arXiv subjects

Wenyuan Xu

Publications and source records attributed to Wenyuan Xu.

At least 19 recordsLinked to original sources

arXiv2026

"Your Robot Was Trained on a Lie": Collision Mesh Poisoning Attacks on Robotic Manipulation

Learning-enabled robotic manipulation increasingly relies on robot simulators for policy training and evaluation before real-world deployment. Inside a simulator, a 3D asset contains two separate geometries: a visual mesh used for rendering and a collision mesh used for physical interaction. For computational efficiency, the collision mesh is deliberately a coarse approximation that need not have the same geometry as the visual mesh, a legitimate and pervasive discrepancy we call the Visual--Collision Gap (V--C Gap). We show that the V--C Gap opens a new and practical attack surface, and propose Collision Mesh Poisoning (CMP), the first poisoning attack against robotic manipulation delivered through the 3D asset supply chain. An attacker modifies only the collision mesh of a 3D asset, leaving the visual mesh and all other components unchanged. A policy trained and evaluated with the poisoned asset behaves normally throughout simulation, yet degrades, fails, or creates physical safety risks once deployed in the real world. Since current asset review practices cover malware, copyright, and format compliance, but not visual--collision consistency, poisoned assets can be distributed through legitimate supply chain channels. We evaluate several defenses and our results show that they are insufficient to defend against CMP, highlighting the need for new defenses.

cs.CR↗

arXiv2026

GhostTac: Manipulating Tactile Sensors without Physical Contact

Tactile sensors are integral components of modern robotic systems, enabling robots to perceive and interact with the physical environment through tactile feedback. Despite their importance, the physical-layer security of tactile sensors has received little attention in prior work. In this paper, we present GhostTac, to the best of our knowledge, the first contactless attack that manipulates tactile sensing via electromagnetic interference (EMI). We identify that EMI exploits the nonlinear rectification and limited bandwidth amplification effects, allowing carefully crafted EMI signals to be converted into a persistent DC offset that bypasses on-board filtering and induces stable measurement deviations. Building on this mechanism, GhostTac enables fine-grained and controllable manipulation of sensor outputs by reshaping the spatial distribution and manipulating the magnitude at the targeted location. Such interference can induce unintended and harmful robot behaviors, such as causing a domestic robot to exert excessive force, resulting in physical damage or human injury. We evaluate GhostTac on 10 sensor modules and 2 dexterous hands, covering 15 tactile sensors of different types, and demonstrate consistent attack effectiveness across all tested devices. We further present three case studies on tactile grasping, slip detection, and material classification to illustrate practical impacts in real robotic tasks. We envision that our findings shed light on a new physical attack vector against tactile sensing in robotic systems.

cs.CR↗

arXiv2026

Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs

Large Language Models (LLMs) have been integrated into many applications (e.g., web agents) to perform more sophisticated tasks. However, LLM-empowered applications are vulnerable to Indirect Prompt Injection (IPI) attacks, where instructions are injected via untrustworthy external data sources. This paper presents Rennervate, a defense framework to detect and prevent IPI attacks. Rennervate leverages attention features to detect the covert injection at a fine-grained token level, enabling precise sanitization that neutralizes IPI attacks while maintaining LLM functionalities. Specifically, the token-level detector is materialized with a 2-step attentive pooling mechanism, which aggregates attention heads and response tokens for IPI detection and sanitization. Moreover, we establish a fine-grained IPI dataset, FIPI, to be open-sourced to support further research. Extensive experiments verify that Rennervate outperforms 15 commercial and academic IPI defense methods, achieving high precision on 5 LLMs and 6 datasets. We also demonstrate that Rennervate is transferable to unseen attacks and robust against adaptive adversaries.

cs.CR↗

arXiv2026

Bit2Watt: A Cyber-Physical Vulnerability Exploiting GPU Workloads Across Power and Computing Infrastructures

Modern data centers increasingly rely on large-scale GPU clusters and on-site renewable energy resources, resulting in a tightly coupled cyber-physical system between computing workloads and power-electronic-dominated grids. In this paper, we reveal Bit2Watt, a previously unexplored vulnerability in which an adversary manipulates GPU workloads to induce controlled, high-frequency power modulations that destabilize local power infrastructure and propagate back to disrupt computing services. Unlike traditional attacks that compromise grid-side devices or communication channels, Bit2Watt operates entirely within the cyber layer as a legal tenant, which could amplify fluctuations, harmonic distortion, and damping degradation, particularly in high-DER-penetration scenarios. This risk is difficult to detect under routine cloud- and facility-side monitoring because it exploits legitimate workload execution paths and concentrates much of its distinctive behavior in high-frequency components that are weakly captured by common telemetry. We validate Bit2Watt through impedance-based analysis, power system simulations, and real-world experiments on GPUs and grid-connected PV inverters. Under the synchronized worst-case aggregation model studied in the paper, manipulating 1,000 GPUs in a 1-MW local power system with 90% DERs raises current THD to 46.8% and results in a damping ratio of -0.27. We further show that the resulting power-quality degradation can stress data-center power-delivery equipment, trigger protection mechanisms, and, in extreme simulated cases, induce cascading failures in transmission-scale systems. In addition, we analyze a plausible Watt2Bit feedback path, including denial-of-service risks and covert information exfiltration via EMI side channels. This work highlights the urgent need for cross-layer defenses that jointly consider workload scheduling and power electronics.

cs.CR↗

arXiv2026

TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches

By integrating Chain-of-Thought (CoT) reasoning, Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, particularly by improving generalization and interpretability. However, the security of CoT-based reasoning mechanisms remains largely unexplored. In this paper, we show that CoT reasoning introduces a novel attack vector for targeted behavior hijacking--for example, causing a robot to mistakenly deliver a knife to a person instead of an apple--without modifying the user's instruction. We first provide empirical evidence that CoT strongly governs action generation, even when it is semantically misaligned with the input instructions. Building on this observation, we propose TRAP, the first targeted behavior-hijacking adversarial attack against CoT-reasoning VLA models. By targeting the reasoning-to-action pathway, TRAP uses an adversarial patch (e.g., a tablecloth placed on the table) to steer intermediate CoT reasoning and downstream actions toward adversary-defined behaviors. Extensive evaluations on three representative reasoning VLAs, spanning distinct CoT reasoning mechanisms, demonstrate the effectiveness of TRAP. Notably, we implemented the patch by printing it on paper in a real-world setting. Our findings highlight the urgent need to secure CoT reasoning in VLA systems. The project page is available at https://zhengxian-huang.github.io/TRAP-website/.

cs.CR↗

arXiv2026

False Reality: Uncovering Sensor-induced Human-VR Interaction Vulnerability

Virtual Reality (VR) techniques, serving as the bridge between the real and virtual worlds, have boomed and are widely used in manufacturing, remote healthcare, gaming, etc. Specifically, VR systems offer users immersive experiences that include both perceptions and actions. Various studies have demonstrated that attackers can manipulate VR software to influence users' interactions, including perception and actions. However, such attacks typically require strong access and specialized expertise. In this paper, we are the first to present a systematic analysis of physical attacks against VR systems and introduce False Reality, a new attack threat to VR devices without requiring access to or modification of their software. False Reality disturbs VR system services by tampering with sensor measurements, and further spoofing users' perception even inducing harmful actions, e.g., inducing dizziness or causing users to crash into obstacles, by exploiting perceptual and psychological effects. We formalize these threats through an attack pathway framework and validate three representative pathways via physical experiments and user studies on five commercial VR devices. Finally, we further propose a defense prototype to mitigate such threats. Our findings shall provide valuable insights for enhancing the security and resilience of future VR systems.

cs.CR↗

arXiv2026

CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding

LLM-powered coding agents are reshaping the development paradigm. However, existing evaluation systems, neither traditional tests for humans nor benchmarks for LLMs, fail to capture this shift, excluding problems that require both human reasoning to guide solutions and AI efficiency for implementation. We introduce CentaurEval, a unified, ecologically valid benchmark for measuring human-in-the-loop value in coding. CentaurEval's core innovation is its "Collaboration-Necessary" problem templates, which are intractable for standalone LLMs or humans, but solvable through effective collaboration. CentaurEval dynamically instantiates tasks from 45 templates, providing a standardized IDE for humans and a reproducible 450-task toolkit for LLMs. We benchmark 45 participants against 5 LLMs under 4 levels of human intervention. Results show that while LLMs or humans alone achieve poor pass rates (0.67% and 18.89%), human-AI collaboration significantly improves to 31.11%. Our analysis reveals an emerging co-reasoning partnership, challenging the traditional human-tool hierarchy by showing that strategic breakthroughs can originate from either humans or AI.

cs.SE↗

arXiv2026

A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection

Open-source libraries are widely used in modern software development, introducing significant security vulnerabilities. While static analysis tools can identify potential vulnerabilities at scale, they often generate overwhelming reports with high false positive rates. Automated Exploit Generation (AEG) emerges as a promising solution to confirm vulnerability authenticity by generating an exploit. However, traditional AEG approaches based on fuzzing or symbolic execution face path coverage and constraint-solving problems. Although LLMs show great potential for AEG, how to effectively leverage them to comprehend vulnerabilities and generate corresponding exploits is still an open question. To address these challenges, we propose Vulnsage, a multi-agent framework for AEG. Vulnsage simulates human security researchers' workflows by decomposing the complex AEG process into multiple specialized sub-agents: Code Analyzer Agent, Code Generation Agent, Validation Agent, and a set of Reflection Agents, orchestrated by a central supervisor through iterative cycles. Given a target program, the Code Analyzer Agent performs static analysis to identify potential vulnerabilities and collects relevant information for each one. The Code Generation Agent then utilizes an LLM to generate candidate exploits. The Validation Agent and Reflection Agents form a feedback-driven self-refinement loop that uses execution traces and runtime error analysis to either improve the exploit iteratively or reason about the false positive alert. Experimental evaluation demonstrates that Vulnsage succeeds in generating 34.64\% more exploits than state-of-the-art tools such as \explodejs. Furthermore, Vulnsage has successfully discovered and verified 146 zero-day vulnerabilities in real-world scenarios, demonstrating its practical effectiveness for assisting security assessment in software supply chains.

cs.SE↗

arXiv2026

AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models

The rapid development and widespread adoption of Audio Large Language Models (ALLMs) demand rigorous evaluation of their trustworthiness. However, existing evaluation frameworks are primarily designed for text and fail to capture vulnerabilities introduced by the acoustic properties of audio. We find that significant trustworthiness risks in ALLMs arise from non-semantic acoustic cues, such as timbre, accent, and background noise, which can be exploited to manipulate model behavior. To address this gap, we propose AudioTrust, the first large-scale and systematic framework for evaluating ALLM trustworthiness under audio-specific risks. AudioTrust covers six key dimensions: fairness, hallucination, safety, privacy, robustness, and authenticition. It includes 26 sub-tasks and a curated dataset of more than 4,420 audio samples collected from real-world scenarios, including daily conversations, emergency calls, and voice assistant interactions, and is specifically designed to probe trustworthiness across multiple dimensions. Our comprehensive evaluation spans 18 experimental settings and uses human-validated automated pipelines to enable objective and scalable assessment of model outputs. Experimental results on 14 state-of-the-art open-source and closed-source ALLMs reveal important limitations and failure boundaries under diverse high-risk audio scenarios, providing critical insights for the secure and trustworthy deployment of future audio models. Our platform and benchmark are publicly available at https://github.com/JusperLee/AudioTrust.

cs.SD↗

arXiv2026

Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt

Large Language Models (LLMs) have achieved remarkable performance and received significant research interest. The enormous computational demands, however, hinder the local deployment on devices with limited resources. The current prevalent LLM inference paradigms require users to send queries to the service providers for processing, which raises critical privacy concerns. Existing approaches propose to allow the users to obfuscate the token embeddings before transmission and utilize local models for denoising. Nonetheless, transmitting the token embeddings and deploying local models may result in excessive communication and computation overhead, preventing practical implementation. In this work, we propose \textbf{DEL}, a framework for \textbf{D}ifferentially private and communication \textbf{E}fficient \textbf{L}LM split inference. More specifically, an embedding projection module and a differentially private stochastic quantization mechanism are proposed to reduce the communication overhead in a privacy-preserving manner. To eliminate the need for local models, we adapt soft prompt at the server side to compensate for the utility degradation caused by privacy. To the best of our knowledge, this is the first work that utilizes soft prompt to improve the trade-off between privacy and utility in LLM inference, and extensive experiments on text generation and natural language understanding benchmarks demonstrate the effectiveness of the proposed method.

cs.CR↗

arXiv2026

PINA: Prompt Injection Attack against Navigation Agents

Navigation agents powered by large language models (LLMs) convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide physical navigation, leading to unsafe routes, mission failure, or real-world harm. Despite this high-stakes setting, the vulnerability of navigation agents to prompt injection remains largely unexplored. In this paper, we propose PINA, an adaptive prompt optimization framework tailored to navigation agents under black-box, long-context, and action-executable constraints. Experiments on indoor and outdoor navigation agents show that PINA achieves high attack success rates with an average ASR of 87.5%, surpasses all baselines, and remains robust under ablation and adaptive-attack conditions. This work provides the first systematic investigation of prompt injection attacks in navigation and highlights their urgent security implications for embodied LLM agents.

cs.CR↗

arXiv2025

Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks

Vision-Language-Action (VLA) models revolutionize robotic systems by enabling end-to-end perception-to-action pipelines that integrate multiple sensory modalities, such as visual signals processed by cameras and auditory signals captured by microphones. This multi-modality integration allows VLA models to interpret complex, real-world environments using diverse sensor data streams. Given the fact that VLA-based systems heavily rely on the sensory input, the security of VLA models against physical-world sensor attacks remains critically underexplored. To address this gap, we present the first systematic study of physical sensor attacks against VLAs, quantifying the influence of sensor attacks and investigating the defenses for VLA models. We introduce a novel "Real-Sim-Real" framework that automatically simulates physics-based sensor attack vectors, including six attacks targeting cameras and two targeting microphones, and validates them on real robotic systems. Through large-scale evaluations across various VLA architectures and tasks under varying attack parameters, we demonstrate significant vulnerabilities, with susceptibility patterns that reveal critical dependencies on task types and model designs. We further develop an adversarial-training-based defense that enhances VLA robustness against out-of-distribution physical perturbations caused by sensor attacks while preserving model performance. Our findings expose an urgent need for standardized robustness benchmarks and mitigation strategies to secure VLA deployments in safety-critical environments.

cs.RO↗

arXiv2025

Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries

Text-to-image (T2I) models, though exhibiting remarkable creativity in image generation, can be exploited to produce unsafe images. Existing safety measures, e.g., content moderation or model alignment, fail in the presence of white-box adversaries who know and can adjust model parameters, e.g., by fine-tuning. This paper presents a novel defensive framework, named Patronus, which equips T2I models with holistic protection to defend against white-box adversaries. Specifically, we design an internal moderator that decodes unsafe input features into zero vectors while ensuring the decoding performance of benign input features. Furthermore, we strengthen the model alignment with a carefully designed non-fine-tunable learning mechanism, ensuring the T2I model will not be compromised by malicious fine-tuning. We conduct extensive experiments to validate the intactness of the performance on safe content generation and the effectiveness of rejecting unsafe content generation. Results also confirm the resilience of Patronus against various fine-tuning attacks by white-box adversaries.

cs.CR↗

arXiv2025

SoK: Understanding the Fundamentals and Implications of Sensor Out-of-band Vulnerabilities

Sensors are fundamental to cyber-physical systems (CPS), enabling perception and control by transducing physical stimuli into digital measurements. However, despite growing research on physical attacks on sensors, our understanding of sensor hardware vulnerabilities remains fragmented due to the ad-hoc nature of this field. Moreover, the infinite attack signal space further complicates threat abstraction and defense. To address this gap, we propose a systematization framework, termed sensor out-of-band (OOB) vulnerabilities, that for the first time provides a comprehensive abstraction for sensor attack surfaces based on underlying physical principles. We adopt a bottom-up systematization methodology that analyzes OOB vulnerabilities across three levels. At the component level, we identify the physical principles and limitations that contribute to OOB vulnerabilities. At the sensor level, we categorize known attacks and evaluate their practicality. At the system level, we analyze how CPS features such as sensor fusion, closed-loop control, and intelligent perception impact the exposure and mitigation of OOB threats. Our findings offer a foundational understanding of sensor hardware security and provide guidance and future directions for sensor designers, security researchers, and system developers aiming to build more secure sensors and CPS.

cs.CR↗

arXiv2025

POEX: Towards Policy Executable Jailbreak Attacks Against the LLM-based Robots

The integration of LLMs into robots has witnessed significant growth, where LLMs can convert instructions into executable robot policies. However, the inherent vulnerability of LLMs to jailbreak attacks brings critical security risks from the digital domain to the physical world. An attacked LLM-based robot could execute harmful policies and cause physical harm. In this paper, we investigate the feasibility and rationale of jailbreak attacks against LLM-based robots and answer three research questions: (1) How applicable are existing LLM jailbreak attacks against LLM-based robots? (2) What unique challenges arise if they are not directly applicable? (3) How to defend against such jailbreak attacks? To this end, we first construct a "human-object-environment" robot risks-oriented Harmful-RLbench and then conduct a measurement study on LLM-based robot systems. Our findings conclude that traditional LLM jailbreak attacks are inapplicable in robot scenarios, and we identify two unique challenges: determining policy-executable optimization directions and accurately evaluating robot-jailbroken policies. To enable a more thorough security analysis, we introduce POEX (POlicy EXecutable) jailbreak, a red-teaming framework that induces harmful yet executable policy to jailbreak LLM-based robots. POEX incorporates hidden layer gradient optimization to guarantee jailbreak success and policy execution as well as a multi-agent evaluator to accurately assess the practical executability of policies. Experiments conducted on the real-world robotic systems and in simulation demonstrate the efficacy of POEX, highlighting critical security vulnerabilities and its transferability across LLMs. Finally, we propose prompt-based and model-based defenses to mitigate attacks. Our findings underscore the urgent need for security measures to ensure the safe deployment of LLM-based robots in critical applications.

cs.RO↗

arXiv2025

PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs. Existing solutions to this verification challenge often depend on separate verifier models or require multi-stage self-correction training pipelines, which limit scalability. In this paper, we propose Policy as Generative Verifier (PAG), a simple and effective framework that empowers LLMs to self-correct by alternating between policy and verifier roles within a unified multi-turn reinforcement learning (RL) paradigm. Distinct from prior approaches that always generate a second attempt regardless of model confidence, PAG introduces a selective revision mechanism: the model revises its answer only when its own generative verification step detects an error. This verify-then-revise workflow not only alleviates model collapse but also jointly enhances both reasoning and verification abilities. Extensive experiments across diverse reasoning benchmarks highlight PAG's dual advancements: as a policy, it enhances direct generation and self-correction accuracy; as a verifier, its self-verification outperforms self-consistency.

cs.CL↗

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

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reasoning tasks, the method demonstrates notable generalization across diverse domains. For instance, it surpasses DeepSeek R1 by 8% in win rate on non-reasoning tasks, indicating its broader applicability. Compared to other state-of-the-art reasoning models, Seed1.5-Thinking is a Mixture-of-Experts (MoE) model with a relatively small size, featuring 20B activated and 200B total parameters. As part of our effort to assess generalized reasoning, we develop two internal benchmarks, BeyondAIME and Codeforces, both of which will be publicly released to support future research. Model trial link: https://www.volcengine.com/experience/ark.

cs.CL↗