arXiv subjects

Ximeng Liu

Publications and source records attributed to Ximeng Liu.

At least 19 recordsLinked to original sources

arXiv2026

Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets

LLM-driven program discovery relies on rapid evaluator feedback, but many scientific and engineering tasks require high-fidelity simulations, hardware execution, or physical experiments, making each evaluation expensive. Cheap surrogate evaluators can reduce this cost, yet fixed surrogates are vulnerable to search-induced distribution shift and are difficult to fit reliably from sparse, search-biased labels. We introduce Janus, a framework that uses LLMs to co-evolve target programs and executable proxy evaluators. To address label scarcity, Janus leverages domain knowledge encoded in LLMs to generate task-specific evaluator programs and calibrates them using real outcomes. To mitigate distribution shift, Janus evolves evaluators alongside target programs, selects them using a promotion-aligned objective, and maintains region-conditioned portfolios with online credit updates. Because proxy predictions remain fallible, Janus uses them only to prioritize candidates and requires real validation before candidates can enter the target-program population or update the incumbent. Across five scientific and engineering design tasks, Janus achieves a larger area under the best-so-far improvement curve over the real-evaluation budget and higher final performance than a matched baseline that evolves only target programs. On average, Janus reaches 99/% of the baseline's final improvement with 59.1/% fewer real evaluations. Evolved proxy evaluators also rank promising candidates more accurately than their seed versions. Together, these results extend evaluator-guided LLM discovery from tasks with cheap, scalable feedback to scientific domains where trustworthy evaluation is scarce and expensive.

cs.AI↗

arXiv2026

CDN Tsunami: Exploiting HTTP/3-HTTP/1.1 Conversion for DoS Attacks

Content Delivery Networks (CDNs) provide high availability, accelerate content delivery for their host websites, but are also vulnerable to different types of Denial-of-Service (DoS) attacks. Prior works have studied a variety of DoS attacks with HTTP/1.1 or HTTP/2 connections, but most of them are being fixed, making CDNs robust against such attacks. One unexplored research area is how the recent introduction of HTTP/3 at CDNs affects the DoS attack landscape, especially when there are heterogeneous deployments of HTTP/3 and HTTP/1.1 between CDNs and host websites. In this paper, we design the first study of DoS attacks against HTTP/3 protocols deployed at CDNs. Our key insight is that when the CDN adopts HTTP/3 but the host websites use HTTP/1.1, an adversary can utilize the disparity to amplify a small amount of traffic to the CDN using HTTP/3 to a large amount from the CDN to the host website using HTTP/1.1. More specifically, we design two attack variations-HTTP/3 Bandwidth Amplification (HBA) and HTTP/3 Connection Amplification (HCA)-targeting the bandwidth and the number of connections, respectively. Furthermore, we conduct a large-scale measurement upon the Tranco Top 1M domain list to quantify the real-world impact of these attacks, identifying 42,330 subdomains that are potentially vulnerable to our attacks. Finally, we responsibly disclose the details of our attacks to the affected CDN vendors: so far, two vendors have already acknowledged their vulnerabilities with bounties and have deployed our mitigations.

cs.CR↗

arXiv2026

NeuroRisk: Physics-Informed Neural Optimization for Risk-Aware Traffic Engineering

In production Wide-Area Networks (WANs), correlated failures dominate availability losses, forcing operators to reserve large safety margins that leave substantial capacity underutilized. Achieving high utilization under strict availability targets therefore requires risk-aware Traffic Engineering (TE) over dozens to hundreds of probabilistic failure scenarios-yet solving this problem at operational timescales remains elusive. We demonstrate that existing risk-aware formulations can be unified under an embedded Sort-and-Select structure, exposing a fundamental trade-off between expressiveness and tractability: classical optimizers either restrict scenario selection for efficiency or incur prohibitive decomposition costs. While deep learning appears promising, prior Deep TE methods mainly target maximum link utilization and rely on scaling-based feasibility, which fundamentally breaks under explicit capacity constraints and scenario-dependent risk. We present NeuroRisk, a physics-informed deep unrolled optimizer that exploits the structure of Sort-and-Select. NeuroRisk enforces feasibility via gated edge-local reservations and represents scenario sets through permutation-invariant, gradient-aligned cues. Evaluations on production-style WANs show that NeuroRisk achieves small optimality gaps relative to the solver with orders of magnitude speedup $(10^2- 10^5 \times)$ on risk objectives, while outperforming neural baselines on nominal throughput.

cs.NI↗

arXiv2026

Leaf-centric Logical Topology Design for OCS-based GPU Clusters

Recent years have witnessed the growing deployment of optical circuit switches (OCS) in commercial GPU clusters (e.g., Google A3 GPU cluster) optimized for machine learning (ML) workloads. Such clusters adopt a three-tier leaf-spine-OCS topology, servers attach to leaf-layer electronic packet switches (EPSes); these leaf switches aggregate into spine-layer EPSes to form a Pod; and multiple Pods are interconnected via core-layer OCSes. Unlike EPSes, OCSes only support circuit-based paths between directly connected spine switches, potentially inducing a phenomenon termed routing polarization, which refers to the scenario where the bandwidth requirements between specific pairs of Pods are unevenly fulfilled through links among different spine switches. The resulting imbalance induces traffic contention and bottlenecks on specific leaf-to-spine links, ultimately reducing ML training throughput. To mitigate this issue, we introduce a leaf-centric paradigm to ensure traffic originating from the same leaf switch is evenly distributed across multiple spine switches with balanced loads. Through rigorous theoretical analysis, we establish a sufficient condition for avoiding routing polarization and propose a corresponding logical topology design algorithm with polynomial-time complexity. Large-scale simulations validate up to 19.27% throughput improvement and a 99.16% reduction in logical topology computation overhead compared to Mixed Integer Programming (MIP)-based methods.

cs.NI↗

arXiv2025

ATRO: A Fast Algorithm for Topology Engineering of Reconfigurable Datacenter Networks

Reconfigurable data center networks (DCNs) enhance traditional architectures with optical circuit switches (OCSs), enabling dynamic reconfiguration of inter-pod links, i.e., the logical topology. Optimizing this topology is crucial for adapting to traffic dynamics but is challenging due to its combinatorial nature. The complexity increases further when demands can be distributed across multiple paths, requiring joint optimization of topology and routing. We propose Alternating Topology and Routing Optimization (ATRO), a unified framework that supports both one-hop topology optimization (where traffic is routed via direct paths) and multi-hop joint optimization (where routing is also optimized). Although these settings differ in constraints, both are combinatorially hard and challenge solver-based methods. ATRO addresses both cases efficiently: in the one-hop case, it guarantees the global optimum via an accelerated binary search; in the multi-hop case, it alternates between topology and routing updates, with routing steps optionally accelerated by existing traffic engineering (TE) methods. ATRO supports warm-starting and improves solution quality monotonically across iterations. ATRO remains competitive even when paired with solver-free TE methods, forming a fully solver-free optimization pipeline that still outperforms prior approaches in runtime and maximum link utilization across diverse workloads.

cs.NI↗

arXiv2025

Geminet: Learning the Duality-based Iterative Process for Lightweight Traffic Engineering in Changing Topologies

Recently, researchers have explored ML-based Traffic Engineering (TE), leveraging neural networks to solve TE problems traditionally addressed by optimization. However, existing ML-based TE schemes remain impractical: they either fail to handle topology changes or suffer from poor scalability due to excessive computational and memory overhead. To overcome these limitations, we propose Geminet, a lightweight and scalable ML-based TE framework that can handle changing topologies. Geminet is built upon two key insights: (i) a methodology that decouples neural networks from topology by learning an iterative gradient-descent-based adjustment process, as the update rule of gradient descent is topology-agnostic, relying only on a few gradient-related quantities; (ii) shifting optimization from path-level routing weights to edge-level dual variables, reducing memory consumption by leveraging the fact that edges are far fewer than paths. Evaluations on WAN and data center datasets show that Geminet significantly improves scalability. Its neural network size is only 0.04% to 7% of existing schemes, while handling topology variations as effectively as HARP, a state-of-the-art ML-based TE approach, without performance degradation. When trained on large-scale topologies, Geminet consumes under 10 GiB of memory, more than eight times less than the 80-plus GiB required by HARP, while achieving 5.45 times faster convergence speed, demonstrating its potential for large-scale deployment.

cs.NI↗

arXiv2025

Epass: Efficient and Privacy-Preserving Asynchronous Payment on Blockchain

Buy Now Pay Later (BNPL) is a rapidly proliferating e-commerce model, offering consumers to get the product immediately and defer payments. Meanwhile, emerging blockchain technologies endow BNPL platforms with digital currency transactions, allowing BNPL platforms to integrate with digital wallets. However, the transparency of transactions causes critical privacy concerns because malicious participants may derive consumers' financial statuses from on-chain asynchronous payments. Furthermore, the newly created transactions for deferred payments introduce additional time overheads, which weaken the scalability of BNPL services. To address these issues, we propose an efficient and privacy-preserving blockchain-based asynchronous payment scheme (Epass), which has promising scalability while protecting the privacy of on-chain consumer transactions. Specifically, Epass leverages locally verifiable signatures to guarantee the privacy of consumer transactions against malicious acts. Then, a privacy-preserving asynchronous payment scheme can be further constructed by leveraging time-release encryption to control trapdoors of redactable blockchain, reducing time overheads by modifying transactions for deferred payment. We give formal definitions and security models, generic structures, and formal proofs for Epass. Extensive comparisons and experimental analysis show that \textsf{Epass} achieves KB-level communication costs, and reduces time overhead by more than four times in comparisons with locally verifiable signatures and Go-Ethereum private test networks.

cs.CR↗

arXiv2025

A Fast Solver-Free Algorithm for Traffic Engineering in Large-Scale Data Center Network

Rapid growth of data center networks (DCNs) poses significant challenges for large-scale traffic engineering (TE). Existing acceleration strategies, which rely on commercial solvers or deep learning, face scalability issues and struggle with degrading performance or long computational time. Unlike existing algorithms adopting parallel strategies, we propose Sequential Source-Destination Optimization (SSDO), a sequential solver-free algorithm for TE. SSDO decomposes the problem into subproblems, each focused on adjusting the split ratios for a specific source-destination (SD) demand while keeping others fixed. To enhance the efficiency of subproblem optimization, we design a Balanced Binary Search Method (BBSM), which identifies the most balanced split ratios among multiple solutions that minimize Maximum Link Utilization (MLU). SSDO dynamically updates the sequence of SDs based on real-time utilization, which accelerates convergence and enhances solution quality. We evaluate SSDO on Meta DCNs and two wide-area networks. In a Meta topology, SSDO achieves a 65\% and 60\% reduction in normalized MLU compared to TEAL and POP, two state-of-the-art TE acceleration methods, while delivering a $12\times$ speedup over POP. These results demonstrate the superior performance of SSDO in large-scale TE.

cs.NI↗

arXiv2025

Local Differential Privacy is Not Enough: A Sample Reconstruction Attack against Federated Learning with Local Differential Privacy

Reconstruction attacks against federated learning (FL) aim to reconstruct users' samples through users' uploaded gradients. Local differential privacy (LDP) is regarded as an effective defense against various attacks, including sample reconstruction in FL, where gradients are clipped and perturbed. Existing attacks are ineffective in FL with LDP since clipped and perturbed gradients obliterate most sample information for reconstruction. Besides, existing attacks embed additional sample information into gradients to improve the attack effect and cause gradient expansion, leading to a more severe gradient clipping in FL with LDP. In this paper, we propose a sample reconstruction attack against LDP-based FL with any target models to reconstruct victims' sensitive samples to illustrate that FL with LDP is not flawless. Considering gradient expansion in reconstruction attacks and noise in LDP, the core of the proposed attack is gradient compression and reconstructed sample denoising. For gradient compression, an inference structure based on sample characteristics is presented to reduce redundant gradients against LDP. For reconstructed sample denoising, we artificially introduce zero gradients to observe noise distribution and scale confidence interval to filter the noise. Theoretical proof guarantees the effectiveness of the proposed attack. Evaluations show that the proposed attack is the only attack that reconstructs victims' training samples in LDP-based FL and has little impact on the target model's accuracy. We conclude that LDP-based FL needs further improvements to defend against sample reconstruction attacks effectively.

cs.CR↗

arXiv2024

A Highly Scalable LLM Clusters with Optical Interconnect

Recent years have witnessed the adoption of optical circuit switch (OCS) technology. How to design the physical topology, defined by the physical wiring between electrical switching equipments and the OCS, is fundamental to designing efficient OCS-based clusters. We identify three features to evaluate the quality of a physical topology design: logical topology compatibility, cluster scalability, and topology engineering polynomial-solvability. However, none of existing physical topologies has achieved these three features simultaneously. This paper explores designing an optimal physical topology that simultaneously maximizes all. We begin by analyzing the importance of these features in OCS-based cluster and examine the limitations of current designs. Leveraging a proposed \emph{Symmetric Integer Matrix Decomposition Theorem}, we outline a general approach for designing optimal physical topologies and introduce \textbf{Cross Wiring} as a concrete instantiation. The feasibility and advantages of Cross Wiring are verified through a 128-NPU testbed and large-scale real-trace-based simulations.

cs.NI↗

arXiv2024

MORSE: An Efficient Homomorphic Secret Sharing Scheme Enabling Non-Linear Operation

Homomorphic secret sharing (HSS) enables two servers to locally perform functions on encrypted data directly and obtain the results in the form of shares. A Paillier-based HSS solution seamlessly achieves multiplicative homomorphism and consumes less communication costs. Unfortunately, existing Paillier-based HSS schemes suffer from a large private key size, potential calculation error, expensive computation and storage overhead, and only valid on linear operations (e.g., addition and multiplication). To this end, inspired by the Paillier cryptosystem with fast encryption and decryption, we propose MORSE, an efficient homomorphic secret sharing scheme enabling non-linear operation, which enjoys a small key size, no calculation error and low overhead. In terms of functions, MORSE supports addition, subtraction, multiplication, scalar-multiplication, and comparison. Particularly, we carefully design two conversion protocols achieving the mutual conversion between one Paillier ciphertext and two secret shares, which allows MORSE to continuously perform the above operations. Rigorous analyses demonstrate that MORSE securely outputs correct results. Experimental results show that MORSE makes a runtime improvement of up to 9.3 times in terms of secure multiplication, and a communication costs reduction of up to 16.6% in secure comparison, compared to the state-of-the-art.

cs.CR↗

arXiv2024

Detecting and Measuring Security Implications of Entangled Domain Verification in CDN

Content Delivery Networks (CDNs) offer a protection layer for enhancing the security of websites. However, a significant security flaw named Absence of Domain Verification (DVA) has become emerging recently. Although this threat is recognized, the current practices and security flaws of domain verification strategies in CDNs have not been thoroughly investigated. In this paper, we present DVAHunter, an automated system for detecting DVA vulnerabilities that can lead to domain abuse in CDNs. Our evaluation of 45 major CDN providers reveals the prevalence of DVA: most (39/45) providers do not perform any verification, and even those that do remain exploitable. Additionally, we used DVAHunter to conduct a large-scale measurement of 89M subdomains from Tranco's Top 1M sites hosted on the 45 CDNs under evaluation. Our focus was on two primary DVA exploitation scenarios: covert communication and domain hijacking. We identified over 332K subdomains vulnerable to domain abuse. This tool provides deeper insights into DVA exploitation and allows us to propose viable mitigation practices for CDN providers. To date, we have received vulnerability confirmations from 12 providers; 6 (e.g., Edgio, Kuocai) have implemented fixes, and 1 (ChinaNetCenter) are actively working on solutions based on our recommendations.

cs.CR↗

arXiv2024

Unveiling the Bandwidth Nightmare: CDN Compression Format Conversion Attacks

Content Delivery Networks (CDNs) are designed to enhance network performance and protect against web attack traffic for their hosting websites. And the HTTP compression request mechanism primarily aims to reduce unnecessary network transfers. However, we find that the specification failed to consider the security risks introduced when CDNs meet compression requests. In this paper, we present a novel HTTP amplification attack, CDN Compression Format Convert (CDN-Convet) Attacks. It allows attackers to massively exhaust not only the outgoing bandwidth of the origin servers deployed behind CDNs but also the bandwidth of CDN surrogate nodes. We examined the CDN-Convet attacks on 11 popular CDNs to evaluate the feasibility and real-world impacts. Our experimental results show that all these CDNs are affected by the CDN-Convet attacks. We have also disclosed our findings to affected CDN providers and have received constructive feedback.

cs.CR↗

arXiv2024

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images

Adversarial attack has garnered considerable attention due to its profound implications for the secure deployment of robots in sensitive security scenarios. To potentially push for advances in the field, this paper studies the adversarial attack in the black-box setting and proposes an unlabeled data-driven adversarial attack method, called SemiAdv. Specifically, SemiAdv achieves the following breakthroughs compared with previous works. First, by introducing the semi-supervised learning technique into the adversarial attack, SemiAdv substantially decreases the number of queries required for generating adversarial samples. On average, SemiAdv only needs to query a few hundred times to launch an effective attack with more than 90% success rate. Second, many existing black-box adversarial attacks require massive labeled data to mitigate the difference between the local substitute model and the remote target model for a good attack performance. While SemiAdv relaxes this limitation and is capable of utilizing unlabeled raw data to launch an effective attack. Finally, our experiments show that SemiAdv saves up to 12x query accesses for generating adversarial samples while maintaining a competitive attack success rate compared with state-of-the-art attacks.

cs.CR↗

arXiv2024

MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization

Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which severely affects the generalization performance. Empirically, in the late phases of training, the AT becomes more overfitting to the extent that the individuals for weight averaging also suffer from overfitting and produce anomalous weight values, which causes the self-ensemble model to continue to undergo robust overfitting due to the failure in removing the weight anomalies. To solve this problem, we aim to tackle the influence of outliers in the weight space in this work and propose an easy-to-operate and effective Median-Ensemble Adversarial Training (MEAT) method to solve the robust overfitting phenomenon existing in self-ensemble defense from the source by searching for the median of the historical model weights. Experimental results show that MEAT achieves the best robustness against the powerful AutoAttack and can effectively allievate the robust overfitting. We further demonstrate that most defense methods can improve robust generalization and robustness by combining with MEAT.

cs.LG↗

arXiv2024

Towards Trustworthy Unsupervised Domain Adaptation: A Representation Learning Perspective for Enhancing Robustness, Discrimination, and Generalization

Robust Unsupervised Domain Adaptation (RoUDA) aims to achieve not only clean but also robust cross-domain knowledge transfer from a labeled source domain to an unlabeled target domain. A number of works have been conducted by directly injecting adversarial training (AT) in UDA based on the self-training pipeline and then aiming to generate better adversarial examples (AEs) for AT. Despite the remarkable progress, these methods only focus on finding stronger AEs but neglect how to better learn from these AEs, thus leading to unsatisfied results. In this paper, we investigate robust UDA from a representation learning perspective and design a novel algorithm by utilizing the mutual information theory, dubbed MIRoUDA. Specifically, through mutual information optimization, MIRoUDA is designed to achieve three characteristics that are highly expected in robust UDA, i.e., robustness, discrimination, and generalization. We then propose a dual-model framework accordingly for robust UDA learning. Extensive experiments on various benchmarks verify the effectiveness of the proposed MIRoUDA, in which our method surpasses the state-of-the-arts by a large margin.

cs.CV↗

arXiv2024

FIGRET: Fine-Grained Robustness-Enhanced Traffic Engineering

Traffic Engineering (TE) is critical for improving network performance and reliability. A key challenge in TE is the management of sudden traffic bursts. Existing TE schemes either do not handle traffic bursts or uniformly guard against traffic bursts, thereby facing difficulties in achieving a balance between normal-case performance and burst-case performance. To address this issue, we introduce FIGRET, a Fine-Grained Robustness-Enhanced TE scheme. FIGRET offers a novel approach to TE by providing varying levels of robustness enhancements, customized according to the distinct traffic characteristics of various source-destination pairs. By leveraging a burst-aware loss function and deep learning techniques, FIGRET is capable of generating high-quality TE solutions efficiently. Our evaluations of real-world production networks, including Wide Area Networks and data centers, demonstrate that FIGRET significantly outperforms existing TE schemes. Compared to the TE scheme currently deployed in Jupiter data center networks of Google, FIGRET achieves a 9\%-34\% reduction in average Maximum Link Utilization and improves solution speed by $35\times$-$1800 \times$. Against DOTE, a state-of-the-art deep learning-based TE method, FIGRET substantially lowers the occurrence of significant congestion events triggered by traffic bursts by 41\%-53.9\% in topologies with high traffic dynamics.

cs.NI↗

arXiv2024

MFA-Net: Multi-Scale feature fusion attention network for liver tumor segmentation

Segmentation of organs of interest in medical CT images is beneficial for diagnosis of diseases. Though recent methods based on Fully Convolutional Neural Networks (F-CNNs) have shown success in many segmentation tasks, fusing features from images with different scales is still a challenge: (1) Due to the lack of spatial awareness, F-CNNs share the same weights at different spatial locations. (2) F-CNNs can only obtain surrounding information through local receptive fields. To address the above challenge, we propose a new segmentation framework based on attention mechanisms, named MFA-Net (Multi-Scale Feature Fusion Attention Network). The proposed framework can learn more meaningful feature maps among multiple scales and result in more accurate automatic segmentation. We compare our proposed MFA-Net with SOTA methods on two 2D liver CT datasets. The experimental results show that our MFA-Net produces more precise segmentation on images with different scales.

cs.AI↗