arXiv subjects

Hai Zhou

Publications and source records attributed to Hai Zhou.

10 recordsLinked to original sources

arXiv2026

BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards

Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framework for commercial ads that fuses Chain-of-Thought reasoning with rule-based policy principles and a critic-guided reward. A rule-driven ICoT data-synthesis pipeline jump-starts training by generating structured scene descriptions, reasoning chains and labels, cutting annotation costs. Reinforcement learning then refines the model using a composite reward balancing causal coherence with policy adherence. A multitask architecture models intra-modal manipulations (e.g., exaggerated imagery) and cross-modal mismatches (e.g., subtitle-speech drift), boosting robustness. Experiments on real short-video ads show BLM-Guard surpasses strong baselines in accuracy, consistency and generalization.

cs.CV↗

arXiv2025

LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators

We introduce LLA, an effective intellectual property (IP) protection scheme for generative AI models. LLA leverages the synergy between hardware and software to defend against various supply chain threats, including model theft, model corruption, and information leakage. On the software side, it embeds key bits into neurons that can trigger outliers to degrade performance and applies invariance transformations to obscure the key values. On the hardware side, it integrates a lightweight locking module into the AI accelerator while maintaining compatibility with various dataflow patterns and toolchains. An accelerator with a pre-stored secret key acts as a license to access the model services provided by the IP owner. The evaluation results show that LLA can withstand a broad range of oracle-guided key optimization attacks, while incurring a minimal computational overhead of less than 0.1% for 7,168 key bits.

cs.CR↗

arXiv2025

Modeling Atmospheric Ion Escape from Kepler-1649 b and c over Time

Rocky planets orbiting M-dwarf stars are prime targets for atmospheric characterization, yet their long-term evolution under intense stellar winds and high-energy radiation remains poorly constrained. The Kepler-1649 system, hosting two terrestrial exoplanets orbiting an M5V star, provides a valuable laboratory for studying atmospheric evolution in the extreme environments typical of M-dwarf systems. In this Letter we show that both planets could have retained atmospheres over gigayear timescales. Using a multi-species magnetohydrodynamic model, we simulate atmospheric ion escape driven by stellar winds and extreme ultraviolet radiation from 0.8 to 4.0 Gyr. The results reveal a clear decline in total ion escape rates with stellar age, as captured by a nonparametric LOWESS regression, with O$^{+}$ comprising 98.3%-99.9% of the total loss. Escape rates at 4.0 Gyr are two to three orders of magnitude lower than during early epochs. At 0.8 Gyr, planet b exhibits 3.79$\times$ higher O$^{+}$ escape rates than planet c, whereas by 4.0 Gyr its O$^{+}$ escape rate becomes 39.5$\times$ lower. This reversal arises from a transition to sub-magnetosonic star-planet interactions, where the fast magnetosonic Mach number, $M_f$, falls below unity. Despite substantial early atmospheric erosion, both planets may have retained significant atmospheres, suggesting potential long-term habitability. These findings offer predictive insight into atmospheric retention in the Kepler-1649 system and inform future JWST observations of similar M-dwarf terrestrial exoplanets aimed at refining habitability assessments.

astro-ph.EP↗

arXiv2025

The Power of Graph Signal Processing for Chip Placement Acceleration

Placement is a critical task with high computation complexity in VLSI physical design. Modern analytical placers formulate the placement objective as a nonlinear optimization task, which suffers a long iteration time. To accelerate and enhance the placement process, recent studies have turned to deep learning-based approaches, particularly leveraging graph convolution networks (GCNs). However, learning-based placers require time- and data-consuming model training due to the complexity of circuit placement that involves large-scale cells and design-specific graph statistics. This paper proposes GiFt, a parameter-free technique for accelerating placement, rooted in graph signal processing. GiFt excels at capturing multi-resolution smooth signals of circuit graphs to generate optimized placement solutions without the need for time-consuming model training, and meanwhile significantly reduces the number of iterations required by analytical placers. Experimental results show that GiFt significantly improving placement efficiency, while achieving competitive or superior performance compared to state-of-the-art placers. In particular, compared to DREAMPlace, the recently proposed GPU-accelerated analytical placer, GF-Placer improves total runtime over 45%.

cs.LG↗

arXiv2024

Certifying Global Robustness for Deep Neural Networks

A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systematic and efficient method to evaluate and verify global robustness for deep neural networks, leveraging the PAC verification framework for solid guarantees on verification results. We utilize probabilistic programs to characterize meaningful input regions, setting a realistic standard for global robustness. Additionally, we introduce the cumulative robustness curve as a criterion in evaluating global robustness. We design a statistical method that combines multi-level splitting and regression analysis for the estimation, significantly reducing the execution time. Experimental results demonstrate the efficiency and effectiveness of our verification method and its capability to find rare and diversified counterexamples for adversarial training.

cs.LG↗

arXiv2022

Incentivizing Federated Learning

Federated Learning is an emerging distributed collaborative learning paradigm used by many of applications nowadays. The effectiveness of federated learning relies on clients' collective efforts and their willingness to contribute local data. However, due to privacy concerns and the costs of data collection and model training, clients may not always contribute all the data they possess, which would negatively affect the performance of the global model. This paper presents an incentive mechanism that encourages clients to contribute as much data as they can obtain. Unlike previous incentive mechanisms, our approach does not monetize data. Instead, we implicitly use model performance as a reward, i.e., significant contributors are paid off with better models. We theoretically prove that clients will use as much data as they can possibly possess to participate in federated learning under certain conditions with our incentive mechanism

cs.GT↗

arXiv2021

Multi-level Forwarding and Scheduling Recovery Algorithm in Rapidly-changing Network for Erasure-coded Clusters

A key design goal of erasure-coded clusters is to reduce the repair time. The existing Erasure-coded data repair schemes are roughly classified into two categories: 1. Designing rapid data repair (e.g., PPR) in a homogeneous environment. 2. Constructing data repair (e.g., PPT) based on bandwidth in a heterogeneous environment. However, these solutions are difficult to cope with the heterogeneous and Rapidly-changing network in erasure-coded clusters. To address this problem, a bandwidth-aware multi-level forwarding repair algorithm, called BMFRepair, is proposed. BMFRepair monitors the network bandwidth in real time when data is forwarded, and selects idle nodes with high-bandwidth links to assist in forwarding. Thus, it can reduce the time bottleneck caused by low link transmission. At the same time, multi-node repair becomes very complicated when the bandwidth changes drastically. A multi-node scheduling repairing algorithm, called MSRepair, is proposed for multi-node repairing problems, which can repair multiple failed blocks in parallel by scheduling node resources. The two algorithms can flexibly adapt to the rapidly changing network environment and make full use of the bandwidth resources of idle nodes. Most importantly, algorithms can continuously adjust the repair plan according to the bandwidth change in fast and dynamic network. The algorithms have been evaluated by both simulations on Mininet and real experiments on Aliyun cloud platform ECS. Results show that compared with the state-of-the-art repair schemes PPR and PPT, the algorithms can significantly reduce the repair time in rapidly-changing network.

cs.NI↗

arXiv2020

KNN-enhanced Deep Learning Against Noisy Labels

Supervised learning on Deep Neural Networks (DNNs) is data hungry. Optimizing performance of DNN in the presence of noisy labels has become of paramount importance since collecting a large dataset will usually bring in noisy labels. Inspired by the robustness of K-Nearest Neighbors (KNN) against data noise, in this work, we propose to apply deep KNN for label cleanup. Our approach leverages DNNs for feature extraction and KNN for ground-truth label inference. We iteratively train the neural network and update labels to simultaneously proceed towards higher label recovery rate and better classification performance. Experiment results show that under the same setting, our approach outperforms existing label correction methods and achieves better accuracy on multiple datasets, e.g.,76.78% on Clothing1M dataset.

cs.CV↗

arXiv2020

Benchmarking at the Frontier of Hardware Security: Lessons from Logic Locking

Integrated circuits (ICs) are the foundation of all computing systems. They comprise high-value hardware intellectual property (IP) that are at risk of piracy, reverse-engineering, and modifications while making their way through the geographically-distributed IC supply chain. On the frontier of hardware security are various design-for-trust techniques that claim to protect designs from untrusted entities across the design flow. Logic locking is one technique that promises protection from the gamut of threats in IC manufacturing. In this work, we perform a critical review of logic locking techniques in the literature, and expose several shortcomings. Taking inspiration from other cybersecurity competitions, we devise a community-led benchmarking exercise to address the evaluation deficiencies. In reflecting on this process, we shed new light on deficiencies in evaluation of logic locking and reveal important future directions. The lessons learned can guide future endeavors in other areas of hardware security.

cs.CR↗

arXiv2019

Generation of cylindrically symmetric modes and orbitalangular momentum modes with tilted optical gratings inscribed in high numerical aperture fibers

Optical fiber with high numerical aperture (NA) can efficiently relieve the degeneracy of higher order linearly polarized modes. The degeneracy relief is investigated in two types of high NA fibers, i.e., low index cladding fiber and high-index-core fiber. A naked core fiber, as with low index cladding, can be used theoretically to generate the orbital angular momentum mode (OAMM) HE21 and the cylindrically symmetric modes (CSMs) TM01 and TE01. A high index core fiber incorporated with high contrast index structure can be used similarly to obtain OAMM HE31. The generation of both CSMs and OAMMs required tilted optical gratings to couple the fundamental core mode HE11 into these modes. The tilt angle and modulation period of the grating fringes can be calculated simply and visually with the method proposed in this article.

physics.optics↗