arXiv subjects

Baihe Ma

Publications and source records attributed to Baihe Ma.

9 recordsLinked to original sources

arXiv2026

SoK: Agentic Skills -- Beyond Tool Use in LLM Agents

Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit applicability conditions, execution policies, termination criteria, and reusable interfaces. Unlike one-off plans or atomic tool calls, skills operate (and often do well) across tasks. This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies. The first is a system-level set of \textbf{seven design patterns} capturing how skills are packaged and executed in practice, from metadata-driven progressive disclosure and executable code skills to self-evolving libraries and marketplace distribution. The second is an orthogonal \textbf{representation $\times$ scope} taxonomy describing what skills \emph{are} (natural language, code, policy, hybrid) and what environments they operate over (web, OS, software engineering, robotics). We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution, grounded by a case study of the ClawHavoc campaign in which nearly 1{,}200 malicious skills infiltrated a major agent marketplace, exfiltrating API keys, cryptocurrency wallets, and browser credentials at scale. We further survey deterministic evaluation approaches, anchored by recent benchmark evidence that curated skills can substantially improve agent success rates while self-generated skills may degrade them. We conclude with open challenges toward robust, verifiable, and certifiable skills for real-world autonomous agents.

cs.CR↗

arXiv2025

CAN-Trace Attack: Exploit CAN Messages to Uncover Driving Trajectories

Driving trajectory data remains vulnerable to privacy breaches despite existing mitigation measures. Traditional methods for detecting driving trajectories typically rely on map-matching the path using Global Positioning System (GPS) data, which is susceptible to GPS data outage. This paper introduces CAN-Trace, a novel privacy attack mechanism that leverages Controller Area Network (CAN) messages to uncover driving trajectories, posing a significant risk to drivers' long-term privacy. A new trajectory reconstruction algorithm is proposed to transform the CAN messages, specifically vehicle speed and accelerator pedal position, into weighted graphs accommodating various driving statuses. CAN-Trace identifies driving trajectories using graph-matching algorithms applied to the created graphs in comparison to road networks. We also design a new metric to evaluate matched candidates, which allows for potential data gaps and matching inaccuracies. Empirical validation under various real-world conditions, encompassing different vehicles and driving regions, demonstrates the efficacy of CAN-Trace: it achieves an attack success rate of up to 90.59% in the urban region, and 99.41% in the suburban region.

cs.CR↗

arXiv2025

SoK: Semantic Privacy in Large Language Models

As Large Language Models (LLMs) are increasingly deployed in sensitive domains, traditional data privacy measures prove inadequate for protecting information that is implicit, contextual, or inferable - what we define as semantic privacy. This Systematization of Knowledge (SoK) introduces a lifecycle-centric framework to analyze how semantic privacy risks emerge across input processing, pretraining, fine-tuning, and alignment stages of LLMs. We categorize key attack vectors and assess how current defenses, such as differential privacy, embedding encryption, edge computing, and unlearning, address these threats. Our analysis reveals critical gaps in semantic-level protection, especially against contextual inference and latent representation leakage. We conclude by outlining open challenges, including quantifying semantic leakage, protecting multimodal inputs, balancing de-identification with generation quality, and ensuring transparency in privacy enforcement. This work aims to inform future research on designing robust, semantically aware privacy-preserving techniques for LLMs.

cs.CR↗

arXiv2025

PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking

Our evaluation shows that PoLO achieves \textbf{99\%} watermark detection accuracy for ownership verification, while preserving data privacy and cutting verification costs to just \textbf{1.5--10\%} of traditional methods. Forging PoLO demands \textbf{1.1--4$\times$} more resources than honest proof generation, with the original proof retaining over \textbf{90\%} detection accuracy even after attacks.

cs.CR↗

arXiv2025

Location Privacy Threats and Protections in 6G Vehicular Networks: A Comprehensive Review

Location privacy is critical in vehicular networks, where drivers' trajectories and personal information can be exposed, allowing adversaries to launch data and physical attacks that threaten drivers' safety and personal security. This survey reviews comprehensively different localization techniques, including widely used ones like sensing infrastructure-based, optical vision-based, and cellular radio-based localization, and identifies inadequately addressed location privacy concerns. We classify Location Privacy Preserving Mechanisms (LPPMs) into user-side, server-side, and user-server-interface-based, and evaluate their effectiveness. Our analysis shows that the user-server-interface-based LPPMs have received insufficient attention in the literature, despite their paramount importance in vehicular networks. Further, we examine methods for balancing data utility and privacy protection for existing LPPMs in vehicular networks and highlight emerging challenges from future upper-layer location privacy attacks, wireless technologies, and network convergences. By providing insights into the relationship between localization techniques and location privacy, and evaluating the effectiveness of different LPPMs, this survey can help inform the development of future LPPMs in vehicular networks.

cs.CR↗

arXiv2024

ByCAN: Reverse Engineering Controller Area Network (CAN) Messages from Bit to Byte Level

As the primary standard protocol for modern cars, the Controller Area Network (CAN) is a critical research target for automotive cybersecurity threats and autonomous applications. As the decoding specification of CAN is a proprietary black-box maintained by Original Equipment Manufacturers (OEMs), conducting related research and industry developments can be challenging without a comprehensive understanding of the meaning of CAN messages. In this paper, we propose a fully automated reverse-engineering system, named ByCAN, to reverse engineer CAN messages. ByCAN outperforms existing research by introducing byte-level clusters and integrating multiple features at both byte and bit levels. ByCAN employs the clustering and template matching algorithms to automatically decode the specifications of CAN frames without the need for prior knowledge. Experimental results demonstrate that ByCAN achieves high accuracy in slicing and labeling performance, i.e., the identification of CAN signal boundaries and labels. In the experiments, ByCAN achieves slicing accuracy of 80.21%, slicing coverage of 95.21%, and labeling accuracy of 68.72% for general labels when analyzing the real-world CAN frames.

cs.CR↗

arXiv2023

Split Unlearning

We introduce Split Unlearning, a novel machine unlearning technology designed for Split Learning (SL), enabling the first-ever implementation of Sharded, Isolated, Sliced, and Aggregated (SISA) unlearning in SL frameworks. Particularly, the tight coupling between clients and the server in existing SL frameworks results in frequent bidirectional data flows and iterative training across all clients, violating the "Isolated" principle and making them struggle to implement SISA for independent and efficient unlearning. To address this, we propose SplitWiper with a new one-way-one-off propagation scheme, which leverages the inherently "Sharded" structure of SL and decouples neural signal propagation between clients and the server, enabling effective SISA unlearning even in scenarios with absent clients. We further design SplitWiper+ to enhance client label privacy, which integrates differential privacy and label expansion strategy to defend the privacy of client labels against the server and other potential adversaries. Experiments across diverse data distributions and tasks demonstrate that SplitWiper achieves 0% accuracy for unlearned labels, and 8% better accuracy for retained labels than non-SISA unlearning in SL. Moreover, the one-way-one-off propagation maintains constant overhead, reducing computational and communication costs by 99%. SplitWiper+ preserves 90% of label privacy when sharing masked labels with the server.

cs.CR↗

arXiv2023

A Secure Aggregation for Federated Learning on Long-Tailed Data

As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presence of Byzantine nodes in the FL scenario. A novel two-layer aggregation method is proposed for the rejection of malicious models and the advisable selection of valuable models containing tail class data information. We introduce the concept of think tank to leverage the wisdom of all participants. Preliminary experiments validate that the think tank can make effective model selections for global aggregation.

cs.LG↗

arXiv2023

Blockchained Federated Learning for Internet of Things: A Comprehensive Survey

The demand for intelligent industries and smart services based on big data is rising rapidly with the increasing digitization and intelligence of the modern world. This survey comprehensively reviews Blockchained Federated Learning (BlockFL) that joins the benefits of both Blockchain and Federated Learning to provide a secure and efficient solution for the demand. We compare the existing BlockFL models in four Internet-of-Things (IoT) application scenarios: Personal IoT (PIoT), Industrial IoT (IIoT), Internet of Vehicles (IoV), and Internet of Health Things (IoHT), with a focus on security and privacy, trust and reliability, efficiency, and data heterogeneity. Our analysis shows that the features of decentralization and transparency make BlockFL a secure and effective solution for distributed model training, while the overhead and compatibility still need further study. It also reveals the unique challenges of each domain presents unique challenges, e.g., the requirement of accommodating dynamic environments in IoV and the high demands of identity and permission management in IoHT, in addition to some common challenges identified, such as privacy, resource constraints, and data heterogeneity. Furthermore, we examine the existing technologies that can benefit BlockFL, thereby helping researchers and practitioners to make informed decisions about the selection and development of BlockFL for various IoT application scenarios.

cs.LG↗