Publications (41)
DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices
Run Wang, Felix Juefei-Xu, Yihao Huang +4
With the recent advances in voice synthesis, AI-synthesized fake voices are indistinguishable to human ears and widely are applied to produce realistic and natural DeepFakes, exhib…
FlexMap: Generalized HD Map Construction from Flexible Camera Configurations
Run Wang, Chaoyi Zhou, Amir Salarpour +5
High-definition (HD) maps provide essential semantic information of road structures for autonomous driving systems, yet current HD map construction methods require calibrated multi…
BioTrain: Sub-MB, Sub-50mW On-Device Fine-Tuning for Edge-AI on Biosignals
Run Wang, Victor J. B. Jung, Philip Wiese +5
Biosignals exhibit substantial cross-subject and cross-session variability, inducing severe domain shifts that degrade post-deployment performance for small, edge-oriented AI model…
Towards a Robust Deep Neural Network in Texts: A Survey
Wenqi Wang, Run Wang, Lina Wang +2
Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, rese…
TrainDeeploy: Hardware-Accelerated Parameter-Efficient Fine-Tuning of Small Transformer Models at the Extreme Edge
Run Wang, Victor J. B. Jung, Philip Wiese +3
On-device tuning of deep neural networks enables long-term adaptation at the edge while preserving data privacy. However, the high computational and memory demands of backpropagati…
GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning
Qiannan Wang, Changchun Yin, Zhe Liu +3
Within the realm of computer vision, self-supervised learning (SSL) pertains to training pre-trained image encoders utilizing a substantial quantity of unlabeled images. Pre-traine…
Prediction of the Yield of Enzymatic Synthesis of Betulinic Acid Ester Using Artificial Neural Networks and Support Vector Machine
Run Wang, Qiaoli Mo, Qian Zhang +2
3\b{eta}-O-phthalic ester of betulinic acid is of great importance in anticancer studies. However, the optimization of its reaction conditions requires a large number of experiment…
Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
Yuyang Zhang, Xinyuan Han, Xudong Jiang +1
Large language model agents increasingly rely on Skills to encode procedural knowledge, yet high-quality Skills remain costly to hand-write. This paper studies automatic Skill cons…
Hard Adversarial Example Mining for Improving Robust Fairness
Chenhao Lin, Xiang Ji, Yulong Yang +4
Adversarial training (AT) is widely considered the state-of-the-art technique for improving the robustness of deep neural networks (DNNs) against adversarial examples (AE). Neverth…
Ridge partial correlation screening for ultrahigh-dimensional data
Run Wang, An Nguyen, Somak Dutta +1
Variable selection in ultrahigh-dimensional linear regression is challenging due to its high computational cost. Therefore, a screening step is usually conducted before variable se…
Perception-guided Jailbreak against Text-to-Image Models
Yihao Huang, Le Liang, Tianlin Li +5
In recent years, Text-to-Image (T2I) models have garnered significant attention due to their remarkable advancements. However, security concerns have emerged due to their potential…
Countering Malicious DeepFakes: Survey, Battleground, and Horizon
Felix Juefei-Xu, Run Wang, Yihao Huang +3
The creation or manipulation of facial appearance through deep generative approaches, known as DeepFake, have achieved significant progress and promoted a wide range of benign and…
Amora: Black-box Adversarial Morphing Attack
Run Wang, Felix Juefei-Xu, Qing Guo +4
Nowadays, digital facial content manipulation has become ubiquitous and realistic with the success of generative adversarial networks (GANs), making face recognition (FR) systems s…
Torsional refrigeration by twisted, coiled, and supercoiled fibers
Run Wang, Shaoli Fang, Yicheng Xiao +27
Higher efficiency, lower cost refrigeration is needed for both large and small scale cooling. Refrigerators using entropy changes during cycles of stretching or hydrostatically com…
Offload Rethinking by Cloud Assistance for Efficient Environmental Sound Recognition on LPWANs
Le Zhang, Quanling Zhao, Run Wang +4
Learning-based environmental sound recognition has emerged as a crucial method for ultra-low-power environmental monitoring in biological research and city-scale sensing systems. T…
Maximizing the Smallest Eigenvalue of Grounded Laplacian Matrix
Run Wang, Xiaotian Zhou, Wei Li +1
For a connected graph with nodes, edges, and Laplacian matrix , a grounded Laplacian matrix of $\m…
Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection
Ziyou Liang, Weifeng Liu, Run Wang +5
In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that reli…
VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers
Run Wang, Gamze Islamoglu, Andrea Belano +4
While Transformers are dominated by Floating-Point (FP) Matrix-Multiplications, their aggressive acceleration through dedicated hardware or many-core programmable systems has shift…
FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views
Chaoyi Zhou, Run Wang, Feng Luo +4
Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches treat these capabilities in…
Bayesian iterative screening in ultra-high dimensional linear regressions
Run Wang, Somak Dutta, Vivekananda Roy
Variable selection in ultra-high dimensional linear regression is often preceded by a screening step to significantly reduce the dimension. Here we develop a Bayesian variable scre…
What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network
Ziheng Huang, Boheng Li, Yan Cai +5
In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis. However, well-trained GANs are under the threat of…
FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking
Run Wang, Felix Juefei-Xu, Meng Luo +2
In recent years, DeepFake is becoming a common threat to our society, due to the remarkable progress of generative adversarial networks (GAN) in image synthesis. Unfortunately, exi…
Text Modality Oriented Image Feature Extraction for Detecting Diffusion-based DeepFake
Di Yang, Yihao Huang, Qing Guo +5
The widespread use of diffusion methods enables the creation of highly realistic images on demand, thereby posing significant risks to the integrity and safety of online informatio…
Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
Weifeng Liu, Tianyi She, Jiawei Liu +4
In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, but these methods also pose potential and severe security threats to humani…
Fingerprinting Image-to-Image Generative Adversarial Networks
Guanlin Li, Guowen Xu, Han Qiu +5
Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human…
Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations
Run Wang, Ziheng Huang, Zhikai Chen +3
DeepFake is becoming a real risk to society and brings potential threats to both individual privacy and political security due to the DeepFaked multimedia are realistic and convinc…
Adversarial Prompts for Acceptance Collapse in Speculative Decoding
Run Wang, Chaoyi Zhou, Xi Liu +7
Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model.…
DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
Boheng Li, Junjie Wang, Yiming Li +7
Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or viole…
Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
Boheng Li, Yanhao Wei, Yankai Fu +5
Text-to-image diffusion models are pushing the boundaries of what generative AI can achieve in our lives. Beyond their ability to generate general images, new personalization techn…
FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
Run Wang, Felix Juefei-Xu, Lei Ma +4
In recent years, generative adversarial networks (GANs) and its variants have achieved unprecedented success in image synthesis. They are widely adopted in synthesizing facial imag…
FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
Yihao Huang, Felix Juefei-Xu, Run Wang +7
At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image.…
Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
Boheng Li, Renjie Gu, Junjie Wang +5
Text-to-image (T2I) diffusion models have achieved impressive image generation quality and are increasingly fine-tuned for personalized applications. However, these models often in…
Free Fine-tuning: A Plug-and-Play Watermarking Scheme for Deep Neural Networks
Run Wang, Jixing Ren, Boheng Li +6
Watermarking has been widely adopted for protecting the intellectual property (IP) of Deep Neural Networks (DNN) to defend the unauthorized distribution. Unfortunately, the popular…
A note on marginal correlation based screening
Run Wang, Somak Dutta, Vivekananda Roy
Independence screening methods such as the two sample -test and the marginal correlation based ranking are among the most widely used techniques for variable selection in ultrah…
Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain
Xuanhua He, Tao Hu, Guoli Wang +9
RAW to sRGB mapping, which aims to convert RAW images from smartphones into RGB form equivalent to that of Digital Single-Lens Reflex (DSLR) cameras, has become an important area o…
Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning
Qiaoyi Yang, Chaoyi Zhou, Xi Liu +9
Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and large-scale geographic mappin…
SSL-Auth: An Authentication Framework by Fragile Watermarking for Pre-trained Encoders in Self-supervised Learning
Xiaobei Li, Changchun Yin, Liyue Zhu +4
Self-supervised learning (SSL), a paradigm harnessing unlabeled datasets to train robust encoders, has recently witnessed substantial success. These encoders serve as pivotal featu…
MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models
Xi Ye, Yiwen Liu, Lina Wang +4
Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and conce…
A Minimal Dynamical Model for Incubation-Outbreak Transitions in Social Norm Diffusion
Run Wang, Leonardo Cianfanelli, Giacomo Como +1
In this paper, we introduce a minimal dynamical model for the diffusion of a new social norm, in which individuals transition among three states: non-supporters, silent supporters,…
A Survey of Causal Inference Frameworks
Jingying Zeng, Run Wang
Causal inference is a science with multi-disciplinary evolution and applications. On the one hand, it measures effects of treatments in observational data based on experimental des…
Towards Action Hijacking of Large Language Model-based Agent
Yuyang Zhang, Kangjie Chen, Jiaxin Gao +4
Recently, applications powered by Large Language Models (LLMs) have made significant strides in tackling complex tasks. By harnessing the advanced reasoning capabilities and extens…