arXiv subjects

Tianyu Du

Publications and source records attributed to Tianyu Du.

At least 37 records · Page 2Linked to original sources

arXiv2026

"I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?

Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground the literal sense and evoke the figurative meaning simultaneously. Although Vision-Language Models (VLMs) are widely used in multimodal understanding and generation, their ability to understand puns has not been systematically studied due to a scarcity of rigorous benchmarks. To address this, we first propose a multimodal pun generation pipeline. We then introduce MultiPun, a dataset comprising diverse types of puns alongside adversarial non-pun distractors. Our evaluation reveals that most models struggle to distinguish genuine puns from these distractors. Moreover, we propose both prompt-level and model-level strategies to enhance pun comprehension, with an average improvement of 16.5% in F1 scores. Our findings provide valuable insights for developing future VLMs that master the subtleties of human-like humor via cross-modal reasoning.

cs.CL↗

arXiv2026

From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents

Artificial Intelligence (AI) agents have evolved from passive predictive tools into active entities capable of autonomous decision-making and environmental interaction, driven by the reasoning capabilities of Large Language Models (LLMs). However, this evolution has introduced critical security vulnerabilities that existing frameworks fail to address. The Hierarchical Autonomy Evolution (HAE) framework organizes agent security into three tiers: Cognitive Autonomy (L1) targets internal reasoning integrity; Execution Autonomy (L2) covers tool-mediated environmental interaction; Collective Autonomy (L3) addresses systemic risks in multi-agent ecosystems. We present a taxonomy of threats spanning cognitive manipulation, physical environment disruption, and multi-agent systemic failures, and evaluate existing defenses while identifying key research gaps. The findings aim to guide the development of multilayered, autonomy-aware defense architectures for trustworthy AI agent systems.

cs.CR↗

arXiv2026

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems

Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within these multi-agent systems, the susceptibility of agents to collective cognitive biases remains an underexplored issue. A compelling example is the Mandela effect, a phenomenon where groups collectively misremember past events as a result of false details reinforced through social influence and internalized misinformation. This vulnerability limits our understanding of memory bias in multi-agent systems and raises ethical concerns about the potential spread of misinformation. In this paper, we conduct a comprehensive study on the Mandela effect in LLM-based multi-agent systems, focusing on its existence, causing factors, and mitigation strategies. We propose MANBENCH, a novel benchmark designed to evaluate agent behaviors across four common task types that are susceptible to the Mandela effect, using five interaction protocols that vary in agent roles and memory timescales. We evaluate agents powered by several LLMs on MANBENCH to quantify the Mandela effect and analyze how different factors affect it. Moreover, we propose strategies to mitigate this effect, including prompt-level defenses (e.g., cognitive anchoring and source scrutiny) and model-level alignment-based defense, achieving an average 74.40% reduction in the Mandela effect compared to the baseline. Our findings provide valuable insights for developing more resilient and ethically aligned collaborative multi-agent systems. Code and dataset are available at https://github.com/bluedream02/Mandela-Effect.

cs.CL↗

arXiv2026

Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization

Pre-trained large language models (LLMs) are commonly fine-tuned to adapt to downstream tasks. Since the majority of knowledge is acquired during pre-training, attributing the predictions of fine-tuned LLMs to their pre-training data may provide valuable insights. Influence functions have been proposed as a means to explain model predictions based on training data. However, existing approaches fail to compute ``multi-stage'' influence and lack scalability to billion-scale LLMs. In this paper, we propose the multi-stage influence function to attribute the downstream predictions of fine-tuned LLMs to pre-training data under the full-parameter fine-tuning paradigm. To enhance the efficiency and practicality of our multi-stage influence function, we leverage Eigenvalue-corrected Kronecker-Factored (EK-FAC) parameterization for efficient approximation. Empirical results validate the superior scalability of EK-FAC approximation and the effectiveness of our multi-stage influence function. Additionally, case studies on a real-world LLM, dolly-v2-3b, demonstrate its interpretive power, with exemplars illustrating insights provided by multi-stage influence estimates. Our code is public at https://github.com/colored-dye/multi_stage_influence_function.

cs.CL↗

arXiv2026

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks

Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible to manipulation by fraudulent information, which can lead to harmful outcomes. Although advanced defense methods have been developed to address this issue, they often exhibit limitations in effectiveness, interpretability, and generalizability, particularly when applied to LLM-based applications. To address these challenges, we introduce FraudShield, a novel framework designed to protect LLMs from fraudulent content by leveraging a comprehensive analysis of fraud tactics. Specifically, FraudShield constructs and refines a fraud tactic-keyword knowledge graph to capture high-confidence associations between suspicious text and fraud techniques. The structured knowledge graph augments the original input by highlighting keywords and providing supporting evidence, guiding the LLM toward more secure responses. Extensive experiments show that FraudShield consistently outperforms state-of-the-art defenses across four mainstream LLMs and five representative fraud types, while also offering interpretable clues for the model's generations.

cs.CR↗

arXiv2026

HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors

Recent advances in software vulnerability detection have been driven by Language Model (LM)-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, allowing critical flaws to evade detection. Existing black-box attacks on LM-based vulnerability detectors primarily rely on isolated perturbation strategies, limiting their ability to efficiently explore the adversarial code space for optimal perturbations. To bridge this gap, we propose HogVul, a black-box adversarial code generation framework that integrates both lexical and syntax perturbations under a unified dual-channel optimization strategy driven by Particle Swarm Optimization (PSO). By systematically coordinating two-level perturbations, HogVul effectively expands the search space for adversarial examples, enhancing the attack efficacy. Extensive experiments on four benchmark datasets demonstrate that HogVul achieves an average attack success rate improvement of 26.05\% over state-of-the-art baseline methods. These findings highlight the potential of hybrid optimization strategies in exposing model vulnerabilities.

cs.CR↗

arXiv2026

LABOR-LLM: Language-Based Occupational Representations with Large Language Models

This paper builds an empirical model that predicts a worker's next occupation as a function of the worker's occupational history. Because histories are sequences of occupations, the covariate space is high-dimensional, and further, the outcome (the next occupation) is a discrete choice that can take on many values. To estimate the parameters of the model, we leverage an approach from generative artificial intelligence. Estimation begins from a ``foundation model'' trained on non-representative data and then ``fine-tunes'' the estimation using data about careers from a representative survey. We convert tabular data from the survey into text files that resemble resumes and fine-tune the parameters of the foundation model, a large language model (LLM), using these text files with the objective of predicting the next token (word). The resulting fine-tuned LLM is used to calculate estimates of worker transition probabilities. Its predictive performance surpasses all prior models, both for the task of granularly predicting the next occupation as well as for specific tasks such as predicting whether the worker changes occupations or stays in the labor force. We quantify the value of fine-tuning and further show that by adding more career data from a different population, fine-tuning smaller LLMs (fewer parameters) surpasses the performance of fine-tuning larger models. When we omit the English language occupational title and replace it with a unique code, predictive performance declines.

cs.LG↗

arXiv2025

Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?

Large vision-language models (LVLMs) have achieved remarkable advancements in multimodal reasoning tasks. However, their widespread accessibility raises critical concerns about potential copyright infringement. Will LVLMs accurately recognize and comply with copyright regulations when encountering copyrighted content (i.e., user input, retrieved documents) in the context? Failure to comply with copyright regulations may lead to serious legal and ethical consequences, particularly when LVLMs generate responses based on copyrighted materials (e.g., retrieved book experts, news reports). In this paper, we present a comprehensive evaluation of various LVLMs, examining how they handle copyrighted content -- such as book excerpts, news articles, music lyrics, and code documentation when they are presented as visual inputs. To systematically measure copyright compliance, we introduce a large-scale benchmark dataset comprising 50,000 multimodal query-content pairs designed to evaluate how effectively LVLMs handle queries that could lead to copyright infringement. Given that real-world copyrighted content may or may not include a copyright notice, the dataset includes query-content pairs in two distinct scenarios: with and without a copyright notice. For the former, we extensively cover four types of copyright notices to account for different cases. Our evaluation reveals that even state-of-the-art closed-source LVLMs exhibit significant deficiencies in recognizing and respecting the copyrighted content, even when presented with the copyright notice. To solve this limitation, we introduce a novel tool-augmented defense framework for copyright compliance, which reduces infringement risks in all scenarios. Our findings underscore the importance of developing copyright-aware LVLMs to ensure the responsible and lawful use of copyrighted content.

cs.CL↗

arXiv2025

The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks

Deep neural networks (DNNs) underpin critical applications yet remain vulnerable to backdoor attacks, typically reliant on heuristic brute-force methods. Despite significant empirical advancements in backdoor research, the lack of rigorous theoretical analysis limits understanding of underlying mechanisms, constraining attack predictability and adaptability. Therefore, we provide a theoretical analysis targeting backdoor attacks, focusing on how sparse decision boundaries enable disproportionate model manipulation. Based on this finding, we derive a closed-form, ambiguous boundary region, wherein negligible relabeled samples induce substantial misclassification. Influence function analysis further quantifies significant parameter shifts caused by these margin samples, with minimal impact on clean accuracy, formally grounding why such low poison rates suffice for efficacious attacks. Leveraging these insights, we propose Eminence, an explainable and robust black-box backdoor framework with provable theoretical guarantees and inherent stealth properties. Eminence optimizes a universal, visually subtle trigger that strategically exploits vulnerable decision boundaries and effectively achieves robust misclassification with exceptionally low poison rates (< 0.1%, compared to SOTA methods typically requiring > 1%). Comprehensive experiments validate our theoretical discussions and demonstrate the effectiveness of Eminence, confirming an exponential relationship between margin poisoning and adversarial boundary manipulation. Eminence maintains > 90% attack success rate, exhibits negligible clean-accuracy loss, and demonstrates high transferability across diverse models, datasets and scenarios.

cs.LG↗

arXiv2025

FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training

Federated Recommender Systems (FedRecs) leverage federated learning to protect user privacy by retaining data locally. However, user embeddings in FedRecs often encode sensitive attribute information, rendering them vulnerable to attribute inference attacks. Attribute unlearning has emerged as a promising approach to mitigate this issue. In this paper, we focus on user-level FedRecs, which is a more practical yet challenging setting compared to group-level FedRecs. Adversarial training emerges as the most feasible approach within this context. We identify two key challenges in implementing adversarial training-based attribute unlearning for user-level FedRecs: i) mitigating training instability caused by user data heterogeneity, and ii) preventing attribute information leakage through gradients. To address these challenges, we propose FedAU2, an attribute unlearning method for user-level FedRecs. For CH1, we propose an adaptive adversarial training strategy, where the training dynamics are adjusted in response to local optimization behavior. For CH2, we propose a dual-stochastic variational autoencoder to perturb the adversarial model, effectively preventing gradient-based information leakage. Extensive experiments on three real-world datasets demonstrate that our proposed FedAU2 achieves superior performance in unlearning effectiveness and recommendation performance compared to existing baselines.

cs.IR↗

arXiv2025

DP-GENG : Differentially Private Dataset Distillation Guided by DP-Generated Data

Dataset distillation (DD) compresses large datasets into smaller ones while preserving the performance of models trained on them. Although DD is often assumed to enhance data privacy by aggregating over individual examples, recent studies reveal that standard DD can still leak sensitive information from the original dataset due to the lack of formal privacy guarantees. Existing differentially private (DP)-DD methods attempt to mitigate this risk by injecting noise into the distillation process. However, they often fail to fully leverage the original dataset, resulting in degraded realism and utility. This paper introduces \libn, a novel framework that addresses the key limitations of current DP-DD by leveraging DP-generated data. Specifically, \lib initializes the distilled dataset with DP-generated data to enhance realism. Then, generated data refines the DP-feature matching technique to distill the original dataset under a small privacy budget, and trains an expert model to align the distilled examples with their class distribution. Furthermore, we design a privacy budget allocation strategy to determine budget consumption across DP components and provide a theoretical analysis of the overall privacy guarantees. Extensive experiments show that \lib significantly outperforms state-of-the-art DP-DD methods in terms of both dataset utility and robustness against membership inference attacks, establishing a new paradigm for privacy-preserving dataset distillation.

cs.CR↗

arXiv2025

LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping

Federated learning (FL) enables collaborative model training across distributed nodes without exposing raw data, but its decentralized nature makes it vulnerable in trust-deficient environments. Inference attacks may recover sensitive information from gradient updates, while poisoning attacks can degrade model performance or induce malicious behaviors. Existing defenses often suffer from high communication and computation costs, or limited detection precision. To address these issues, we propose LSHFed, a robust and communication-efficient FL framework that simultaneously enhances aggregation robustness and privacy preservation. At its core, LSHFed incorporates LSHGM, a novel gradient verification mechanism that projects high-dimensional gradients into compact binary representations via multi-hyperplane locally-sensitive hashing. This enables accurate detection and filtering of malicious gradients using only their irreversible hash forms, thus mitigating privacy leakage risks and substantially reducing transmission overhead. Extensive experiments demonstrate that LSHFed maintains high model performance even when up to 50% of participants are collusive adversaries while achieving up to a 1000x reduction in gradient verification communication compared to full-gradient methods.

cs.LG↗

arXiv2025

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools

The remarkable capability of large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol (MCP) tools have become the de facto standard and are now widely integrated into these agents. However, the incorporation of MCP tools introduces the risk of tool poisoning attacks, which can manipulate the behavior of LLM-based agents. Although previous studies have identified such vulnerabilities, their red teaming approaches have largely remained at the proof-of-concept stage, leaving the automatic and systematic red teaming of LLM-based agents under the MCP tool poisoning paradigm an open question. To bridge this gap, we propose AutoMalTool, an automated red teaming framework for LLM-based agents by generating malicious MCP tools. Our extensive evaluation shows that AutoMalTool effectively generates malicious MCP tools capable of manipulating the behavior of mainstream LLM-based agents while evading current detection mechanisms, thereby revealing new security risks in these agents.

cs.CR↗

arXiv2025

CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing

With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code LM to protect its IP, they have limitations when facing the more practical and complex demand, i.e., offering the individual user-level tracing in the black-box setting. This work presents CLMTracing, a black-box code LM watermarking framework employing the rule-based watermarks and utility-preserving injection method for user-level model tracing. CLMTracing further incorporates a parameter selection algorithm sensitive to the robust watermark and adversarial training to enhance the robustness against watermark removal attacks. Comprehensive evaluations demonstrate CLMTracing is effective across multiple state-of-the-art (SOTA) code LMs, showing significant harmless improvements compared to existing SOTA baselines and strong robustness against various removal attacks.

cs.PL↗

arXiv2025

Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes

The rapid advancement of voice deepfake technologies has raised serious concerns about user audio privacy, as attackers increasingly exploit publicly available voice data to generate convincing fake audio for malicious purposes such as identity theft, financial fraud, and misinformation campaigns. While existing defense methods offer partial protection, they face critical limitations, including weak adaptability to unseen user data, poor scalability to long audio, rigid reliance on white-box knowledge, and high computational and temporal costs during the encryption process. To address these challenges and defend against personalized voice deepfake threats, we propose Enkidu, a novel user-oriented privacy-preserving framework that leverages universal frequential perturbations generated through black-box knowledge and few-shot training on a small amount of user data. These highly malleable frequency-domain noise patches enable real-time, lightweight protection with strong generalization across variable-length audio and robust resistance to voice deepfake attacks, all while preserving perceptual quality and speech intelligibility. Notably, Enkidu achieves over 50 to 200 times processing memory efficiency (as low as 0.004 gigabytes) and 3 to 7000 times runtime efficiency (real-time coefficient as low as 0.004) compared to six state-of-the-art countermeasures. Extensive experiments across six mainstream text-to-speech models and five cutting-edge automated speaker verification models demonstrate the effectiveness, transferability, and practicality of Enkidu in defending against both vanilla and adaptive voice deepfake attacks. Our code is currently available.

cs.SD↗

arXiv2025

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models

The rapid growth of text-to-video (T2V) diffusion models has raised concerns about privacy, copyright, and safety due to their potential misuse in generating harmful or misleading content. These models are often trained on numerous datasets, including unauthorized personal identities, artistic creations, and harmful materials, which can lead to uncontrolled production and distribution of such content. To address this, we propose VideoEraser, a training-free framework that prevents T2V diffusion models from generating videos with undesirable concepts, even when explicitly prompted with those concepts. Designed as a plug-and-play module, VideoEraser can seamlessly integrate with representative T2V diffusion models via a two-stage process: Selective Prompt Embedding Adjustment (SPEA) and Adversarial-Resilient Noise Guidance (ARNG). We conduct extensive evaluations across four tasks, including object erasure, artistic style erasure, celebrity erasure, and explicit content erasure. Experimental results show that VideoEraser consistently outperforms prior methods regarding efficacy, integrity, fidelity, robustness, and generalizability. Notably, VideoEraser achieves state-of-the-art performance in suppressing undesirable content during T2V generation, reducing it by 46% on average across four tasks compared to baselines.

cs.CV↗

arXiv2025

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents

Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching information from public websites), tool responses may contain injected instructions that covertly influence agent behaviors and lead to malicious outcomes, a threat referred to as Indirect Prompt Injection (IPI). Existing defenses typically rely on advanced prompting strategies or auxiliary detection models. While these methods have demonstrated some effectiveness, they fundamentally rely on assumptions about the model's inherent security, which lacks structural constraints on agent behaviors. As a result, agents still retain unrestricted access to tool invocations, leaving them vulnerable to stronger attack vectors that can bypass the security guardrails of the model. To prevent malicious tool invocations at the source, we propose a novel defensive task execution paradigm, called IPIGuard, which models the agents' task execution process as a traversal over a planned Tool Dependency Graph (TDG). By explicitly decoupling action planning from interaction with external data, IPIGuard significantly reduces unintended tool invocations triggered by injected instructions, thereby enhancing robustness against IPI attacks. Experiments on the AgentDojo benchmark show that IPIGuard achieves a superior balance between effectiveness and robustness, paving the way for the development of safer agentic systems in dynamic environments.

cs.CR↗

arXiv2025

Tool-Planner: Task Planning with Clusters across Multiple Tools

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing examples of tool usage and their corresponding functions, allowing LLMs to formulate plans and demonstrate the process of invoking and executing each tool. LLMs can address tasks that they cannot complete independently, thereby enhancing their potential across different tasks. However, this approach faces two key challenges. First, redundant error correction leads to unstable planning and long execution time. Additionally, designing a correct plan among multiple tools is also a challenge in tool learning. To address these issues, we propose Tool-Planner, a task-processing framework based on toolkits. Tool-Planner groups tools based on the API functions with the same function into a toolkit and allows LLMs to implement planning across the various toolkits. When a tool error occurs, the language model can reselect and adjust tools based on the toolkit. Experiments show that our approach demonstrates a high pass and win rate across different datasets and optimizes the planning scheme for tool learning in models such as GPT-4 and Claude 3, showcasing the potential of our method. Our code is public at https://github.com/OceannTwT/Tool-Planner

cs.AI↗