arXiv subjects

Guowen Xu

Publications and source records attributed to Guowen Xu.

At least 37 records · Page 2Linked to original sources

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

CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perception

Collaborative Perception (CP) has shown a promising technique for autonomous driving, where multiple connected and autonomous vehicles (CAVs) share their perception information to enhance the overall perception performance and expand the perception range. However, in CP, ego CAV needs to receive messages from its collaborators, which makes it easy to be attacked by malicious agents. For example, a malicious agent can send harmful information to the ego CAV to mislead it. To address this critical issue, we propose a novel method, CP-Guard, a tailored defense mechanism for CP that can be deployed by each agent to accurately detect and eliminate malicious agents in its collaboration network. Our key idea is to enable CP to reach a consensus rather than a conflict against the ego CAV's perception results. Based on this idea, we first develop a probability-agnostic sample consensus (PASAC) method to effectively sample a subset of the collaborators and verify the consensus without prior probabilities of malicious agents. Furthermore, we define a collaborative consistency loss (CCLoss) to capture the discrepancy between the ego CAV and its collaborators, which is used as a verification criterion for consensus. Finally, we conduct extensive experiments in collaborative bird's eye view (BEV) tasks and our results demonstrate the effectiveness of our CP-Guard. Code is available at https://github.com/CP-Security/CP-Guard

cs.AI↗

arXiv2025

FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition

Traffic sign recognition (TSR) systems are crucial for autonomous driving but are vulnerable to backdoor attacks. Existing physical backdoor attacks either lack stealth, provide inflexible attack control, or ignore emerging Vision-Large-Language-Models (VLMs). In this paper, we introduce FIGhost, the first physical-world backdoor attack leveraging fluorescent ink as triggers. Fluorescent triggers are invisible under normal conditions and activated stealthily by ultraviolet light, providing superior stealthiness, flexibility, and untraceability. Inspired by real-world graffiti, we derive realistic trigger shapes and enhance their robustness via an interpolation-based fluorescence simulation algorithm. Furthermore, we develop an automated backdoor sample generation method to support three attack objectives. Extensive evaluations in the physical world demonstrate FIGhost's effectiveness against state-of-the-art detectors and VLMs, maintaining robustness under environmental variations and effectively evading existing defenses.

cs.CV↗

arXiv2025

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks

Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however, are effective only for specific pre-defined downstream tasks. In reality, these PTLMs can be adapted to many other unrelated downstream tasks. Such adaptation may lead to unforeseen consequences in downstream model outputs, consequently raising user suspicion and compromising attack stealthiness. We refer to this phenomenon as backdoor complications. In this paper, we undertake the first comprehensive quantification of backdoor complications. Through extensive experiments using 4 prominent PTLMs and 16 text classification benchmark datasets, we demonstrate the widespread presence of backdoor complications in downstream models fine-tuned from backdoored PTLMs. The output distribution of triggered samples significantly deviates from that of clean samples. Consequently, we propose a backdoor complication reduction method leveraging multi-task learning to mitigate complications without prior knowledge of downstream tasks. The experimental results demonstrate that our proposed method can effectively reduce complications while maintaining the efficacy and consistency of backdoor attacks. Our code is available at https://github.com/zhangrui4041/Backdoor_Complications.

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

Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAV

Connected and autonomous vehicles (CAVs) have garnered significant attention due to their extended perception range and enhanced sensing coverage. To address challenges such as blind spots and obstructions, CAVs employ vehicle-to-vehicle (V2V) communications to aggregate sensory data from surrounding vehicles. However, cooperative perception is often constrained by the limitations of achievable network throughput and channel quality. In this paper, we propose a channel-aware throughput maximization approach to facilitate CAV data fusion, leveraging a self-supervised autoencoder for adaptive data compression. We formulate the problem as a mixed integer programming (MIP) model, which we decompose into two sub-problems to derive optimal data rate and compression ratio solutions under given link conditions. An autoencoder is then trained to minimize bitrate with the determined compression ratio, and a fine-tuning strategy is employed to further reduce spectrum resource consumption. Experimental evaluation on the OpenCOOD platform demonstrates the effectiveness of our proposed algorithm, showing more than 20.19\% improvement in network throughput and a 9.38\% increase in average precision (AP@IoU) compared to state-of-the-art methods, with an optimal latency of 19.99 ms.

cs.AI↗

arXiv2025

Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal

The intellectual property of deep image-to-image models can be protected by the so-called box-free watermarking. It uses an encoder and a decoder, respectively, to embed into and extract from the model's output images invisible copyright marks. Prior works have improved watermark robustness, focusing on the design of better watermark encoders. In this paper, we reveal an overlooked vulnerability of the unprotected watermark decoder which is jointly trained with the encoder and can be exploited to train a watermark removal network. To defend against such an attack, we propose the decoder gradient shield (DGS) as a protection layer in the decoder API to prevent gradient-based watermark removal with a closed-form solution. The fundamental idea is inspired by the classical adversarial attack, but is utilized for the first time as a defensive mechanism in the box-free model watermarking. We then demonstrate that DGS can reorient and rescale the gradient directions of watermarked queries and stop the watermark remover's training loss from converging to the level without DGS, while retaining decoder output image quality. Experimental results verify the effectiveness of proposed method. Code of paper will be made available upon acceptance.

cs.CV↗

arXiv2025

CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perception

Collaborative perception (CP) is a promising method for safe connected and autonomous driving, which enables multiple vehicles to share sensing information to enhance perception performance. However, compared with single-vehicle perception, the openness of a CP system makes it more vulnerable to malicious attacks that can inject malicious information to mislead the perception of an ego vehicle, resulting in severe risks for safe driving. To mitigate such vulnerability, we first propose a new paradigm for malicious agent detection that effectively identifies malicious agents at the feature level without requiring verification of final perception results, significantly reducing computational overhead. Building on this paradigm, we introduce CP-GuardBench, the first comprehensive dataset provided to train and evaluate various malicious agent detection methods for CP systems. Furthermore, we develop a robust defense method called CP-Guard+, which enhances the margin between the representations of benign and malicious features through a carefully designed Dual-Centered Contrastive Loss (DCCLoss). Finally, we conduct extensive experiments on both CP-GuardBench and V2X-Sim, and demonstrate the superiority of CP-Guard+.

cs.CR↗

arXiv2025

Rethinking Membership Inference Attacks Against Transfer Learning

Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain limited-explored in transfer learning. The interaction between teacher and student models in transfer learning has not been thoroughly explored in MIAs, potentially resulting in an under-examined aspect of privacy vulnerabilities within transfer learning. In this paper, we propose a new MIA vector against transfer learning, to determine whether a specific data point was used to train the teacher model while only accessing the student model in a white-box setting. Our method delves into the intricate relationship between teacher and student models, analyzing the discrepancies in hidden layer representations between the student model and its shadow counterpart. These identified differences are then adeptly utilized to refine the shadow model's training process and to inform membership inference decisions effectively. Our method, evaluated across four datasets in diverse transfer learning tasks, reveals that even when an attacker only has access to the student model, the teacher model's training data remains susceptible to MIAs. We believe our work unveils the unexplored risk of membership inference in transfer learning.

cs.CR↗

arXiv2024

Adaptive Communications in Collaborative Perception with Domain Alignment for Autonomous Driving

Collaborative perception among multiple connected and autonomous vehicles can greatly enhance perceptive capabilities by allowing vehicles to exchange supplementary information via communications. Despite advances in previous approaches, challenges still remain due to channel variations and data heterogeneity among collaborative vehicles. To address these issues, we propose ACC-DA, a channel-aware collaborative perception framework to dynamically adjust the communication graph and minimize the average transmission delay while mitigating the side effects from the data heterogeneity. Our novelties lie in three aspects. We first design a transmission delay minimization method, which can construct the communication graph and minimize the transmission delay according to different channel information state. We then propose an adaptive data reconstruction mechanism, which can dynamically adjust the rate-distortion trade-off to enhance perception efficiency. Moreover, it minimizes the temporal redundancy during data transmissions. Finally, we conceive a domain alignment scheme to align the data distribution from different vehicles, which can mitigate the domain gap between different vehicles and improve the performance of the target task. Comprehensive experiments demonstrate the effectiveness of our method in comparison to the existing state-of-the-art works.

cs.AI↗

arXiv2024

Secure Traffic Sign Recognition: An Attention-Enabled Universal Image Inpainting Mechanism against Light Patch Attacks

Traffic sign recognition systems play a crucial role in assisting drivers to make informed decisions while driving. However, due to the heavy reliance on deep learning technologies, particularly for future connected and autonomous driving, these systems are susceptible to adversarial attacks that pose significant safety risks to both personal and public transportation. Notably, researchers recently identified a new attack vector to deceive sign recognition systems: projecting well-designed adversarial light patches onto traffic signs. In comparison with traditional adversarial stickers or graffiti, these emerging light patches exhibit heightened aggression due to their ease of implementation and outstanding stealthiness. To effectively counter this security threat, we propose a universal image inpainting mechanism, namely, SafeSign. It relies on attention-enabled multi-view image fusion to repair traffic signs contaminated by adversarial light patches, thereby ensuring the accurate sign recognition. Here, we initially explore the fundamental impact of malicious light patches on the local and global feature spaces of authentic traffic signs. Then, we design a binary mask-based U-Net image generation pipeline outputting diverse contaminated sign patterns, to provide our image inpainting model with needed training data. Following this, we develop an attention mechanism-enabled neural network to jointly utilize the complementary information from multi-view images to repair contaminated signs. Finally, extensive experiments are conducted to evaluate SafeSign's effectiveness in resisting potential light patch-based attacks, bringing an average accuracy improvement of 54.8% in three widely-used sign recognition models

cs.CV↗

arXiv2024

Fingerprinting Image-to-Image Generative Adversarial Networks

Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human resources, the copyright protection of GANs is urgently needed. This paper presents a novel fingerprinting scheme for the Intellectual Property (IP) protection of image-to-image GANs based on a trusted third party. We break through the stealthiness and robustness bottlenecks suffered by previous fingerprinting methods for classification models being naively transferred to GANs. Specifically, we innovatively construct a composite deep learning model from the target GAN and a classifier. Then we generate fingerprint samples from this composite model, and embed them in the classifier for effective ownership verification. This scheme inspires some concrete methodologies to practically protect the modern image-to-image translation GANs. Theoretical analysis proves that these methods can satisfy different security requirements necessary for IP protection. We also conduct extensive experiments to show that our solutions outperform existing strategies.

cs.CR↗

arXiv2024

Backdoor Attacks against Image-to-Image Networks

Recently, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks such as image super-resolution and denoising. Despite their remarkable performance, the backdoor vulnerability of I2I networks has not been explored. To fill this research gap, we conduct a comprehensive investigation on the susceptibility of I2I networks to backdoor attacks. Specifically, we propose a novel backdoor attack technique, where the compromised I2I network behaves normally on clean input images, yet outputs a predefined image of the adversary for malicious input images containing the trigger. To achieve this I2I backdoor attack, we propose a targeted universal adversarial perturbation (UAP) generation algorithm for I2I networks, where the generated UAP is used as the backdoor trigger. Additionally, in the backdoor training process that contains the main task and the backdoor task, multi-task learning (MTL) with dynamic weighting methods is employed to accelerate convergence rates. In addition to attacking I2I tasks, we extend our I2I backdoor to attack downstream tasks, including image classification and object detection. Extensive experiments demonstrate the effectiveness of the I2I backdoor on state-of-the-art I2I network architectures, as well as the robustness against different mainstream backdoor defenses.

cs.CV↗

arXiv2024

Security Analysis of WiFi-based Sensing Systems: Threats from Perturbation Attacks

Deep learning technologies are pivotal in enhancing the performance of WiFi-based wireless sensing systems. However, they are inherently vulnerable to adversarial perturbation attacks, and regrettably, there is lacking serious attention to this security issue within the WiFi sensing community. In this paper, we elaborate such an attack, called WiIntruder, distinguishing itself with universality, robustness, and stealthiness, which serves as a catalyst to assess the security of existing WiFi-based sensing systems. This attack encompasses the following salient features: (1) Maximizing transferability by differentiating user-state-specific feature spaces across sensing models, leading to a universally effective perturbation attack applicable to common applications; (2) Addressing perturbation signal distortion caused by device synchronization and wireless propagation when critical parameters are optimized through a heuristic particle swarm-driven perturbation generation algorithm; and (3) Enhancing attack pattern diversity and stealthiness through random switching of perturbation surrogates generated by a generative adversarial network. Extensive experimental results confirm the practical threats of perturbation attacks to common WiFi-based services, including user authentication and respiratory monitoring.

cs.CR↗

arXiv2024

CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning

The increasing prevalence of audio deepfakes poses significant security threats, necessitating robust detection methods. While existing detection systems exhibit promise, their robustness against malicious audio manipulations remains underexplored. To bridge the gap, we undertake the first comprehensive study of the susceptibility of the most widely adopted audio deepfake detectors to manipulation attacks. Surprisingly, even manipulations like volume control can significantly bypass detection without affecting human perception. To address this, we propose CLAD (Contrastive Learning-based Audio deepfake Detector) to enhance the robustness against manipulation attacks. The key idea is to incorporate contrastive learning to minimize the variations introduced by manipulations, therefore enhancing detection robustness. Additionally, we incorporate a length loss, aiming to improve the detection accuracy by clustering real audios more closely in the feature space. We comprehensively evaluated the most widely adopted audio deepfake detection models and our proposed CLAD against various manipulation attacks. The detection models exhibited vulnerabilities, with FAR rising to 36.69%, 31.23%, and 51.28% under volume control, fading, and noise injection, respectively. CLAD enhanced robustness, reducing the FAR to 0.81% under noise injection and consistently maintaining an FAR below 1.63% across all tests. Our source code and documentation are available in the artifact repository (https://github.com/CLAD23/CLAD).

cs.CR↗

arXiv2024

SmartCooper: Vehicular Collaborative Perception with Adaptive Fusion and Judger Mechanism

In recent years, autonomous driving has garnered significant attention due to its potential for improving road safety through collaborative perception among connected and autonomous vehicles (CAVs). However, time-varying channel variations in vehicular transmission environments demand dynamic allocation of communication resources. Moreover, in the context of collaborative perception, it is important to recognize that not all CAVs contribute valuable data, and some CAV data even have detrimental effects on collaborative perception. In this paper, we introduce SmartCooper, an adaptive collaborative perception framework that incorporates communication optimization and a judger mechanism to facilitate CAV data fusion. Our approach begins with optimizing the connectivity of vehicles while considering communication constraints. We then train a learnable encoder to dynamically adjust the compression ratio based on the channel state information (CSI). Subsequently, we devise a judger mechanism to filter the detrimental image data reconstructed by adaptive decoders. We evaluate the effectiveness of our proposed algorithm on the OpenCOOD platform. Our results demonstrate a substantial reduction in communication costs by 23.10\% compared to the non-judger scheme. Additionally, we achieve a significant improvement on the average precision of Intersection over Union (AP@IoU) by 7.15\% compared with state-of-the-art schemes.

cs.CV↗

arXiv2023

Alleviating the Effect of Data Imbalance on Adversarial Training

In this paper, we study adversarial training on datasets that obey the long-tailed distribution, which is practical but rarely explored in previous works. Compared with conventional adversarial training on balanced datasets, this process falls into the dilemma of generating uneven adversarial examples (AEs) and an unbalanced feature embedding space, causing the resulting model to exhibit low robustness and accuracy on tail data. To combat that, we theoretically analyze the lower bound of the robust risk to train a model on a long-tailed dataset to obtain the key challenges in addressing the aforementioned dilemmas. Based on it, we propose a new adversarial training framework -- Re-balancing Adversarial Training (REAT). This framework consists of two components: (1) a new training strategy inspired by the effective number to guide the model to generate more balanced and informative AEs; (2) a carefully constructed penalty function to force a satisfactory feature space. Evaluation results on different datasets and model structures prove that REAT can effectively enhance the model's robustness and preserve the model's clean accuracy. The code can be found in https://github.com/GuanlinLee/REAT.

cs.LG↗

arXiv2023

Mercury: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator

DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerators is the confidentiality of the deployed models: model inference execution on the accelerators could leak side-channel information, which enables an adversary to preciously recover the model details. Such model extraction attacks can not only compromise the intellectual property of DNN models, but also facilitate some adversarial attacks. Although previous works have demonstrated a number of side-channel techniques to extract models from DNN accelerators, they are not practical for two reasons. (1) They only target simplified accelerator implementations, which have limited practicality in the real world. (2) They require heavy human analysis and domain knowledge. To overcome these limitations, this paper presents Mercury, the first automated remote side-channel attack against the off-the-shelf Nvidia DNN accelerator. The key insight of Mercury is to model the side-channel extraction process as a sequence-to-sequence problem. The adversary can leverage a time-to-digital converter (TDC) to remotely collect the power trace of the target model's inference. Then he uses a learning model to automatically recover the architecture details of the victim model from the power trace without any prior knowledge. The adversary can further use the attention mechanism to localize the leakage points that contribute most to the attack. Evaluation results indicate that Mercury can keep the error rate of model extraction below 1%.

cs.CR↗