Searcharxiv⌕ Search

arXiv subjects

Qingni Shen

Publications and source records attributed to Qingni Shen.

At least 19 recordsLinked to original sources

Security of Deep Research Agents: Attack Surface, Defenses, Benchmarks, and Agenda Seeding against Research Planning

Deep research and agentic search agents autonomously retrieve content from the open web and generate reports with citations, and their outputs are often taken directly as research conclusions. This paper systematizes security research in this area along four stages, namely retrieval, planning, evidence integration, and report generation. We present a unified threat model, a taxonomy of attacks and defenses, and a review of evaluation benchmarks, and we align the area dimension by dimension with retrieval-augmented generation (RAG) poisoning, prompt injection, and generative engine optimization (GEO). Coding 34 primary studies shows that only 26.5% of them involve the planning stage, and none performs an end-to-end poisoning evaluation on commercial products. To address this gap, we propose the agenda seeding attack, in which the attacker writes no instructions and only introduces a fictitious evaluation metric. Across 3,520 sandboxed research runs under the same budget, GEO and prompt injection are nearly ineffective, whereas agenda seeding makes the attacker's target the top pick in 16% to 28% of reports. Injection detection and query anchoring fail against it, verification prompting hurts utility, and our proposed provenance tagging preserves utility but can be bypassed by multi-site bait. Finally, we propose eight research directions.

cs.CR↗

PRISM: Causal Counterfactual Minimization of Agent Tool Privileges via Information Bottleneck Role Induction

This paper shifts the object of role engineering from human users to large language model (LLM) agents, and proposes PRISM to address the over-authorization that arises when an agent obtains full tool privileges through the Model Context Protocol (MCP). PRISM formulates whether a tool is necessary for a task as an intervenable causal proposition, and applies structured interventions in a sandbox to learn a counterfactual necessity model. It then compresses trajectories into discrete latent variables through an information bottleneck, and determines the number of roles from the knee of the rate-distortion curve. Finally, it formalizes pruning as a bilevel Stackelberg game, in which a generative flow network samples diverse near-optimal solutions. On three public benchmarks, AgentDojo, $τ$-bench and ToolEmu, PRISM compresses the number of authorized tools per role by 78.3%, attains a task success rate of 78.2%, reaches a counterfactual necessity accuracy of 88.7%, and lowers the blast radius to 15.9%.

cs.CR↗

CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection

Agents extend their capabilities through reusable skills that package instructions, executable code, and resources. Composing these skills enables complex task workflows, but their dependencies can also connect malicious operations across skills, making their combined intent difficult to identify through individual-package auditing. We introduce CoRedSkill, a compositional red-teaming method that forms stealthy attacks through cooperating skills while preserving their original utility. CoRedSkill decomposes an existing workflow into interdependent skills and embeds attack operations in task functions through abstract syntax tree (AST) rewriting, with skill instructions guiding the agent to autonomously select and invoke the relevant skills, and workflow dependencies and intermediate artifacts connecting the injected operations during task execution. We construct a benchmark of 150 cases covering 50 tasks and three attack objectives to evaluate attack success, task completion, and audit detection. In the main evaluation, CoRedSkill achieves 98.0% attack success and 95.3% task success with a 3.3% detection rate, and a joint success rate of 90.7% (attack success, task completion, and audit evasion in the same case) compared with 6.7--42.7% for the four baselines. Skill compositions can therefore complete legitimate tasks while carrying out unauthorized operations that evade auditing.

cs.CR↗

zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models

Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at Transformer scale. We present zkLLMPoT, a zero-knowledge framework that certifies auditor-defined properties of a trained checkpoint through forward evaluation rather than verification of its optimization trajectory. zkLLMPoT includes 2 phases: 1) The trainer fixes the architecture and the model weights are committed. Then the auditor selects challenge sequences, preventing the trainer from modifying the checkpoint in response to the audit data. 2) Then the trainer proves the objective value attained by the committed model on those sequences. This formulation makes the certification cost independent of the number of training iterations, without revealing model weights or requiring access to private training data. We build on sumcheck- and lookup-based arguments to certify Transformer computations, while supporting next-token loss and task-specific audit objectives. Across four model families, operator-level benchmarks yield proving times of 41-59 seconds for 1.1-1.5B-parameter models and 131 seconds at 13B for the covered operators, with verification below half a second at a sequence length of 512.

cs.AI↗

ACLE-MCP: Attested Capability Leases for Execution-Time Trust in Remote LLM Tool Use

Remote Model Context Protocol (MCP) services enable large language model agents to invoke external tools, but OAuth authorization alone does not ensure that a later tool call is executed by the provider-side workload that the relying party intended to trust. An endpoint may remain authorized even after execution shifts to a substituted workload, relies on stale appraisal state, reuses authority transferred from another sender, or traverses an undeclared downstream component. We call this problem the post-authorization execution trust gap. We present ACLE-MCP, an invocation-scoped architecture that couples delegated authorization, workload appraisal, and resource-side execution admission. For protected calls, ACLE-MCP issues a short-lived, sender-constrained capability lease that binds the expected workload, freshness requirement, operation, object and parameter bounds, downstream constraints, and receipt obligations. A provider-side Execution Gate consumes the lease immediately before protected tool logic begins. We implement a runnable prototype with Keycloak/OIDC validation, an MCP Python SDK server, and an optional vTPM quote-verification backend. Controlled security experiments and an agent tool-use extension show that weaker authorization or connect-time attestation modes leave distinct post-authorization attacks open, whereas full ACLE-MCP blocks all evaluated attack families while preserving all benign tasks. In the locally simulated agent extension, the complete design increases request-level pooled p95 latency on normal allowed calls by 25.7% relative to OAuth-only. These results indicate that invocation-time binding between call authority and current workload state is a practical complement to OAuth-protected remote tool use.

cs.CR↗

JITterFlip: Uncovering Fault Attack Surfaces in JIT-Compiled LLM Serving

LLMs are widely deployed through cloud-hosted inference services, where Just-in-Time (JIT) compilation is used to reduce recurring framework and GPU-launch overhead. JIT serving introduces a host-side control plane that selects compiled artifacts and orchestrates their execution on the GPU. Meanwhile, the shared cloud setting has motivated a growing body of bit-flip attacks (BFAs) against LLM/DNN inference. Most existing BFAs target model parameters or weights and require model-specific knowledge. A smaller body of work reduces this dependency by faulting executable code, yet still corrupts code that directly implements model computation, limiting their attack effect to inference depletion. We present JITterFlip, the first BFA targeting the host-side JIT serving control plane of GPU-based LLM inference. By faulting CPU-resident serving decisions rather than model computation, JITterFlip enables both gibberish output generation and a correct-output sponge attack. To identify exploitable targets in a large JIT compiler stack, JITterFlip develops a decision-guided fault-vulnerable code analysis. Across four text and multimodal LLM workloads, the identified vulnerable code faults exhibit cross-model transferability, produce gibberish outputs with PPL ratios of $15.45\times$ to $2.48{\times}10^{6}\times$, and demonstrate correct-output sponge attacks with latency amplification of $2.03\times$ to $181.90\times$. JITterFlip also bypasses recent BFA defenses for LLMs while retaining both attack effects. Last, we demonstrate end-to-end Rowhammer attacks across four LLMs: a single bit flip in CPU-resident branch code propagates across the CPU-GPU boundary to disrupt GPU-executed inference without direct access to GPU memory, reaching up to $7.23{\times}10^{6}\times$ PPL amplification or $124.97\times$ latency amplification while preserving the exact generated output.

cs.CR↗

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy. To facilitate practical deployment on resource-constrained edge devices, Spiking Neural Networks (SNNs) have emerged as a promising alternative to traditional Artificial Neural Networks (ANNs) due to their sparse computing mechanisms and high energy efficiency. However, jointly training ANNs and SNNs exposes a challenge of representational misalignment, which is intrinsically caused by differences in information representation, specifically the semantic gap between continuous real-valued activations in ANNs and discrete spatio-temporal spikes in SNNs. To overcome this barrier, we propose AS-FedBridge, a novel federated learning framework tailored for mixed ANN-SNN clients. AS-FedBridge features a lightweight Bridge equipped with a Pseudo-Spike Interface, which effectively projects continuous signals into a spike-compatible space to facilitate ANN-SNN alignment. Given the absence of existing mixed ANN-SNN federated frameworks, we establish a comprehensive benchmark to evaluate against multiple advanced heterogeneous FL methods. Our empirical analysis demonstrates a positive correlation between the degree of ANN-SNN alignment and the collaborative FL performance. Across four datasets, AS-FedBridge consistently demonstrates advanced accuracy while mitigating extreme scale, architecture, and client heterogeneity challenge. Furthermore, our framework enables a highly controllable trade-off between model performance and resource efficiency. AS-FedBridge accomplishes these robust performance gains while introducing only marginal computational overhead, establishing a robust and practical foundation for mixed ANN-SNN federated learning systems.

cs.LG↗

Exploring Information Seeking Agent Consolidation

Information-seeking agents have emerged as a powerful paradigm for knowledge-intensive tasks, yet today's systems remain specialized for the open web, documents, or local knowledge bases, hindering scalable and cross-domain deployment. We present the first systematic empirical study of consolidating these information-seeking agents into a single foundation agentic model. We compare two paradigms -- \emph{data-level mixing}, which trains a unified model on a mixture of datasets, and \emph{parameter-level merging}, which merges independently trained experts in parameter space -- across 3 training scenarios, evaluating \textbf{26} representative parameter-level methods on \textbf{10} benchmarks. To compare across heterogeneous benchmarks, we introduce a geometric Composite Score and an Imbalance Score that describe overall performance and task skew. Our analysis shows that (i) well-designed parameter-level merging attains parity with data mixing at a fraction of its training cost and is order-agnostic; (ii) parameter-level merging structurally preserves out-of-domain capabilities that data mixing universally forgets; and (iii) cross-scenario stability is strongly tied to consolidation quality. We distil our observations into a method-selection guide and design principles for next-generation merging operators.

cs.AI↗

FedSRD: Sparsify-Reconstruct-Decompose for Communication-Efficient Federated Large Language Models Fine-Tuning

The current paradigm of training large language models (LLMs) on public available Web data is becoming unsustainable as high-quality data sources in specialized domains near exhaustion. Federated Learning (FL) emerges as a practical solution for the next generation of AI on a decentralized Web, enabling privacy-preserving collaborative fine-tuning on decentralized private data. While Low-Rank Adaptation (LoRA) is standard for efficient fine-tuning, its federated application faces a critical bottleneck: communication overhead under heterogeneous network conditions. Structural redundancy in LoRA parameters increases communication costs and causes aggregation conflicts. To address this, we propose FedSRD, a Sparsify-Reconstruct-Decompose framework for communication-efficient federated LLM fine-tuning. We introduce importance-aware sparsification to reduce the upload parameter count while preserving the structural integrity of LoRA updates. The server aggregates updates in full-rank space to mitigate conflicts, then decomposes the global update into a sparse low-rank format for broadcast, ensuring a symmetrically efficient cycle. We also propose an efficient variant, FedSRD-e, to reduce computational overhead. Experiments on 10 benchmarks show our framework significantly reduces communication costs by up to 90\% while improving performance on heterogeneous client data.

cs.CL↗

Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch

Diffusion models enable high-fidelity image editing but can also be misused for unauthorized style imitation and harmful content generation. To mitigate these risks, proactive image protection methods embed small, often imperceptible adversarial perturbations into images before sharing to disrupt downstream editing or fine-tuning. However, in realistic post-release scenarios, content owners cannot control downstream processing pipelines, and protections optimized for a surrogate model may fail when attackers use mismatched diffusion pipelines. Existing purification methods can weaken protections but often sacrifice image quality and rarely examine architectural mismatch. We introduce a unified post-release purification framework to evaluate protection survivability under model mismatch. We propose two practical purifiers: VAE-Trans, which corrects protected images via latent-space projection, and EditorClean, which performs instruction-guided reconstruction with a Diffusion Transformer to exploit architectural heterogeneity. Both operate without access to protected images or defense internals. Across 2,100 editing tasks and six representative protection methods, EditorClean consistently restores editability. Compared to protected inputs, it improves PSNR by 3-6 dB and reduces FID by 50-70 percent on downstream edits, while outperforming prior purification baselines by about 2 dB PSNR and 30 percent lower FID. Our results reveal a purify-once, edit-freely failure mode: once purification succeeds, the protective signal is largely removed, enabling unrestricted editing. This highlights the need to evaluate protections under model mismatch and design defenses robust to heterogeneous attackers.

cs.CR↗

Personalized One-shot Federated Graph Learning for Heterogeneous Clients

Federated Graph Learning (FGL) has emerged as a promising paradigm for breaking data silos among distributed private graphs. In practical scenarios involving heterogeneous distributed graph data, personalized Federated Graph Learning (pFGL) aims to enhance model utility by training personalized models tailored to client needs. However, existing pFGL methods often require numerous communication rounds under heterogeneous graphs, leading to significant communication overhead and security concerns. While One-shot Federated Learning (OFL) enables collaboration in a single round, existing OFL methods are designed for image-centric tasks and are ineffective for graph data, leaving a critical gap in the field. Additionally, personalized models derived from existing methods suffer from bias, failing to effectively generalize to the minority. To address these challenges, we propose the first \textbf{O}ne-shot \textbf{p}ersonalized \textbf{F}ederated \textbf{G}raph \textbf{L}earning method (\textbf{O-pFGL}) for node classification, compatible with Secure Aggregation protocols for privacy preservation. Specifically, for effective graph learning in one communication round, our method estimates and aggregates class-wise feature distribution statistics to construct a global surrogate graph on the server, facilitating the training of a global graph model. To mitigate bias, we introduce a two-stage personalized training approach that adaptively balances local personal information and global insights from the surrogate graph, improving both personalization and generalization. Extensive experiments on 14 diverse real-world graph datasets demonstrate that our method significantly outperforms state-of-the-art baselines across various settings.

cs.LG↗

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↗

dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis

Federated learning has wide applications in the medical field. It enables knowledge sharing among different healthcare institutes while protecting patients' privacy. However, existing federated learning systems are typically centralized, requiring clients to upload client-specific knowledge to a central server for aggregation. This centralized approach would integrate the knowledge from each client into a centralized server, and the knowledge would be already undermined during the centralized integration before it reaches back to each client. Besides, the centralized approach also creates a dependency on the central server, which may affect training stability if the server malfunctions or connections are unstable. To address these issues, we propose a decentralized federated learning framework named dFLMoE. In our framework, clients directly exchange lightweight head models with each other. After exchanging, each client treats both local and received head models as individual experts, and utilizes a client-specific Mixture of Experts (MoE) approach to make collective decisions. This design not only reduces the knowledge damage with client-specific aggregations but also removes the dependency on the central server to enhance the robustness of the framework. We validate our framework on multiple medical tasks, demonstrating that our method evidently outperforms state-of-the-art approaches under both model homogeneity and heterogeneity settings.

cs.LG↗

Life-Cycle Routing Vulnerabilities of LLM Router

Large language models (LLMs) have achieved remarkable success in natural language processing, yet their performance and computational costs vary significantly. LLM routers play a crucial role in dynamically balancing these trade-offs. While previous studies have primarily focused on routing efficiency, security vulnerabilities throughout the entire LLM router life cycle, from training to inference, remain largely unexplored. In this paper, we present a comprehensive investigation into the life-cycle routing vulnerabilities of LLM routers. We evaluate both white-box and black-box adversarial robustness, as well as backdoor robustness, across several representative routing models under extensive experimental settings. Our experiments uncover several key findings: 1) Mainstream DNN-based routers tend to exhibit the weakest adversarial and backdoor robustness, largely due to their strong feature extraction capabilities that amplify vulnerabilities during both training and inference; 2) Training-free routers demonstrate the strongest robustness across different attack types, benefiting from the absence of learnable parameters that can be manipulated. These findings highlight critical security risks spanning the entire life cycle of LLM routers and provide insights for developing more robust models.

cs.CR↗

SoK: Understanding zk-SNARKs: The Gap Between Research and Practice

Zero-knowledge succinct non-interactive arguments of knowledge (zk-SNARKs) are a powerful tool for proving computation correctness, attracting significant interest from researchers, developers, and users. However, the complexity of zk-SNARKs has created gaps between these groups, hindering progress. Researchers focus on constructing efficient proving systems with stronger security and new properties, while developers and users prioritize toolchains, usability, and compatibility. In this work, we provide a comprehensive study of zk-SNARK, from theory to practice, pinpointing gaps and limitations. We first present a master recipe that unifies the main steps in converting a program into a zk-SNARK. We then classify existing zk-SNARKs according to their key techniques. Our classification addresses the main difference in practically valuable properties between existing zk-SNARK schemes. We survey over 40 zk-SNARKs since 2013 and provide a reference table listing their categories and properties. Following the steps in master recipe, we then survey 11 general-purpose popular used libraries. We elaborate on these libraries' usability, compatibility, efficiency and limitations. Since installing and executing these zk-SNARK systems is challenging, we also provide a completely virtual environment in which to run the compiler for each of them. We identify that the proving system is the primary focus in cryptography academia. In contrast, the constraint system presents a bottleneck in industry. To bridge this gap, we offer recommendations and advocate for the opensource community to enhance documentation, standardization and compatibility.

cs.CR↗

FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis

Federated learning has become a promising solution for collaboration among medical institutions. However, data owned by each institution would be highly heterogeneous and the distribution is always non-independent and identical distribution (non-IID), resulting in client drift and unsatisfactory performance. Despite existing federated learning methods attempting to solve the non-IID problems, they still show marginal advantages but rely on frequent communication which would incur high costs and privacy concerns. In this paper, we propose a novel federated learning method: \textbf{Fed}erated learning via \textbf{V}aluable \textbf{C}ondensed \textbf{K}nowledge (FedVCK). We enhance the quality of condensed knowledge and select the most necessary knowledge guided by models, to tackle the non-IID problem within limited communication budgets effectively. Specifically, on the client side, we condense the knowledge of each client into a small dataset and further enhance the condensation procedure with latent distribution constraints, facilitating the effective capture of high-quality knowledge. During each round, we specifically target and condense knowledge that has not been assimilated by the current model, thereby preventing unnecessary repetition of homogeneous knowledge and minimizing the frequency of communications required. On the server side, we propose relational supervised contrastive learning to provide more supervision signals to aid the global model updating. Comprehensive experiments across various medical tasks show that FedVCK can outperform state-of-the-art methods, demonstrating that it's non-IID robust and communication-efficient.

cs.LG↗

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy

Text-to-image diffusion models have achieved tremendous success in the field of controllable image generation, while also coming along with issues of privacy leakage and data copyrights. Membership inference arises in these contexts as a potential auditing method for detecting unauthorized data usage. While some efforts have been made on diffusion models, they are not applicable to text-to-image diffusion models due to the high computation overhead and enhanced generalization capabilities. In this paper, we first identify a conditional overfitting phenomenon in text-to-image diffusion models, indicating that these models tend to overfit the conditional distribution of images given the corresponding text rather than the marginal distribution of images only. Based on this observation, we derive an analytical indicator, namely Conditional Likelihood Discrepancy (CLiD), to perform membership inference, which reduces the stochasticity in estimating memorization of individual samples. Experimental results demonstrate that our method significantly outperforms previous methods across various data distributions and dataset scales. Additionally, our method shows superior resistance to overfitting mitigation strategies, such as early stopping and data augmentation.

cs.CR↗

pFLFE: Cross-silo Personalized Federated Learning via Feature Enhancement on Medical Image Segmentation

In medical image segmentation, personalized cross-silo federated learning (FL) is becoming popular for utilizing varied data across healthcare settings to overcome data scarcity and privacy concerns. However, existing methods often suffer from client drift, leading to inconsistent performance and delayed training. We propose a new framework, Personalized Federated Learning via Feature Enhancement (pFLFE), designed to mitigate these challenges. pFLFE consists of two main stages: feature enhancement and supervised learning. The first stage improves differentiation between foreground and background features, and the second uses these enhanced features for learning from segmentation masks. We also design an alternative training approach that requires fewer communication rounds without compromising segmentation quality, even with limited communication resources. Through experiments on three medical segmentation tasks, we demonstrate that pFLFE outperforms the state-of-the-art methods.

cs.CV↗