arXiv subjects

Haoran Li

Publications and source records attributed to Haoran Li.

At least 181 records · Page 10Linked to original sources

arXiv2025

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the instructions in the data content, such as web pages from search engines, the LLMs are vulnerable to prompt injection attacks. These attacks trick the LLMs into deviating from the original input instruction and executing the attackers' target instruction. Recently, various instruction hierarchy defense strategies are proposed to effectively defend against prompt injection attacks via fine-tuning. In this paper, we explore more vicious attacks that nullify the prompt injection defense methods, even the instruction hierarchy: backdoor-powered prompt injection attacks, where the attackers utilize the backdoor attack for prompt injection attack purposes. Specifically, the attackers poison the supervised fine-tuning samples and insert the backdoor into the model. Once the trigger is activated, the backdoored model executes the injected instruction surrounded by the trigger. We construct a benchmark for comprehensive evaluation. Our experiments demonstrate that backdoor-powered prompt injection attacks are more harmful than previous prompt injection attacks, nullifying existing prompt injection defense methods, even the instruction hierarchy techniques.

cs.CR↗

arXiv2025

Dual Alignment Maximin Optimization for Offline Model-based RL

Offline reinforcement learning agents face significant deployment challenges due to the synthetic-to-real distribution mismatch. While most prior research has focused on improving the fidelity of synthetic sampling and incorporating off-policy mechanisms, the directly integrated paradigm often fails to ensure consistent policy behavior in biased models and underlying environmental dynamics, which inherently arise from discrepancies between behavior and learning policies. In this paper, we first shift the focus from model reliability to policy discrepancies while optimizing for expected returns, and then self-consistently incorporate synthetic data, deriving a novel actor-critic paradigm, Dual Alignment Maximin Optimization (DAMO). It is a unified framework to ensure both model-environment policy consistency and synthetic and offline data compatibility. The inner minimization performs dual conservative value estimation, aligning policies and trajectories to avoid out-of-distribution states and actions, while the outer maximization ensures that policy improvements remain consistent with inner value estimates. Empirical evaluations demonstrate that DAMO effectively ensures model and policy alignments, achieving competitive performance across diverse benchmark tasks.

cs.LG↗

arXiv2025

MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning

Multi-agent systems (MAS), leveraging the remarkable capabilities of Large Language Models (LLMs), show great potential in addressing complex tasks. In this context, integrating MAS with legal tasks is a crucial step. While previous studies have developed legal benchmarks for LLM agents, none are specifically designed to consider the unique advantages of MAS, such as task decomposition, agent specialization, and flexible training. In fact, the lack of evaluation methods limits the potential of MAS in the legal domain. To address this gap, we propose MASLegalBench, a legal benchmark tailored for MAS and designed with a deductive reasoning approach. Our benchmark uses GDPR as the application scenario, encompassing extensive background knowledge and covering complex reasoning processes that effectively reflect the intricacies of real-world legal situations. Furthermore, we manually design various role-based MAS and conduct extensive experiments using different state-of-the-art LLMs. Our results highlight the strengths, limitations, and potential areas for improvement of existing models and MAS architectures.

cs.AI↗

arXiv2025

MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol

As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks. Its decentralized architecture, which separates clients and servers, poses unique challenges for systematic safety analysis. This paper proposes a novel framework to enhance MCP safety. Guided by the MAESTRO framework, we first analyze the missing safety mechanisms in MCP, and based on this analysis, we propose the Model Contextual Integrity Protocol (MCIP), a refined version of MCP that addresses these gaps. Next, we develop a fine-grained taxonomy that captures a diverse range of unsafe behaviors observed in MCP scenarios. Building on this taxonomy, we develop benchmark and training data that support the evaluation and improvement of LLMs' capabilities in identifying safety risks within MCP interactions. Leveraging the proposed benchmark and training data, we conduct extensive experiments on state-of-the-art LLMs. The results highlight LLMs' vulnerabilities in MCP interactions and demonstrate that our approach substantially improves their safety performance.

cs.CL↗

arXiv2025

Re-Densification Meets Cross-Scale Propagation: Real-Time Neural Compression of LiDAR Point Clouds

LiDAR point clouds are fundamental to various applications, yet high-precision scans incur substantial storage and transmission overhead. Existing methods typically convert unordered points into hierarchical octree or voxel structures for dense-to-sparse predictive coding. However, the extreme sparsity of geometric details hinders efficient context modeling, thereby limiting their compression performance and speed. To address this challenge, we propose to generate compact features for efficient predictive coding. Our framework comprises two lightweight modules. First, the Geometry Re-Densification Module re-densifies encoded sparse geometry, extracts features at denser scale, and then re-sparsifies the features for predictive coding. This module avoids costly computation on highly sparse details while maintaining a lightweight prediction head. Second, the Cross-scale Feature Propagation Module leverages occupancy cues from multiple resolution levels to guide hierarchical feature propagation. This design facilitates information sharing across scales, thereby reducing redundant feature extraction and providing enriched features for the Geometry Re-Densification Module. By integrating these two modules, our method yields a compact feature representation that provides efficient context modeling and accelerates the coding process. Experiments on the KITTI dataset demonstrate state-of-the-art compression ratios and real-time performance, achieving 26 FPS for encoding/decoding at 12-bit quantization. Code is available at https://github.com/pengpeng-yu/FastPCC.

cs.CV↗

arXiv2025

Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance

The proliferation of Large Language Models (LLMs) has demonstrated remarkable capabilities, elevating the critical importance of LLM safety. However, existing safety methods rely on ad-hoc taxonomy and lack a rigorous, systematic protection, failing to ensure safety for the nuanced and complex behaviors of modern LLM systems. To address this problem, we solve LLM safety from legal compliance perspectives, named safety compliance. In this work, we posit relevant established legal frameworks as safety standards for defining and measuring safety compliance, including the EU AI Act and GDPR, which serve as core legal frameworks for AI safety and data security in Europe. To bridge the gap between LLM safety and legal compliance, we first develop a new benchmark for safety compliance by generating realistic LLM safety scenarios seeded with legal statutes. Subsequently, we align Qwen3-8B using Group Policy Optimization (GRPO) to construct a safety reasoner, Compliance Reasoner, which effectively aligns LLMs with legal standards to mitigate safety risks. Our comprehensive experiments demonstrate that the Compliance Reasoner achieves superior performance on the new benchmark, with average improvements of +10.45% for the EU AI Act and +11.85% for GDPR.

cs.CL↗

arXiv2025

Lifetimes of the Metastable $6\mathrm{d}\, ^{2}\mathrm{D}_{5/2}$ and $6\mathrm{d}\, ^{2}\mathrm{D}_{3/2}$ States of Ra$^+$

We report lifetime measurements of the metastable $6\mathrm{d}\, ^{2}\mathrm{D}_{5/2}$ and $6\mathrm{d}\, ^{2}\mathrm{D}_{3/2}$ states of Ra$^+$. The measured lifetimes, $τ_{5} = $ 303.8(1.5) ms and $τ_{3} = $ 642(9) ms, are important for optical frequency standards and for benchmarking high-precision relativistic atomic theory. Independent of the reported measurements, the D state lifetimes were calculated using the coupled-cluster single double triple method, in which the coupled-cluster equations for both core and valence triple excitations were solved iteratively. The method was designed for precise prediction of atomic properties, especially for heavy elements, where relativistic and correlation corrections become large, making their treatment more challenging. This Letter presents the first tests of the method for transition properties. Our prediction agrees with experimental values within the uncertainties. The ability to accurately predict the atomic properties of heavy elements is important for many applications, from tests of fundamental symmetries to the development of optical clocks.

physics.atom-ph↗

arXiv2025

InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding

Grounding large language models (LLMs) in external knowledge sources is a promising method for faithful prediction. While existing grounding approaches work well for simple queries, many real-world information needs require synthesizing multiple pieces of evidence. We introduce "integrative grounding" -- the challenge of retrieving and verifying multiple inter-dependent pieces of evidence to support a hypothesis query. To systematically study this problem, we repurpose data from four domains for evaluating integrative grounding capabilities. Our investigation reveals two critical findings: First, in groundedness verification, while LLMs are robust to redundant evidence, they tend to rationalize using internal knowledge when information is incomplete. Second, in examining retrieval planning strategies, we find that undirected planning can degrade performance through noise introduction, while premise abduction emerges as a promising approach due to its logical constraints. Additionally, LLMs' zero-shot self-reflection capabilities consistently improve grounding quality. These insights provide valuable direction for developing more effective integrative grounding systems.

cs.CL↗

arXiv2025

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning

While Large Language Models (LLMs) exhibit remarkable capabilities, they also introduce significant safety and privacy risks. Current mitigation strategies often fail to preserve contextual reasoning capabilities in risky scenarios. Instead, they rely heavily on sensitive pattern matching to protect LLMs, which limits the scope. Furthermore, they overlook established safety and privacy standards, leading to systemic risks for legal compliance. To address these gaps, we formulate safety and privacy issues into contextualized compliance problems following the Contextual Integrity (CI) theory. Under the CI framework, we align our model with three critical regulatory standards: GDPR, EU AI Act, and HIPAA. Specifically, we employ reinforcement learning (RL) with a rule-based reward to incentivize contextual reasoning capabilities while enhancing compliance with safety and privacy norms. Through extensive experiments, we demonstrate that our method not only significantly enhances legal compliance (achieving a +8.58% accuracy improvement in safety/privacy benchmarks) but also further improves general reasoning capability. For OpenThinker-7B, a strong reasoning model that significantly outperforms its base model Qwen2.5-7B-Instruct across diverse subjects, our method enhances its general reasoning capabilities, with +2.05% and +8.98% accuracy improvement on the MMLU and LegalBench benchmark, respectively.

cs.CL↗

arXiv2025

Classification of Vision-Based Tactile Sensors: A Review

Vision-based tactile sensors (VBTS) have gained widespread application in robotic hands, grippers and prosthetics due to their high spatial resolution, low manufacturing costs, and ease of customization. While VBTSs have common design features, such as a camera module, they can differ in a rich diversity of sensing principles, material compositions, multimodal approaches, and data interpretation methods. Here, we propose a novel classification of VBTS that categorizes the technology into two primary sensing principles based on the underlying transduction of contact into a tactile image: the Marker-Based Transduction Principle and the Intensity-Based Transduction Principle. Marker-Based Transduction interprets tactile information by detecting marker displacement and changes in marker density. In contrast, Intensity-Based Transduction maps external disturbances with variations in pixel values. Depending on the design of the contact module, Marker-Based Transduction can be further divided into two subtypes: Simple Marker-Based (SMB) and Morphological Marker-Based (MMB) mechanisms. Similarly, the Intensity-Based Transduction Principle encompasses the Reflective Layer-based (RLB) and Transparent Layer-Based (TLB) mechanisms. This paper provides a comparative study of the hardware characteristics of these four types of sensors including various combination types, and discusses the commonly used methods for interpreting tactile information. This~comparison reveals some current challenges faced by VBTS technology and directions for future research.

cs.RO↗

arXiv2025

Tactile SoftHand-A: 3D-Printed, Tactile, Highly-underactuated, Anthropomorphic Robot Hand with an Antagonistic Tendon Mechanism

A challenging and important problem for tendon-driven multi-fingered robotic hands is to ensure grasping adaptivity while minimizing the number of actuators needed to provide human-like functionality. Inspired by the Pisa/IIT SoftHand, this paper introduces a 3D-printed, highly-underactuated, tactile-sensorized, five-finger robotic hand named the Tactile SoftHand-A, which features an antagonistic mechanism to actively open and close the hand. Our proposed dual-tendon design gives options that allow active control of specific (distal or proximal interphalangeal) joints; for example, to adjust from an enclosing to fingertip grasp or to manipulate an object with a fingertip. We also develop and integrate a new design of fully 3D-printed vision-based tactile sensor within the fingers that requires minimal hand assembly. A control scheme based on analytically extracting contact location and slip from the tactile images is used to coordinate the antagonistic tendon mechanism (using a marker displacement density map, suitable for TacTip-based sensors). We perform extensive testing of a single finger, the entire hand, and the tactile capabilities to show the improvements in reactivity, load-bearing, and manipulability in comparison to a SoftHand that lacks the antagonistic mechanism. We also demonstrate the hand's reactivity to contact disturbances including slip, and how this enables teleoperated control from human hand gestures. Overall, this study points the way towards a class of low-cost, accessible, 3D-printable, tactile, underactuated human-like robotic hands, and we openly release the designs to facilitate others to build upon this work. The designs are open-sourced at https://github.com/HaoranLi-Data/Tactile_SoftHand_A

cs.RO↗

arXiv2025

RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis

The success of large language models (LLMs) has attracted many individuals to fine-tune them for domain-specific tasks by uploading their data. However, in sensitive areas like healthcare and finance, privacy concerns often arise. One promising solution is to generate synthetic data with Differential Privacy (DP) guarantees to replace private data. However, these synthetic data contain significant flawed data, which are considered as noise. Existing solutions typically rely on naive filtering by comparing ROUGE-L scores or embedding similarities, which are ineffective in addressing the noise. To address this issue, we propose \textit{RewardDS}, a novel privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation. Our \textit{RewardDS} introduces two key modules, Reward Guided Filtering and Self-Optimizing Refinement, to both filter and refine the synthetic data, effectively mitigating the noise. Extensive experiments across medical, financial, and code generation domains demonstrate the effectiveness of our method.

cs.CR↗

arXiv2025

ORCAS: Obfuscation-Resilient Binary Code Similarity Analysis using Dominance Enhanced Semantic Graph

Binary code similarity analysis (BCSA) serves as a foundational technique for binary analysis tasks such as vulnerability detection and malware identification. Existing graph based BCSA approaches capture more binary code semantics and demonstrate remarkable performance. However, when code obfuscation is applied, the unstable control flow structure degrades their performance. To address this issue, we develop ORCAS, an Obfuscation-Resilient BCSA model based on Dominance Enhanced Semantic Graph (DESG). The DESG is an original binary code representation, capturing more binaries' implicit semantics without control flow structure, including inter-instruction relations (e.g., def-use), inter-basic block relations (i.e., dominance and post-dominance), and instruction-basic block relations. ORCAS takes binary functions from different obfuscation options, optimization levels, and instruction set architectures as input and scores their semantic similarity more robustly. Extensive experiments have been conducted on ORCAS against eight baseline approaches over the BinKit dataset. For example, ORCAS achieves an average 12.1% PR-AUC improvement when using combined three obfuscation options compared to the state-of-the-art approaches. In addition, an original obfuscated real-world vulnerability dataset has been constructed and released to facilitate a more comprehensive research on obfuscated binary code analysis. ORCAS outperforms the state-of-the-art approaches over this newly released real-world vulnerability dataset by up to a recall improvement of 43%.

cs.CR↗

arXiv2025

Tech-ASan: Two-stage check for Address Sanitizer

Address Sanitizer (ASan) is a sharp weapon for detecting memory safety violations, including temporal and spatial errors hidden in C/C++ programs during execution. However, ASan incurs significant runtime overhead, which limits its efficiency in testing large software. The overhead mainly comes from sanitizer checks due to the frequent and expensive shadow memory access. Over the past decade, many methods have been developed to speed up ASan by eliminating and accelerating sanitizer checks, however, they either fail to adequately eliminate redundant checks or compromise detection capabilities. To address this issue, this paper presents Tech-ASan, a two-stage check based technique to accelerate ASan with safety assurance. First, we propose a novel two-stage check algorithm for ASan, which leverages magic value comparison to reduce most of the costly shadow memory accesses. Second, we design an efficient optimizer to eliminate redundant checks, which integrates a novel algorithm for removing checks in loops. Third, we implement Tech-ASan as a memory safety tool based on the LLVM compiler infrastructure. Our evaluation using the SPEC CPU2006 benchmark shows that Tech-ASan outperforms the state-of-the-art methods with 33.70% and 17.89% less runtime overhead than ASan and ASan--, respectively. Moreover, Tech-ASan detects 56 fewer false negative cases than ASan and ASan-- when testing on the Juliet Test Suite under the same redzone setting.

cs.SE↗

arXiv2025

PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis

Modern power systems are becoming increasingly dynamic, with changing topologies and time-varying loads driven by renewable energy variability, electric vehicle adoption, and active grid reconfiguration. Despite these changes, publicly available test cases remain scarce, due to security concerns and the significant effort required to anonymize real systems. Such limitations call for generative tools that can jointly synthesize grid structure and nodal dynamics. However, modeling the joint distribution of network topology, branch attributes, bus properties, and dynamic load profiles remains a major challenge, while preserving physical feasibility and avoiding prohibitive computational costs. We present PowerGrow, a co-generative framework that significantly reduces computational overhead while maintaining operational validity. The core idea is dependence decomposition: the complex joint distribution is factorized into a chain of conditional distributions over feasible grid topologies, time-series bus loads, and other system attributes, leveraging their mutual dependencies. By constraining the generation process at each stage, we implement a hierarchical graph beta-diffusion process for structural synthesis, paired with a temporal autoencoder that embeds time-series data into a compact latent space, improving both training stability and sample fidelity. Experiments across benchmark settings show that PowerGrow not only outperforms prior diffusion models in fidelity and diversity but also achieves a 98.9\% power flow convergence rate and improved N-1 contingency resilience. This demonstrates its ability to generate operationally valid and realistic power grid scenarios.

cs.LG↗

arXiv2025

FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real

Generalizable object fetching in cluttered scenes remains a fundamental and application-critical challenge in embodied AI. Closely packed objects cause inevitable occlusions, making safe action generation particularly difficult. Under such partial observability, effective policies must not only generalize across diverse objects and layouts but also reason about occlusion to avoid collisions. However, collecting large-scale real-world data for this task remains prohibitively expensive, leaving this problem largely unsolved. In this paper, we introduce FetchBot, a sim-to-real framework for this challenge. We first curate a large-scale synthetic dataset featuring 1M diverse scenes and 500k representative demonstrations. Based on this dataset, FetchBot employs a depth-conditioned method for action generation, which leverages structural cues to enable robust obstacle-aware action planning. However, depth is perfect in simulation but noisy in real-world environments. To address this sim-to-real gap, FetchBot predicts depth from RGB inputs using a foundation model and integrates local occupancy prediction as a pre-training task, providing a generalizable latent representation for sim-to-real transfer. Extensive experiments in simulation and real-world environments demonstrate the strong zero-shot sim-to-real transfer, effective clutter handling, and adaptability to novel scenarios. In cluttered environments, it achieves an average real-world success rate of 89.95%, significantly outperforming prior methods. Moreover, FetchBot demonstrates excellent robustness in challenging cases, such as fetching transparent, reflective, and irregular objects, highlighting its practical value.

cs.RO↗

arXiv2025

On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions

Conceptualization, a fundamental element of human cognition, plays a pivotal role in human generalizable reasoning. Generally speaking, it refers to the process of sequentially abstracting specific instances into higher-level concepts and then forming abstract knowledge that can be applied in unfamiliar or novel situations. This enhances models' inferential capabilities and supports the effective transfer of knowledge across various domains. Despite its significance, the broad nature of this term has led to inconsistencies in understanding conceptualization across various works, as there exists different types of instances that can be abstracted in a wide variety of ways. There is also a lack of a systematic overview that comprehensively examines existing works on the definition, execution, and application of conceptualization to enhance reasoning tasks. In this paper, we address these gaps by first proposing a categorization of different types of conceptualizations into four levels based on the types of instances being conceptualized, in order to clarify the term and define the scope of our work. Then, we present the first comprehensive survey of over 150 papers, surveying various definitions, resources, methods, and downstream applications related to conceptualization into a unified taxonomy, with a focus on the entity and event levels. Furthermore, we shed light on potential future directions in this field and hope to garner more attention from the community.

cs.CL↗

arXiv2025

From Imperfect Signals to Trustworthy Structure: Confidence-Aware Inference from Heterogeneous and Reliability-Varying Utility Data

Accurate distribution grid topology is essential for reliable modern grid operations. However, real-world utility data originates from multiple sources with varying characteristics and levels of quality. In this work, developed in collaboration with Oncor Electric Delivery, we propose a scalable framework that reconstructs a trustworthy grid topology by systematically integrating heterogeneous data. We observe that distribution topology is fundamentally governed by two complementary dimensions: the spatial layout of physical infrastructure (e.g., GIS and asset metadata) and the dynamic behavior of the system in the signal domain (e.g., voltage time series). When jointly leveraged, these dimensions support a complete and physically coherent reconstruction of network connectivity. To address the challenge of uneven data quality without compromising observability, we introduce a confidence-aware inference mechanism that preserves structurally informative yet imperfect inputs, while quantifying the reliability of each inferred connection for operator interpretation. This soft handling of uncertainty is tightly coupled with hard enforcement of physical feasibility: we embed operational constraints, such as transformer capacity limits and radial topology requirements, directly into the learning process. Together, these components ensure that inference is both uncertainty-aware and structurally valid, enabling rapid convergence to actionable, trustworthy topologies under real-world deployment conditions. The proposed framework is validated using data from over 8000 meters across 3 feeders in Oncor's service territory, demonstrating over 95% accuracy in topology reconstruction and substantial improvements in confidence calibration and computational efficiency relative to baseline methods.

cs.LG↗