arXiv subjects

Tianwei Zhang

Publications and source records attributed to Tianwei Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2025

An S-shaped filament formed due to Cloud-Cloud Collision in molecular cloud G178.28-00.61

We present compelling observational evidence supporting G178.28-00.61 as an early-stage candidate for Cloud-Cloud Collision (CCC), with indications of the formation of an S-shaped filament, evenly-separated dense cores, and young star clusters. The observations of CO molecular line emission demonstrate the existence of two interacting molecular clouds with systemic velocities of 0.8 km/s and -1.2 km/s, respectively. The convergence zone of these two clouds reveals an S-shaped filament in the JCMT 850 micron continuum image, suggesting cloud interaction. In line with expectations from CCC simulations, broad bridging features are discernible in the position-velocity diagrams. An elevated concentration of identified Class I and II young stellar objects along the filament at the intersection area further supports the hypothesis of a collision-induced origin. This observation could be explained by a recent MHD model of CCC (Kong et al. 2024), which predicts a similar morphology, scale, density, and unbound status, as well as the orientation of the polarization.

astro-ph.GA↗

arXiv2025

ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs

Recent advancements have led to the widespread adoption of code-oriented large language models (Code LLMs) for programming tasks. Despite their success in deployment, their security research is left far behind. This paper introduces a new attack paradigm: (automatic) external prompt injection against Code LLMs, where attackers generate concise, non-functional induced perturbations and inject them within a victim's code context. These induced perturbations can be disseminated through commonly used dependencies (e.g., packages or RAG's knowledge base), manipulating Code LLMs to achieve malicious objectives during the code completion process. Compared to existing attacks, this method is more realistic and threatening: it does not necessitate control over the model's training process, unlike backdoor attacks, and can achieve specific malicious objectives that are challenging for adversarial attacks. Furthermore, we propose ShadowCode, a simple yet effective method that automatically generates induced perturbations based on code simulation to achieve effective and stealthy external prompt injection. ShadowCode designs its perturbation optimization objectives by simulating realistic code contexts and employs a greedy optimization approach with two enhancement modules: forward reasoning enhancement and keyword-based perturbation design. We evaluate our method across 13 distinct malicious objectives, generating 31 threat cases spanning three popular programming languages. Our results demonstrate that ShadowCode successfully attacks three representative open-source Code LLMs (achieving up to a 97.9% attack success rate) and two mainstream commercial Code LLM-integrated applications (with over 90% attack success rate) across all threat cases, using only a 12-token non-functional induced perturbation. The code is available at https://github.com/LianPing-cyber/ShadowCodeEPI.

cs.CR↗

arXiv2025

Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges

As large language models (LLMs) evolve, deploying them solely in the cloud or compressing them for edge devices has become inadequate due to concerns about latency, privacy, cost, and personalization. This survey explores a collaborative paradigm in which cloud-based LLMs and edge-deployed small language models (SLMs) cooperate across both inference and training. We present a unified taxonomy of edge-cloud collaboration strategies. For inference, we categorize approaches into task assignment, task division, and mixture-based collaboration at both task and token granularity, encompassing adaptive scheduling, resource-aware offloading, speculative decoding, and modular routing. For training, we review distributed adaptation techniques, including parameter alignment, pruning, bidirectional distillation, and small-model-guided optimization. We further summarize datasets, benchmarks, and deployment cases, and highlight privacy-preserving methods and vertical applications. This survey provides the first systematic foundation for LLM-SLM collaboration, bridging system and algorithm co-design to enable efficient, scalable, and trustworthy edge-cloud intelligence.

cs.DC↗

arXiv2025

Understanding the Dark Side of LLMs' Intrinsic Self-Correction

Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic self-correction fails without oracle labels as feedback prompts. In this paper, we aim to interpret LLMs' intrinsic self-correction for different tasks, especially for those failure cases. By including one simple task and three complex tasks with state-of-the-art (SOTA) LLMs like ChatGPT families (o1, 4o, 3.5-turbo) and Llama families (2-7B, 3-8B, and 3.1-8B), we design three interpretation methods to reveal the dark side of LLMs' intrinsic self-correction. We identify intrinsic self-correction can (1) cause LLMs to waver both intermedia and final answers and lead to prompt bias on simple factual questions; (2) introduce human-like cognitive bias on complex tasks. In light of our findings, we also provide two simple yet effective strategies for alleviation: question repeating and supervised fine-tuning with a few samples. We open-source our work at https://x-isc.info/.

cs.CL↗

arXiv2025

BURN: Backdoor Unlearning via Adversarial Boundary Analysis

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic labels of poison samples. This limitation prevents them from fully eliminating the false correlation between the trigger pattern and the target label. To address this, we leverage boundary adversarial attack techniques, revealing two key observations. First, poison samples exhibit significantly greater distances from decision boundaries compared to clean samples, indicating they require larger adversarial perturbations to change their predictions. Second, while adversarial predicted labels for clean samples are uniformly distributed, those for poison samples tend to revert to their original correct labels. Moreover, the features of poison samples restore to closely resemble those of corresponding clean samples after adding adversarial perturbations. Building upon these insights, we propose Backdoor Unlearning via adversaRial bouNdary analysis (BURN), a novel defense framework that integrates false correlation decoupling, progressive data refinement, and model purification. In the first phase, BURN employs adversarial boundary analysis to detect poisoned samples based on their abnormal adversarial boundary distances, then restores their correct semantic labels for fine-tuning. In the second phase, it employs a feedback mechanism that tracks prediction discrepancies between the original backdoored model and progressively sanitized models, guiding both dataset refinement and model purification. Extensive evaluations across multiple datasets, architectures, and seven diverse backdoor attack types confirm that BURN effectively removes backdoor threats while maintaining the model's original performance.

cs.CR↗

arXiv2025

Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack

By using a control variate to calibrate the local gradient of each client, Scaffold has been widely known as a powerful solution to mitigate the impact of data heterogeneity in Federated Learning. Although Scaffold achieves significant performance improvements, we show that this superiority is at the cost of increased security vulnerabilities. Specifically, this paper presents BadSFL, the first backdoor attack targeting Scaffold, which turns benign clients into accomplices to amplify the attack effect. The core idea of BadSFL is to uniquely tamper with the control variate to subtly steer benign clients' local gradient updates towards the attacker's poisoned direction, effectively turning them into unwitting accomplices and significantly enhancing the backdoor persistence. Additionally, BadSFL leverages a GAN-enhanced poisoning strategy to enrich the attacker's dataset, maintaining high accuracy on both benign and backdoored samples while remaining stealthy. Extensive experiments demonstrate that BadSFL achieves superior attack durability, maintaining effectiveness for over 60 global rounds, lasting up to three times longer than existing baselines even after ceasing malicious model injections.

cs.LG↗

arXiv2025

DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving

The Text-to-Video (T2V) model aims to generate dynamic and expressive videos from textual prompts. The generation pipeline typically involves multiple modules, such as language encoder, Diffusion Transformer (DiT), and Variational Autoencoders (VAE). Existing serving systems often rely on monolithic model deployment, while overlooking the distinct characteristics of each module, leading to inefficient GPU utilization. In addition, DiT exhibits varying performance gains across different resolutions and degrees of parallelism, and significant optimization potential remains unexplored. To address these problems, we present DDiT, a flexible system that integrates both inter-phase and intra-phase optimizations. DDiT focuses on two key metrics: optimal degree of parallelism, which prevents excessive parallelism for specific resolutions, and starvation time, which quantifies the sacrifice of each request. To this end, DDiT introduces a decoupled control mechanism to minimize the computational inefficiency caused by imbalances in the degree of parallelism between the DiT and VAE phases. It also designs a greedy resource allocation algorithm with a novel scheduling mechanism that operates at the single-step granularity, enabling dynamic and timely resource scaling. Our evaluation on the T5 encoder, OpenSora SDDiT, and OpenSora VAE models across diverse datasets reveals that DDiT significantly outperforms state-of-the-art baselines by up to 1.44x in p99 latency and 1.43x in average latency.

cs.DC↗

arXiv2025

Towards Action Hijacking of Large Language Model-based Agent

Recently, applications powered by Large Language Models (LLMs) have made significant strides in tackling complex tasks. By harnessing the advanced reasoning capabilities and extensive knowledge embedded in LLMs, these applications can generate detailed action plans that are subsequently executed by external tools. Furthermore, the integration of retrieval-augmented generation (RAG) enhances performance by incorporating up-to-date, domain-specific knowledge into the planning and execution processes. This approach has seen widespread adoption across various sectors, including healthcare, finance, and software development. Meanwhile, there are also growing concerns regarding the security of LLM-based applications. Researchers have disclosed various attacks, represented by jailbreak and prompt injection, to hijack the output actions of these applications. Existing attacks mainly focus on crafting semantically harmful prompts, and their validity could diminish when security filters are employed. In this paper, we introduce AI$\mathbf{^2}$, a novel attack to manipulate the action plans of LLM-based applications. Different from existing solutions, the innovation of AI$\mathbf{^2}$ lies in leveraging the knowledge from the application's database to facilitate the construction of malicious but semantically-harmless prompts. To this end, it first collects action-aware knowledge from the victim application. Based on such knowledge, the attacker can generate misleading input, which can mislead the LLM to generate harmful action plans, while bypassing possible detection mechanisms easily. Our evaluations on three real-world applications demonstrate the effectiveness of AI$\mathbf{^2}$: it achieves an average attack success rate of 84.30\% with the best of 99.70\%. Besides, it gets an average bypass rate of 92.7\% against common safety filters and 59.45\% against dedicated defense.

cs.CR↗

arXiv2025

ObfusBFA: A Holistic Approach to Safeguarding DNNs from Different Types of Bit-Flip Attacks

Bit-flip attacks (BFAs) represent a serious threat to Deep Neural Networks (DNNs), where flipping a small number of bits in the model parameters or binary code can significantly degrade the model accuracy or mislead the model prediction in a desired way. Existing defenses exclusively focus on protecting models for specific attacks and platforms, while lacking effectiveness for other scenarios. We propose ObfusBFA, an efficient and holistic methodology to mitigate BFAs targeting both the high-level model weights and low-level codebase (executables or shared libraries). The key idea of ObfusBFA is to introduce random dummy operations during the model inference, which effectively transforms the delicate attacks into random bit flips, making it much harder for attackers to pinpoint and exploit vulnerable bits. We design novel algorithms to identify critical bits and insert obfuscation operations. We evaluate ObfusBFA against different types of attacks, including the adaptive scenarios where the attacker increases the flip bit budget to attempt to circumvent our defense. The results show that ObfusBFA can consistently preserve the model accuracy across various datasets and DNN architectures while significantly reducing the attack success rates. Additionally, it introduces minimal latency and storage overhead, making it a practical solution for real-world applications.

cs.CR↗

arXiv2025

An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems

Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes $μ$MOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), $μ$MOEA promotes the LLM to comprehend the optimization problem and generate an initial population tailed to evolutionary objectives. Subsequently, it employs adaptive selection and variation to iteratively produce offspring, balancing the evolutionary efficiency and diversity. During the evolutionary process, to navigate away from the local optima, $μ$MOEA integrates the evolutionary experience back into the LLM. This utilization harnesses the LLM's quantitative reasoning prowess to generate differential seeds, breaking away from current optimal solutions. We evaluate $μ$MOEA in finding safety violations of MCDL systems, and compare its performance with state-of-the-art MOEA methods. Experimental results show that $μ$MOEA can significantly improve the efficiency and diversity of the evolutionary search.

cs.NE↗

arXiv2025

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e.g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs. To address this gap, this paper introduces, for the first time, the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization. Compared to the off-the-shelf LLM safety surveys, our work demonstrates several distinctive advantages: (I) Comprehensive Perspective. We define the complete LLM lifecycle as encompassing data preparation, pre-training, post-training, deployment and final commercialization. To our knowledge, this represents the first safety survey to encompass the entire lifecycle of LLMs. (II) Extensive Literature Support. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues within a more holistic understanding. (III) Unique Insights. Through systematic literature analysis, we have developed reliable roadmaps and perspectives for each chapter. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems. These insights provide valuable guidance for researchers pursuing future work in this field.

cs.CR↗

arXiv2025

Rethinking Machine Unlearning in Image Generation Models

With the surge and widespread application of image generation models, data privacy and content safety have become major concerns and attracted great attention from users, service providers, and policymakers. Machine unlearning (MU) is recognized as a cost-effective and promising means to address these challenges. Despite some advancements, image generation model unlearning (IGMU) still faces remarkable gaps in practice, e.g., unclear task discrimination and unlearning guidelines, lack of an effective evaluation framework, and unreliable evaluation metrics. These can hinder the understanding of unlearning mechanisms and the design of practical unlearning algorithms. We perform exhaustive assessments over existing state-of-the-art unlearning algorithms and evaluation standards, and discover several critical flaws and challenges in IGMU tasks. Driven by these limitations, we make several core contributions, to facilitate the comprehensive understanding, standardized categorization, and reliable evaluation of IGMU. Specifically, (1) We design CatIGMU, a novel hierarchical task categorization framework. It provides detailed implementation guidance for IGMU, assisting in the design of unlearning algorithms and the construction of testbeds. (2) We introduce EvalIGMU, a comprehensive evaluation framework. It includes reliable quantitative metrics across five critical aspects. (3) We construct DataIGM, a high-quality unlearning dataset, which can be used for extensive evaluations of IGMU, training content detectors for judgment, and benchmarking the state-of-the-art unlearning algorithms. With EvalIGMU and DataIGM, we discover that most existing IGMU algorithms cannot handle the unlearning well across different evaluation dimensions, especially for preservation and robustness. Code and models are available at https://github.com/ryliu68/IGMU.

cs.AI↗

arXiv2025

Network of velocity-coherent filaments formed by supersonic turbulence in a very-high-velocity HI cloud

The warm neutral medium (WNM) was thought to be subsonically/transonically turbulent, and it lacks a network of intertwined filaments that are commonly seen in both molecular clouds and cold neutral medium (CNM). Here, we report HI~21 cm line observations of a very-high-velocity (-330 km s$^{-1}$ $<V_{\rm LSR}<$ -250 km s$^{-1}$) cloud (VHVC), using the Five-hundred-meter Aperture Spherical radio Telescope (FAST) with unprecedented resolution and sensitivity. For the first time, such a VHVC is clearly revealed to be a supersonic WNM system consisting of a network of velocity-coherent HI~filaments. The filaments are in the forms of slim curves, hubs, and webs, distributed in different layers within the position-position-velocity ({\it ppv}) data cube. The entire cloud has skewed log-normal probability distribution of column density and the filaments themselves show asymmetrical radial density profiles, indicating shock compression by supersonic magnetohydrodynamic (MHD) turbulence, as is also confirmed by our MHD simulation (sonic Mach number $M_{\rm s}=3$ and Alfvén Mach number $M_{\rm A}=1$). This work suggests that hierarchical filaments can be established by shocks in a low-density WNM, where gravity is negligible, offering a viable pathway to structure formation in the earliest evolutionary phases of the interstellar medium (ISM).

astro-ph.GA↗

arXiv2025

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings

Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent studies show that simple character substitutions in toxic Chinese text can easily confuse the state-of-the-art (SOTA) LLMs. In this paper, we highlight the multimodal nature of Chinese language as a key challenge for deploying LLMs in toxic Chinese detection. First, we propose a taxonomy of 3 perturbation strategies and 8 specific approaches in toxic Chinese content. Then, we curate a dataset based on this taxonomy, and benchmark 9 SOTA LLMs (from both the US and China) to assess if they can detect perturbed toxic Chinese text. Additionally, we explore cost-effective enhancement solutions like in-context learning (ICL) and supervised fine-tuning (SFT). Our results reveal two important findings. (1) LLMs are less capable of detecting perturbed multimodal Chinese toxic contents. (2) ICL or SFT with a small number of perturbed examples may cause the LLMs "overcorrect'': misidentify many normal Chinese contents as toxic.

cs.CL↗

arXiv2025

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion

We present Adversarial Object Fusion (AdvOF), a novel attack framework targeting vision-and-language navigation (VLN) agents in service-oriented environments by generating adversarial 3D objects. While foundational models like Large Language Models (LLMs) and Vision Language Models (VLMs) have enhanced service-oriented navigation systems through improved perception and decision-making, their integration introduces vulnerabilities in mission-critical service workflows. Existing adversarial attacks fail to address service computing contexts, where reliability and quality-of-service (QoS) are paramount. We utilize AdvOF to investigate and explore the impact of adversarial environments on the VLM-based perception module of VLN agents. In particular, AdvOF first precisely aggregates and aligns the victim object positions in both 2D and 3D space, defining and rendering adversarial objects. Then, we collaboratively optimize the adversarial object with regularization between the adversarial and victim object across physical properties and VLM perceptions. Through assigning importance weights to varying views, the optimization is processed stably and multi-viewedly by iterative fusions from local updates and justifications. Our extensive evaluations demonstrate AdvOF can effectively degrade agent performance under adversarial conditions while maintaining minimal interference with normal navigation tasks. This work advances the understanding of service security in VLM-powered navigation systems, providing computational foundations for robust service composition in physical-world deployments.

cs.CR↗

arXiv2025

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models

In this paper, we present a new form of backdoor attack against Large Language Models (LLMs): lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the language itself serves as the trigger to hijack the infected LLMs to generate inflammatory speech. They enable the precise targeting of a specific language-speaking group, exacerbating racial discrimination by malicious entities. We first implement a baseline lingual-backdoor attack, which is carried out by poisoning a set of training data for specific downstream tasks through translation into the trigger language. However, this baseline attack suffers from poor task generalization and is impractical in real-world settings. To address this challenge, we design BadLingual, a novel task-agnostic lingual-backdoor, capable of triggering any downstream tasks within the chat LLMs, regardless of the specific questions of these tasks. We design a new approach using PPL-constrained Greedy Coordinate Gradient-based Search (PGCG) based adversarial training to expand the decision boundary of lingual-backdoor, thereby enhancing the generalization ability of lingual-backdoor across various tasks. We perform extensive experiments to validate the effectiveness of our proposed attacks. Specifically, the baseline attack achieves an ASR of over 90% on the specified tasks. However, its ASR reaches only 37.61% across six tasks in the task-agnostic scenario. In contrast, BadLingual brings up to 37.35% improvement over the baseline. Our study sheds light on a new perspective of vulnerabilities in LLMs with multilingual capabilities and is expected to promote future research on the potential defenses to enhance the LLMs' robustness

cs.CR↗

arXiv2025

Testing the Fault-Tolerance of Multi-Sensor Fusion Perception in Autonomous Driving Systems

High-level Autonomous Driving Systems (ADSs), such as Google Waymo and Baidu Apollo, typically rely on multi-sensor fusion (MSF) based approaches to perceive their surroundings. This strategy increases perception robustness by combining the respective strengths of the camera and LiDAR and directly affects the safety-critical driving decisions of autonomous vehicles (AVs). However, in real-world autonomous driving scenarios, cameras and LiDAR are subject to various faults, which can probably significantly impact the decision-making and behaviors of ADSs. Existing MSF testing approaches only discovered corner cases that the MSF-based perception cannot accurately detected by MSF-based perception, while lacking research on how sensor faults affect the system-level behaviors of ADSs. To address this gap, we conduct the first exploration of the fault tolerance of MSF perception-based ADS for sensor faults. In this paper, we systematically and comprehensively build fault models for cameras and LiDAR in AVs and inject them into the MSF perception-based ADS to test its behaviors in test scenarios. To effectively and efficiently explore the parameter spaces of sensor fault models, we design a feedback-guided differential fuzzer to discover the safety violations of MSF perception-based ADS caused by the injected sensor faults. We evaluate FADE on the representative and practical industrial ADS, Baidu Apollo. Our evaluation results demonstrate the effectiveness and efficiency of FADE, and we conclude some useful findings from the experimental results. To validate the findings in the physical world, we use a real Baidu Apollo 6.0 EDU autonomous vehicle to conduct the physical experiments, and the results show the practical significance of our findings.

cs.RO↗

arXiv2025

The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning

In Federated Learning (FL), clients share gradients with a central server while keeping their data local. However, malicious servers could deliberately manipulate the models to reconstruct clients' data from shared gradients, posing significant privacy risks. Although such active gradient leakage attacks (AGLAs) have been widely studied, they suffer from two severe limitations: (i) coverage: no existing AGLAs can reconstruct all samples in a batch from the shared gradients; (ii) stealthiness: no existing AGLAs can evade principled checks of clients. In this paper, we address these limitations with two core contributions. First, we introduce a new theoretical analysis approach, which uniformly models AGLAs as backdoor poisoning. This analysis approach reveals that the core principle of AGLAs is to bias the gradient space to prioritize the reconstruction of a small subset of samples while sacrificing the majority, which theoretically explains the above limitations of existing AGLAs. Second, we propose Enhanced Gradient Global Vulnerability (EGGV), the first AGLA that achieves complete attack coverage while evading client-side detection. In particular, EGGV employs a gradient projector and a jointly optimized discriminator to assess gradient vulnerability, steering the gradient space toward the point most prone to data leakage. Extensive experiments show that EGGV achieves complete attack coverage and surpasses state-of-the-art (SOTA) with at least a 43% increase in reconstruction quality (PSNR) and a 45% improvement in stealthiness (D-SNR).

cs.CR↗