arXiv subjects

Wenjie Qu

Publications and source records attributed to Wenjie Qu.

33 records · Page 2Linked to original sources

arXiv2025

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by incorporating external knowledge bases, but this may expose them to extraction attacks, leading to potential copyright and privacy risks. However, existing extraction methods typically rely on malicious inputs such as prompt injection or jailbreaking, making them easily detectable via input- or output-level detection. In this paper, we introduce Implicit Knowledge Extraction Attack (IKEA), which conducts Knowledge Extraction on RAG systems through benign queries. Specifically, IKEA first leverages anchor concepts-keywords related to internal knowledge-to generate queries with a natural appearance, and then designs two mechanisms that lead anchor concepts to thoroughly "explore" the RAG's knowledge: (1) Experience Reflection Sampling, which samples anchor concepts based on past query-response histories, ensuring their relevance to the topic; (2) Trust Region Directed Mutation, which iteratively mutates anchor concepts under similarity constraints to further exploit the embedding space. Extensive experiments demonstrate IKEA's effectiveness under various defenses, surpassing baselines by over 80% in extraction efficiency and 90% in attack success rate. Moreover, the substitute RAG system built from IKEA's extractions shows comparable performance to the original RAG and outperforms those based on baselines across multiple evaluation tasks, underscoring the stealthy copyright infringement risk in RAG systems.

cs.CR↗

arXiv2025

Parallax: Efficient LLM Inference Service over Decentralized Environment

Deploying a large language model (LLM) inference service remains costly because centralized serving depends on specialized GPU clusters and high-bandwidth interconnects in datacenters. An appealing alternative is to leverage collaborative decentralized GPU pools. However, heterogeneity in GPU and limited interconnected network bandwidth, along with potentially dynamic availability, make efficient scheduling the central challenge in this scenario. In this paper, we present Parallax, a decentralized LLM serving system that turns a pool of heterogeneous GPUs into an efficient inference platform via a two-phase scheduler. Parallax decomposes planning into (i) model allocation, which places layers of each replica across diverse GPUs to jointly optimize latency and throughput under memory and link-bandwidth constraints, and (ii) request-time GPU pipeline selection, which stitches layers from different replicas into end-to-end execution chains that balance load and adapt to current conditions. We implement Parallax and evaluate it on open-source LLMs deployed over real volunteer nodes. Parallax consistently reduces latency and increases throughput relative to decentralized baselines, demonstrating that principled scheduling can make volunteer compute a practical, affordable substrate for LLM inference. Github Repo at: https://github.com/GradientHQ/parallax.

cs.DC↗

arXiv2025

Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation

In recent years, text-to-image (T2I) diffusion models have gained significant attention for their ability to generate high quality images reflecting text prompts. However, their growing popularity has also led to the emergence of backdoor threats, posing substantial risks. Currently, effective defense strategies against such threats are lacking due to the diversity of backdoor targets in T2I synthesis. In this paper, we propose NaviT2I, an efficient input-level backdoor defense framework against diverse T2I backdoors. Our approach is based on the new observation that trigger tokens tend to induce significant neuron activation variation in the early stage of the diffusion generation process, a phenomenon we term Early-step Activation Variation. Leveraging this insight, NaviT2I navigates T2I models to prevent malicious inputs by analyzing Neuron activation variations caused by input tokens. Extensive experiments show that NaviT2I significantly outperforms the baselines in both effectiveness and efficiency across diverse datasets, various T2I backdoors, and different model architectures including UNet and DiT. Furthermore, we show that our method remains effective under potential adaptive attacks.

cs.CR↗

arXiv2025

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models

Text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images but also raise people's concerns about generating harmful or misleading content. While extensive approaches have been proposed to erase unwanted concepts without requiring retraining from scratch, they inadvertently degrade performance on normal generation tasks. In this work, we propose Interpret then Deactivate (ItD), a novel framework to enable precise concept removal in T2I diffusion models while preserving overall performance. ItD first employs a sparse autoencoder (SAE) to interpret each concept as a combination of multiple features. By permanently deactivating the specific features associated with target concepts, we repurpose SAE as a zero-shot classifier that identifies whether the input prompt includes target concepts, allowing selective concept erasure in diffusion models. Moreover, we demonstrate that ItD can be easily extended to erase multiple concepts without requiring further training. Comprehensive experiments across celebrity identities, artistic styles, and explicit content demonstrate ItD's effectiveness in eliminating targeted concepts without interfering with normal concept generation. Additionally, ItD is also robust against adversarial prompts designed to circumvent content filters. Code is available at: https://github.com/NANSirun/Interpret-then-deactivate.

cs.CV↗

arXiv2025

Towards Collaborative Anti-Money Laundering Among Financial Institutions

Money laundering is the process that intends to legalize the income derived from illicit activities, thus facilitating their entry into the monetary flow of the economy without jeopardizing their source. It is crucial to identify such activities accurately and reliably in order to enforce anti-money laundering (AML). Despite considerable efforts to AML, a large number of such activities still go undetected. Rule-based methods were first introduced and are still widely used in current detection systems. With the rise of machine learning, graph-based learning methods have gained prominence in detecting illicit accounts through the analysis of money transfer graphs. Nevertheless, these methods generally assume that the transaction graph is centralized, whereas in practice, money laundering activities usually span multiple financial institutions. Due to regulatory, legal, commercial, and customer privacy concerns, institutions tend not to share data, restricting their utility in practical usage. In this paper, we propose the first algorithm that supports performing AML over multiple institutions while protecting the security and privacy of local data. To evaluate, we construct Alipay-ECB, a real-world dataset comprising digital transactions from Alipay, the world's largest mobile payment platform, alongside transactions from E-Commerce Bank (ECB). The dataset includes over 200 million accounts and 300 million transactions, covering both intra-institution transactions and those between Alipay and ECB. This makes it the largest real-world transaction graph available for analysis. The experimental results demonstrate that our methods can effectively identify cross-institution money laundering subgroups. Additionally, experiments on synthetic datasets also demonstrate that our method is efficient, requiring only a few minutes on datasets with millions of transactions.

cs.SI↗

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

Efficient Reasoning via Chain of Unconscious Thought

Large Reasoning Models (LRMs) achieve promising performance but compromise token efficiency due to verbose reasoning processes. Unconscious Thought Theory (UTT) posits that complex problems can be solved more efficiently through internalized cognitive processes. Inspired by UTT, we propose a new reasoning paradigm, termed Chain of Unconscious Thought (CoUT), to improve the token efficiency of LRMs by guiding them to mimic human unconscious thought and internalize reasoning processes. Concretely, we first prompt the model to internalize the reasoning by thinking in the hidden layer. Then, we design a bag of token-efficient strategies to further help models reduce unnecessary tokens yet preserve the performance. Our work reveals that models may possess beneficial unconscious thought, enabling improved efficiency without sacrificing performance. Extensive experiments demonstrate the effectiveness of CoUT. Remarkably, it surpasses CoT by reducing token usage by 47.62% while maintaining comparable accuracy, as shown in Figure 1. The code of CoUT is available at this link: https://github.com/Rohan-GRH/CoUT

cs.CL↗

arXiv2025

Prompt Inversion Attack against Collaborative Inference of Large Language Models

Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high resource requirements, making deployment expensive and limiting widespread development. The collaborative inference is a promising solution for this problem, in which users collaborate by each hosting a subset of layers and transmitting intermediate activation. Many companies are building collaborative inference platforms to reduce LLM serving costs, leveraging users' underutilized GPUs. Despite widespread interest in collaborative inference within academia and industry, the privacy risks associated with LLM collaborative inference have not been well studied. This is largely because of the challenge posed by inverting LLM activation due to its strong non-linearity. In this paper, to validate the severity of privacy threats in LLM collaborative inference, we introduce the concept of prompt inversion attack (PIA), where a malicious participant intends to recover the input prompt through the activation transmitted by its previous participant. Extensive experiments show that our PIA method substantially outperforms existing baselines. For example, our method achieves an 88.4\% token accuracy on the Skytrax dataset with the Llama-65B model when inverting the maximum number of transformer layers, while the best baseline method only achieves 22.8\% accuracy. The results verify the effectiveness of our PIA attack and highlights its practical threat to LLM collaborative inference systems.

cs.CR↗

arXiv2025

Provably Robust Multi-bit Watermarking for AI-generated Text

Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises ethical concerns. Watermarking is a key technique to address these concerns, which embeds a message (e.g., a bit string) into a text generated by an LLM. By embedding the user ID (represented as a bit string) into generated texts, we can trace generated texts to the user, known as content source tracing. The major limitation of existing watermarking techniques is that they achieve sub-optimal performance for content source tracing in real-world scenarios. The reason is that they cannot accurately or efficiently extract a long message from a generated text. We aim to address the limitations. In this work, we introduce a new watermarking method for LLM-generated text grounded in pseudo-random segment assignment. We also propose multiple techniques to further enhance the robustness of our watermarking algorithm. We conduct extensive experiments to evaluate our method. Our experimental results show that our method substantially outperforms existing baselines in both accuracy and robustness on benchmark datasets. For instance, when embedding a message of length 20 into a 200-token generated text, our method achieves a match rate of $97.6\%$, while the state-of-the-art work Yoo et al. only achieves $49.2\%$. Additionally, we prove that our watermark can tolerate edits within an edit distance of 17 on average for each paragraph under the same setting.

cs.CR↗

arXiv2023

A Certified Radius-Guided Attack Framework to Image Segmentation Models

Image segmentation is an important problem in many safety-critical applications. Recent studies show that modern image segmentation models are vulnerable to adversarial perturbations, while existing attack methods mainly follow the idea of attacking image classification models. We argue that image segmentation and classification have inherent differences, and design an attack framework specially for image segmentation models. Our attack framework is inspired by certified radius, which was originally used by defenders to defend against adversarial perturbations to classification models. We are the first, from the attacker perspective, to leverage the properties of certified radius and propose a certified radius guided attack framework against image segmentation models. Specifically, we first adapt randomized smoothing, the state-of-the-art certification method for classification models, to derive the pixel's certified radius. We then focus more on disrupting pixels with relatively smaller certified radii and design a pixel-wise certified radius guided loss, when plugged into any existing white-box attack, yields our certified radius-guided white-box attack. Next, we propose the first black-box attack to image segmentation models via bandit. We design a novel gradient estimator, based on bandit feedback, which is query-efficient and provably unbiased and stable. We use this gradient estimator to design a projected bandit gradient descent (PBGD) attack, as well as a certified radius-guided PBGD (CR-PBGD) attack. We prove our PBGD and CR-PBGD attacks can achieve asymptotically optimal attack performance with an optimal rate. We evaluate our certified-radius guided white-box and black-box attacks on multiple modern image segmentation models and datasets. Our results validate the effectiveness of our certified radius-guided attack framework.

cs.CV↗

arXiv2023

REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service

Encoder as a service is an emerging cloud service. Specifically, a service provider first pre-trains an encoder (i.e., a general-purpose feature extractor) via either supervised learning or self-supervised learning and then deploys it as a cloud service API. A client queries the cloud service API to obtain feature vectors for its training/testing inputs when training/testing its classifier (called downstream classifier). A downstream classifier is vulnerable to adversarial examples, which are testing inputs with carefully crafted perturbation that the downstream classifier misclassifies. Therefore, in safety and security critical applications, a client aims to build a robust downstream classifier and certify its robustness guarantees against adversarial examples. What APIs should the cloud service provide, such that a client can use any certification method to certify the robustness of its downstream classifier against adversarial examples while minimizing the number of queries to the APIs? How can a service provider pre-train an encoder such that clients can build more certifiably robust downstream classifiers? We aim to answer the two questions in this work. For the first question, we show that the cloud service only needs to provide two APIs, which we carefully design, to enable a client to certify the robustness of its downstream classifier with a minimal number of queries to the APIs. For the second question, we show that an encoder pre-trained using a spectral-norm regularization term enables clients to build more robust downstream classifiers.

cs.CR↗

arXiv2022

Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning

Classifiers in supervised learning have various security and privacy issues, e.g., 1) data poisoning attacks, backdoor attacks, and adversarial examples on the security side as well as 2) inference attacks and the right to be forgotten for the training data on the privacy side. Various secure and privacy-preserving supervised learning algorithms with formal guarantees have been proposed to address these issues. However, they suffer from various limitations such as accuracy loss, small certified security guarantees, and/or inefficiency. Self-supervised learning is an emerging technique to pre-train encoders using unlabeled data. Given a pre-trained encoder as a feature extractor, supervised learning can train a simple yet accurate classifier using a small amount of labeled training data. In this work, we perform the first systematic, principled measurement study to understand whether and when a pre-trained encoder can address the limitations of secure or privacy-preserving supervised learning algorithms. Our key findings are that a pre-trained encoder substantially improves 1) both accuracy under no attacks and certified security guarantees against data poisoning and backdoor attacks of state-of-the-art secure learning algorithms (i.e., bagging and KNN), 2) certified security guarantees of randomized smoothing against adversarial examples without sacrificing its accuracy under no attacks, 3) accuracy of differentially private classifiers, and 4) accuracy and/or efficiency of exact machine unlearning.

cs.CR↗

arXiv2022

MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples

Multi-label classification, which predicts a set of labels for an input, has many applications. However, multiple recent studies showed that multi-label classification is vulnerable to adversarial examples. In particular, an attacker can manipulate the labels predicted by a multi-label classifier for an input via adding carefully crafted, human-imperceptible perturbation to it. Existing provable defenses for multi-class classification achieve sub-optimal provable robustness guarantees when generalized to multi-label classification. In this work, we propose MultiGuard, the first provably robust defense against adversarial examples to multi-label classification. Our MultiGuard leverages randomized smoothing, which is the state-of-the-art technique to build provably robust classifiers. Specifically, given an arbitrary multi-label classifier, our MultiGuard builds a smoothed multi-label classifier via adding random noise to the input. We consider isotropic Gaussian noise in this work. Our major theoretical contribution is that we show a certain number of ground truth labels of an input are provably in the set of labels predicted by our MultiGuard when the $\ell_2$-norm of the adversarial perturbation added to the input is bounded. Moreover, we design an algorithm to compute our provable robustness guarantees. Empirically, we evaluate our MultiGuard on VOC 2007, MS-COCO, and NUS-WIDE benchmark datasets. Our code is available at: \url{https://github.com/quwenjie/MultiGuard}

cs.CR↗

arXiv2022

jTrans: Jump-Aware Transformer for Binary Code Similarity

Binary code similarity detection (BCSD) has important applications in various fields such as vulnerability detection, software component analysis, and reverse engineering. Recent studies have shown that deep neural networks (DNNs) can comprehend instructions or control-flow graphs (CFG) of binary code and support BCSD. In this study, we propose a novel Transformer-based approach, namely jTrans, to learn representations of binary code. It is the first solution that embeds control flow information of binary code into Transformer-based language models, by using a novel jump-aware representation of the analyzed binaries and a newly-designed pre-training task. Additionally, we release to the community a newly-created large dataset of binaries, BinaryCorp, which is the most diverse to date. Evaluation results show that jTrans outperforms state-of-the-art (SOTA) approaches on this more challenging dataset by 30.5% (i.e., from 32.0% to 62.5%). In a real-world task of known vulnerability searching, jTrans achieves a recall that is 2X higher than existing SOTA baselines.

cs.CR↗

arXiv2021

EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning

Given a set of unlabeled images or (image, text) pairs, contrastive learning aims to pre-train an image encoder that can be used as a feature extractor for many downstream tasks. In this work, we propose EncoderMI, the first membership inference method against image encoders pre-trained by contrastive learning. In particular, given an input and a black-box access to an image encoder, EncoderMI aims to infer whether the input is in the training dataset of the image encoder. EncoderMI can be used 1) by a data owner to audit whether its (public) data was used to pre-train an image encoder without its authorization or 2) by an attacker to compromise privacy of the training data when it is private/sensitive. Our EncoderMI exploits the overfitting of the image encoder towards its training data. In particular, an overfitted image encoder is more likely to output more (or less) similar feature vectors for two augmented versions of an input in (or not in) its training dataset. We evaluate EncoderMI on image encoders pre-trained on multiple datasets by ourselves as well as the Contrastive Language-Image Pre-training (CLIP) image encoder, which is pre-trained on 400 million (image, text) pairs collected from the Internet and released by OpenAI. Our results show that EncoderMI can achieve high accuracy, precision, and recall. We also explore a countermeasure against EncoderMI via preventing overfitting through early stopping. Our results show that it achieves trade-offs between accuracy of EncoderMI and utility of the image encoder, i.e., it can reduce the accuracy of EncoderMI, but it also incurs classification accuracy loss of the downstream classifiers built based on the image encoder.

cs.CR↗