arXiv subjects

Dake Chen

Publications and source records attributed to Dake Chen.

12 recordsLinked to original sources

arXiv2026

Scaling Muon for Diffusion Transformers

The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end efficiency on large Diffusion Transformers (DiTs) remain unclear. We first establish Muon's scaling behavior on DiTs from 1.3B to 15B parameters, showing that its optimization and generative quality advantages over AdamW persist across model scales. However, at scale, the 5-step Newton--Schulz iteration (NS5) performed at every optimization step, together with full-momentum materialization, introduces substantial computation and communication overhead that can offset Muon's step-efficiency advantage. We introduce \emph{Periodic Row-wise Muon}, which performs a full NS5 spectral update once every \(K\) steps and applies a low compute and communication cost row-wise constrained update based on the current momentum at the remaining steps. We further co-design a distributed implementation that operates directly on sharded momentum during non-refresh steps and accelerates spectral refreshes through bucketed all-gather and communication--computation overlap. Across all scales, Muon improves the best observed generative quality over AdamW by 12.9--19.1\%. Compared with vanilla Muon, Periodic Row-wise Muon remains within 0.5\% in best generative quality on the 1.3B--4B models and improves it by 4.5\% at 9B. It reduces optimizer time by 46.9--54.3\%, end-to-end step time by 15.7--24.3\%, and logical communication volume by 66.7\%, while reaching its respective best generative quality with 33.7--64.8\% less active training time. These results show that Periodic Row-wise Muon preserves Muon's generative quality advantage while translating it into end-to-end training efficiency for large DiTs.

cs.LG↗

arXiv2026

Global kilometre-scale tropical cyclone inner-core vector winds from sparse scalar CYGNSS observations

Tropical cyclone (TC) inner-core surface wind vectors underpin intensity forecasting and storm-surge prediction, yet direct observations remain scarce: routine aircraft reconnaissance is confined to the North Atlantic and Eastern Pacific and, even there, samples each storm only episodically. CYGNSS is the only satellite that penetrates heavy precipitation to measure inner-core surface winds, but delivers directionless scalar wind speeds and is assimilated by no operational analysis system. Here we show that the full 10 m vector wind field inside the TC inner core can be reconstructed globally at 1.5 km resolution from sparse CYGNSS scalar observations alone, by generalising score-based diffusion assimilation to a nonlinear observation operator and injecting three TC boundary-layer constraints; we further propose a CYGNSS-intrinsic Observation Coverage Sufficiency (OCS) criterion that flags reliable reconstructions without external references. Applied to 4,955 snapshots of 249 TCs across all six active basins (2020-2022), the reconstructions reduce systematic Vmax bias against IBTrACS best-track by ~79% and ~75% relative to ERA5 and CCMP. Independent Tail Doppler Radar validation (47 storms) yields a wind speed RMSE of 6.9 m/s on the 23 coverage-sufficient cases (7.5 m/s overall); ablation across the full sample shows that the physical constraints cut wind-direction RMSE by 60% without degrading speed accuracy. The framework further supports joint assimilation of heterogeneous observations: adding only 11 dropsonde vectors to CYGNSS for TC FIONA (2022) reduces the cross-eye profile RMSE by 42%, outlining a practical pathway for fusing CYGNSS with SFMR, SAR and scatterometer data. The result is a globally consistent, observation-anchored kilometre-scale description of TC inner-core vector winds across all six active basins, including those without routine aircraft reconnaissance.

physics.ao-ph↗

arXiv2024

LoyalDiffusion: A Diffusion Model Guarding Against Data Replication

Diffusion models have demonstrated significant potential in image generation. However, their ability to replicate training data presents a privacy risk, particularly when the training data includes confidential information. Existing mitigation strategies primarily focus on augmenting the training dataset, leaving the impact of diffusion model architecture under explored. In this paper, we address this gap by examining and mitigating the impact of the model structure, specifically the skip connections in the diffusion model's U-Net model. We first present our observation on a trade-off in the skip connections. While they enhance image generation quality, they also reinforce the memorization of training data, increasing the risk of replication. To address this, we propose a replication-aware U-Net (RAU-Net) architecture that incorporates information transfer blocks into skip connections that are less essential for image quality. Recognizing the potential impact of RAU-Net on generation quality, we further investigate and identify specific timesteps during which the impact on memorization is most pronounced. By applying RAU-Net selectively at these critical timesteps, we couple our novel diffusion model with a targeted training and inference strategy, forming a framework we refer to as LoyalDiffusion. Extensive experiments demonstrate that LoyalDiffusion outperforms the state-of-the-art replication mitigation method achieving a 48.63% reduction in replication while maintaining comparable image quality.

cs.CV↗

arXiv2024

Quantitative causality, causality-guided scientific discovery, and causal machine learning

It has been said, arguably, that causality analysis should pave a promising way to interpretable deep learning and generalization. Incorporation of causality into artificial intelligence (AI) algorithms, however, is challenged with its vagueness, non-quantitiveness, computational inefficiency, etc. During the past 18 years, these challenges have been essentially resolved, with the establishment of a rigorous formalism of causality analysis initially motivated from atmospheric predictability. This not only opens a new field in the atmosphere-ocean science, namely, information flow, but also has led to scientific discoveries in other disciplines, such as quantum mechanics, neuroscience, financial economics, etc., through various applications. This note provides a brief review of the decade-long effort, including a list of major theoretical results, a sketch of the causal deep learning framework, and some representative real-world applications in geoscience pertaining to this journal, such as those on the anthropogenic cause of global warming, the decadal prediction of El Ni\~no Modoki, the forecasting of an extreme drought in China, among others.

cs.AI↗

arXiv2023

GameGPT: Multi-agent Collaborative Framework for Game Development

The large language model (LLM) based agents have demonstrated their capacity to automate and expedite software development processes. In this paper, we focus on game development and propose a multi-agent collaborative framework, dubbed GameGPT, to automate game development. While many studies have pinpointed hallucination as a primary roadblock for deploying LLMs in production, we identify another concern: redundancy. Our framework presents a series of methods to mitigate both concerns. These methods include dual collaboration and layered approaches with several in-house lexicons, to mitigate the hallucination and redundancy in the planning, task identification, and implementation phases. Furthermore, a decoupling approach is also introduced to achieve code generation with better precision.

cs.AI↗

arXiv2023

Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement

While diffusion models demonstrate a remarkable capability for generating high-quality images, their tendency to `replicate' training data raises privacy concerns. Although recent research suggests that this replication may stem from the insufficient generalization of training data captions and duplication of training images, effective mitigation strategies remain elusive. To address this gap, our paper first introduces a generality score that measures the caption generality and employ large language model (LLM) to generalize training captions. Subsequently, we leverage generalized captions and propose a novel dual fusion enhancement approach to mitigate the replication of diffusion models. Our empirical results demonstrate that our proposed methods can significantly reduce replication by 43.5% compared to the original diffusion model while maintaining the diversity and quality of generations. Code is available at https://github.com/HowardLi0816/dual-fusion-diffusion.

cs.CV↗

arXiv2023

Island-based Random Dynamic Voltage Scaling vs ML-Enhanced Power Side-Channel Attacks

In this paper, we describe and analyze an island-based random dynamic voltage scaling (iRDVS) approach to thwart power side-channel attacks. We first analyze the impact of the number of independent voltage islands on the resulting signal-to-noise ratio and trace misalignment. As part of our analysis of misalignment, we propose a novel unsupervised machine learning (ML) based attack that is effective on systems with three or fewer independent voltages. Our results show that iRDVS with four voltage islands, however, cannot be broken with 200k encryption traces, suggesting that iRDVS can be effective. We finish the talk by describing an iRDVS test chip in a 12nm FinFet process that incorporates three variants of an AES-256 accelerator, all originating from the same RTL. This included a synchronous core, an asynchronous core with no protection, and a core employing the iRDVS technique using asynchronous logic. Lab measurements from the chips indicated that both unprotected variants failed the test vector leakage assessment (TVLA) security metric test, while the iRDVS was proven secure in a variety of configurations.

cs.CR↗

arXiv2023

Unraveling Latch Locking Using Machine Learning, Boolean Analysis, and ILP

Logic locking has become a promising approach to provide hardware security in the face of a possibly insecure fabrication supply chain. While many techniques have focused on locking combinational logic (CL), an alternative latch-locking approach in which the sequential elements are locked has also gained significant attention. Latch (LAT) locking duplicates a subset of the flip-flops (FF) of a design, retimes these FFs and replaces them with latches, and adds two types of decoy latches to obfuscate the netlist. It then adds control circuitry (CC) such that all latches must be correctly keyed for the circuit to function correctly. This paper presents a two-phase attack on latch-locked circuits that uses a novel combination of deep learning, Boolean analysis, and integer linear programming (ILP). The attack requires access to the reverse-engineered netlist but, unlike SAT attacks, is oracle-less, not needing access to the unlocked circuit or correct input/output pairs. We trained and evaluated the attack using the ISCAS'89 and ITC'99 benchmark circuits. The attack successfully identifies a key that is, on average, 96.9% accurate and fully discloses the correct functionality in 8 of the tested 19 circuits and leads to low function corruptibility (less than 4%) in 3 additional circuits. The attack run-times are manageable.

cs.CR↗

arXiv2023

C2PI: An Efficient Crypto-Clear Two-Party Neural Network Private Inference

Recently, private inference (PI) has addressed the rising concern over data and model privacy in machine learning inference as a service. However, existing PI frameworks suffer from high computational and communication costs due to the expensive multi-party computation (MPC) protocols. Existing literature has developed lighter MPC protocols to yield more efficient PI schemes. We, in contrast, propose to lighten them by introducing an empirically-defined privacy evaluation. To that end, we reformulate the threat model of PI and use inference data privacy attacks (IDPAs) to evaluate data privacy. We then present an enhanced IDPA, named distillation-based inverse-network attack (DINA), for improved privacy evaluation. Finally, we leverage the findings from DINA and propose C2PI, a two-party PI framework presenting an efficient partitioning of the neural network model and requiring only the initial few layers to be performed with MPC protocols. Based on our experimental evaluations, relaxing the formal data privacy guarantees C2PI can speed up existing PI frameworks, including Delphi [1] and Cheetah [2], up to 2.89x and 3.88x under LAN and WAN settings, respectively, and save up to 2.75x communication costs.

cs.CR↗

arXiv2023

Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference

Large number of ReLU and MAC operations of Deep neural networks make them ill-suited for latency and compute-efficient private inference. In this paper, we present a model optimization method that allows a model to learn to be shallow. In particular, we leverage the ReLU sensitivity of a convolutional block to remove a ReLU layer and merge its succeeding and preceding convolution layers to a shallow block. Unlike existing ReLU reduction methods, our joint reduction method can yield models with improved reduction of both ReLUs and linear operations by up to 1.73x and 1.47x, respectively, evaluated with ResNet18 on CIFAR-100 without any significant accuracy-drop.

cs.LG↗

arXiv2021

Fun-SAT: Functional Corruptibility-Guided SAT-Based Attack on Sequential Logic Encryption

The SAT attack has shown to be efficient against most combinational logic encryption methods. It can be extended to attack sequential logic encryption techniques by leveraging circuit unrolling and model checking methods. However, with no guidance on the number of times that a circuit needs to be unrolled to find the correct key, the attack tends to solve many time-consuming Boolean satisfiability (SAT) and model checking problems, which can significantly hamper its efficiency. In this paper, we introduce Fun-SAT, a functional corruptibility-guided SAT-based attack that can significantly decrease the SAT solving and model checking time of a SAT-based attack on sequential encryption by efficiently estimating the minimum required number of circuit unrollings. Fun-SAT relies on a notion of functional corruptibility for encrypted sequential circuits and its relationship with the required number of circuit unrollings in a SAT-based attack. Numerical results show that Fun-SAT can be, on average, 90x faster than previous attacks against state-of-the-art encryption methods, when both attacks successfully complete before a one-day time-out. Moreover, Fun-SAT completes before the time-out on many more circuits.

cs.CR↗

arXiv2021

GF-Flush: A GF(2) Algebraic Attack on Secure Scan Chains

Scan chains provide increased controllability and observability for testing digital circuits. The increased testability, however, can also be a source of information leakage for sensitive designs. The state-of-the-art defenses to secure scan chains apply dynamic keys to pseudo-randomly invert the scan vectors. In this paper, we pinpoint an algebraic vulnerability of these dynamic defenses that involves creating and solving a system of linear equations over the finite field GF(2). In particular, we propose a novel GF(2)-based flush attack that breaks even the most rigorous version of state-of-the-art dynamic defenses. Our experimental results demonstrate that our attack recovers the key as long as 500 bits in less than 7 seconds, the attack times are about one hundredth of state-of-the-art SAT based attacks on the same defenses. We then demonstrate how our attacks can be extended to scan chains compressed with Multiple-Input Signature Registers (MISRs).

cs.CR↗