipulations. Extensive experiments demonstrate satisfactory robustness and fragility of our approach against common image processing operations and Deepfake manipulations, outperforming state-of-the-art semi-fragile watermarking algorithms and passive detectors for Deepfake detection. Furthermore, by highlighting the areas manipulated, our method provides explainability for the proactive Deepfake detection results.

  PublisherDOI

• Bridging the Intent Gap: Knowledge-Enhanced Visual Generation

  arXiv (Cornell University) · 2024-05-21

  preprintOpen access

  For visual content generation, discrepancies between user intentions and the generated content have been a longstanding problem. This discrepancy arises from two main factors. First, user intentions are inherently complex, with subtle details not fully captured by input prompts. The absence of such details makes it challenging for generative models to accurately reflect the intended meaning, leading to a mismatch between the desired and generated output. Second, generative models trained on visual-label pairs lack the comprehensive knowledge to accurately represent all aspects of the input data in their generated outputs. To address these challenges, we propose a knowledge-enhanced iterative refinement framework for visual content generation. We begin by analyzing and identifying the key challenges faced by existing generative models. Then, we introduce various knowledge sources, including human insights, pre-trained models, logic rules, and world knowledge, which can be leveraged to address these challenges. Furthermore, we propose a novel visual generation framework that incorporates a knowledge-based feedback module to iteratively refine the generation process. This module gradually improves the alignment between the generated content and user intentions. We demonstrate the efficacy of the proposed framework through preliminary results, highlighting the potential of knowledge-enhanced generative models for intention-aligned content generation.

  PublisherOA PDFDOI

• Diffusion Facial Forgery Detection

  2024-10-26 · 29 citations

  article1st authorCorresponding

  Detecting diffusion-generated images has recently developed as an emerging research area. Existing diffusion-based datasets predominantly focus on general image generation. However, facial forgeries, which pose severe social risks, have remained less explored thus far. To address this gap, this paper introduces DiFF, a comprehensive dataset dedicated to face-focused diffusion-generated images. DiFF comprises over 500,000 images that are synthesized using thirteen distinct generation methods under four conditions. In particular, this dataset utilizes 30,000 carefully collected textual and visual prompts, ensuring the synthesis of images with both high fidelity and semantic consistency. We conduct extensive experiments on the DiFF dataset via human subject tests and several representative forgery detection methods. The results demonstrate that the binary detection accuracies of both human observers and automated detectors often fall below 30%, revealing insights on the challenges in detecting diffusion-generated facial forgeries. Moreover, our experiments demonstrate that DiFF, compared to previous facial forgery datasets, contains a more diverse and realistic range of forgeries, showcasing its potential to aid in the development of more generalized detectors. Finally, we propose an edge graph regularization approach to effectively enhance the generalization capability of existing detectors.

  PublisherDOI

• LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks

  2024-10-26 · 19 citations

  preprintOpen access

  Deepfake facial manipulation has garnered significant public attention due to its impacts on enhancing human experiences and posing privacy threats. Despite numerous passive algorithms that have been attempted to thwart malicious Deepfake attacks, they mostly struggle with the generalizability challenge when confronted with hyper-realistic synthetic facial images. To tackle the problem, this paper proposes a proactive Deepfake detection approach by introducing a novel training-free landmark perceptual watermark, LampMark for short. We first analyze the structure-sensitive characteristics of Deepfake manipulations and devise a secure and confidential transformation pipeline from the structural representations, i.e. facial landmarks, to binary landmark perceptual watermarks. Subsequently, we present an end-to-end watermarking framework that imperceptibly and robustly embeds and extracts watermarks concerning the images to be protected. Relying on promising watermark recovery accuracies, Deepfake detection is accomplished by assessing the consistency between the content-matched landmark perceptual watermark and the robustly recovered watermark of the suspect image. Experimental results demonstrate the superior performance of our approach in watermark recovery and Deepfake detection compared to state-of-the-art methods across in-dataset, cross-dataset, and cross-manipulation scenarios.

  PublisherOA PDFDOI

• Diffusion Facial Forgery Detection

  arXiv (Cornell University) · 2024-01-29

  preprintOpen access1st authorCorresponding

  Detecting diffusion-generated images has recently grown into an emerging research area. Existing diffusion-based datasets predominantly focus on general image generation. However, facial forgeries, which pose a more severe social risk, have remained less explored thus far. To address this gap, this paper introduces DiFF, a comprehensive dataset dedicated to face-focused diffusion-generated images. DiFF comprises over 500,000 images that are synthesized using thirteen distinct generation methods under four conditions. In particular, this dataset leverages 30,000 carefully collected textual and visual prompts, ensuring the synthesis of images with both high fidelity and semantic consistency. We conduct extensive experiments on the DiFF dataset via a human test and several representative forgery detection methods. The results demonstrate that the binary detection accuracy of both human observers and automated detectors often falls below 30%, shedding light on the challenges in detecting diffusion-generated facial forgeries. Furthermore, we propose an edge graph regularization approach to effectively enhance the generalization capability of existing detectors.

  PublisherOA PDFDOI

Recent grants

• RET Site: Computing Research Experiences for STEM Teachers (CREST)

  NSF · $516k · 2011–2015

• EAGER: Collaborative Mathematics Learning with Robots

  NSF · $300k · 2012–2015

• NRI-Small: Co-Robots for STEM Education in the 21st Century

  NSF · $951k · 2012–2016

Frequent coauthors

• Joe Palen

  California Department of Transportation

  26 shared

• David Ko

  21 shared

• Stephen S. Nestinger

  Worcester Polytechnic Institute

  19 shared

• Liqiang Nie

  15 shared

• Yu‐Cheng Chou

  National Cheng Kung University Hospital

  14 shared

• Binsen Qian

  University of California, Davis

  14 shared

• Zhaoqing Wang

  12 shared

• Ben Shaw

  11 shared

Education

• Ph.d, School of Computer Science and Technology

  Shandong University

  2025

• M.S, School of Computer Science and Technology

  Shandong University

  2021