arXiv subjects

Jianbo Gao

Publications and source records attributed to Jianbo Gao.

At least 19 recordsLinked to original sources

arXiv2026

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Representation Engineering analyses often characterize refusal using static directions extracted from terminal or pooled representations. We ask whether this view misses how refusal is constructed across layer-token positions. Using causal tracing, we identify a \textit{Refusal Trajectory}: a sparse upstream activation pattern that often persists even when attacks such as GCG suppress terminal refusal signals. Based on this observation, we propose SALO (Sparse Activation Localization Operator), a lightweight white-box detector that operates on raw hidden-state volumes from a selected layer window. Across Qwen, Llama, and Mistral models, SALO improves jailbreak detection on several attack families under a fixed XSTest-calibrated operating point. We further analyze static RepE-style baselines, ROI sensitivity, adaptive GCG attacks, and encoded-input boundary cases, clarifying both the promise and limitations of refusal-trajectory monitoring.

cs.CR↗

arXiv2026

A402: Binding Cryptocurrency Payments to Service Execution for Agentic Commerce

The rapid proliferation of autonomous AI agents is driving a shift toward agentic commerce, where agents are expected to autonomously invoke and pay for services. While blockchain-based payments offer a programmable foundation for such interactions, the recently proposed x402 standard fails to enforce end-to-end atomicity across service execution, payment, and result delivery. In this paper, we present A402, a trust-minimized payment architecture that securely binds cryptocurrency payments to service execution. A402 introduces Atomic Service Channels (ASCs), a new channel protocol that integrates service execution into payment channels, enabling real-time, high-frequency micropayments for agentic commerce. Within each ASC, A402 employs an atomic exchange protocol based on TEE-assisted adaptor signatures, ensuring that payments are finalized if and only if the requested service is correctly executed and the corresponding result is delivered. To further ensure privacy, A402 incorporates a TEE-based Liquidity Vault that privately manages the lifecycle of ASCs and aggregates their settlements into a single on-chain transaction, revealing only aggregated balances. We implement A402 and evaluate it against x402 with integrations on both Bitcoin and Ethereum. Our results show that A402 delivers orders-of-magnitude performance and on-chain cost improvements over x402 while providing trust-minimized security guarantees.

cs.DC↗

arXiv2026

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction

Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution. Existing defenses typically rely on strict filtering or refusal mechanisms, which suffer from a critical limitation: over-refusal, prematurely terminating valid agentic workflows. We propose ICON, a probing-to-mitigation framework that neutralizes attacks while preserving task continuity. Our key insight is that IPI attacks leave distinct over-focusing signatures in the latent space. We introduce a Latent Space Trace Prober to detect attacks based on high intensity scores. Subsequently, a Mitigating Rectifier performs surgical attention steering that selectively manipulate adversarial query key dependencies while amplifying task relevant elements to restore the LLM's functional trajectory. Extensive evaluations on multiple backbones show that ICON achieves a competitive 0.4% ASR, matching commercial grade detectors, while yielding a over 50% task utility gain. Furthermore, ICON demonstrates robust Out of Distribution(OOD) generalization and extends effectively to multi-modal agents, establishing a superior balance between security and efficiency.

cs.AI↗

arXiv2026

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection (IPI) attacks. Existing attack methods are limited by their reliance on static patterns and evaluation on simple language models, failing to address the fast-evolving nature of modern AI agents. We introduce AdapTools, a novel adaptive IPI attack framework that selects stealthier attack tools and generates adaptive attack prompts to create a rigorous security evaluation environment. Our approach comprises two key components: (1) Adaptive Attack Strategy Construction, which develops transferable adversarial strategies for prompt optimization, and (2) Attack Enhancement, which identifies stealthy tools capable of circumventing task-relevance defenses. Comprehensive experimental evaluation shows that AdapTools achieves a 2.13 times improvement in attack success rate while degrading system utility by a factor of 1.78. Notably, the framework maintains its effectiveness even against state-of-the-art defense mechanisms. Our method advances the understanding of IPI attacks and provides a useful reference for future research.

cs.CR↗

arXiv2025

AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection

Recent advancement in large-scale Artificial Intelligence (AI) models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution (OoD) data as backdoor watermarks and retrain the original model for copyright protection. However, existing methods are susceptible to malicious detection and forgery by adversaries, resulting in watermark evasion. In this work, we propose Model-\underline{ag}nostic Black-box Backdoor W\underline{ate}rmarking Framework (AGATE) to address stealthiness and robustness challenges in multimodal model copyright protection. Specifically, we propose an adversarial trigger generation method to generate stealthy adversarial triggers from ordinary dataset, providing visual fidelity while inducing semantic shifts. To alleviate the issue of anomaly detection among model outputs, we propose a post-transform module to correct the model output by narrowing the distance between adversarial trigger image embedding and text embedding. Subsequently, a two-phase watermark verification is proposed to judge whether the current model infringes by comparing the two results with and without the transform module. Consequently, we consistently outperform state-of-the-art methods across five datasets in the downstream tasks of multimodal image-text retrieval and image classification. Additionally, we validated the robustness of AGATE under two adversarial attack scenarios.

cs.CR↗

arXiv2024

ContractTinker: LLM-Empowered Vulnerability Repair for Real-World Smart Contracts

Smart contracts are susceptible to being exploited by attackers, especially when facing real-world vulnerabilities. To mitigate this risk, developers often rely on third-party audit services to identify potential vulnerabilities before project deployment. Nevertheless, repairing the identified vulnerabilities is still complex and labor-intensive, particularly for developers lacking security expertise. Moreover, existing pattern-based repair tools mostly fail to address real-world vulnerabilities due to their lack of high-level semantic understanding. To fill this gap, we propose ContractTinker, a Large Language Models (LLMs)-empowered tool for real-world vulnerability repair. The key insight is our adoption of the Chain-of-Thought approach to break down the entire generation task into sub-tasks. Additionally, to reduce hallucination, we integrate program static analysis to guide the LLM. We evaluate ContractTinker on 48 high-risk vulnerabilities. The experimental results show that among the patches generated by ContractTinker, 23 (48%) are valid patches that fix the vulnerabilities, while 10 (21%) require only minor modifications. A video of ContractTinker is available at https://youtu.be/HWFVi-YHcPE.

cs.SE↗

arXiv2024

Demystifying and Detecting Cryptographic Defects in Ethereum Smart Contracts

Ethereum has officially provided a set of system-level cryptographic APIs to enhance smart contracts with cryptographic capabilities. These APIs have been utilized in over 10% of Ethereum transactions, motivating developers to implement various on-chain cryptographic tasks, such as digital signatures. However, since developers may not always be cryptographic experts, their ad-hoc and potentially defective implementations could compromise the theoretical guarantees of cryptography, leading to real-world security issues. To mitigate this threat, we conducted the first study aimed at demystifying and detecting cryptographic defects in smart contracts. Through the analysis of 2,406 real-world security reports, we defined nine types of cryptographic defects in smart contracts with detailed descriptions and practical detection patterns. Based on this categorization, we proposed CrySol, a fuzzing-based tool to automate the detection of cryptographic defects in smart contracts. It combines transaction replaying and dynamic taint analysis to extract fine-grained crypto-related semantics and employs crypto-specific strategies to guide the test case generation process. Furthermore, we collected a large-scale dataset containing 25,745 real-world crypto-related smart contracts and evaluated CrySol's effectiveness on it. The result demonstrated that CrySol achieves an overall precision of 95.4% and a recall of 91.2%. Notably, CrySol revealed that 5,847 (22.7%) out of 25,745 smart contracts contain at least one cryptographic defect, highlighting the prevalence of these defects.

cs.CR↗

arXiv2023

When Contracts Meets Crypto: Exploring Developers' Struggles with Ethereum Cryptographic APIs

To empower smart contracts with the promising capabilities of cryptography, Ethereum officially introduced a set of cryptographic APIs that facilitate basic cryptographic operations within smart contracts, such as elliptic curve operations. However, since developers are not necessarily cryptography experts, requiring them to directly interact with these basic APIs has caused real-world security issues and potential usability challenges. To guide future research and solutions to these challenges, we conduct the first empirical study on Ethereum cryptographic practices. Through the analysis of 91,484,856 Ethereum transactions, 500 crypto-related contracts, and 483 StackExchange posts, we provide the first in-depth look at cryptographic tasks developers need to accomplish and identify five categories of obstacles they encounter. Furthermore, we conduct an online survey with 78 smart contract practitioners to explore their perspectives on these obstacles and elicit the underlying reasons. We find that more than half of practitioners face more challenges in cryptographic tasks compared to general business logic in smart contracts. Their feedback highlights the gap between low-level cryptographic APIs and high-level tasks they need to accomplish, emphasizing the need for improved cryptographic APIs, task-based templates, and effective assistance tools. Based on these findings, we provide practical implications for further improvements and outline future research directions.

cs.SE↗

arXiv2022

Xscope: Hunting for Cross-Chain Bridge Attacks

Cross-Chain bridges have become the most popular solution to support asset interoperability between heterogeneous blockchains. However, while providing efficient and flexible cross-chain asset transfer, the complex workflow involving both on-chain smart contracts and off-chain programs causes emerging security issues. In the past year, there have been more than ten severe attacks against cross-chain bridges, causing billions of loss. With few studies focusing on the security of cross-chain bridges, the community still lacks the knowledge and tools to mitigate this significant threat. To bridge the gap, we conduct the first study on the security of cross-chain bridges. We document three new classes of security bugs and propose a set of security properties and patterns to characterize them. Based on those patterns, we design Xscope, an automatic tool to find security violations in cross-chain bridges and detect real-world attacks. We evaluate Xscope on four popular cross-chain bridges. It successfully detects all known attacks and finds suspicious attacks unreported before. A video of Xscope is available at https://youtu.be/vMRO_qOqtXY.

cs.SE↗

arXiv2022

Learning Entity Linking Features for Emerging Entities

Entity linking (EL) is the process of linking entity mentions appearing in text with their corresponding entities in a knowledge base. EL features of entities (e.g., prior probability, relatedness score, and entity embedding) are usually estimated based on Wikipedia. However, for newly emerging entities (EEs) which have just been discovered in news, they may still not be included in Wikipedia yet. As a consequence, it is unable to obtain required EL features for those EEs from Wikipedia and EL models will always fail to link ambiguous mentions with those EEs correctly as the absence of their EL features. To deal with this problem, in this paper we focus on a new task of learning EL features for emerging entities in a general way. We propose a novel approach called STAMO to learn high-quality EL features for EEs automatically, which needs just a small number of labeled documents for each EE collected from the Web, as it could further leverage the knowledge hidden in the unlabeled data. STAMO is mainly based on self-training, which makes it flexibly integrated with any EL feature or EL model, but also makes it easily suffer from the error reinforcement problem caused by the mislabeled data. Instead of some common self-training strategies that try to throw the mislabeled data away explicitly, we regard self-training as a multiple optimization process with respect to the EL features of EEs, and propose both intra-slot and inter-slot optimizations to alleviate the error reinforcement problem implicitly. We construct two EL datasets involving selected EEs to evaluate the quality of obtained EL features for EEs, and the experimental results show that our approach significantly outperforms other baseline methods of learning EL features.

cs.CL↗

arXiv2022

Community Question Answering Entity Linking via Leveraging Auxiliary Data

Community Question Answering (CQA) platforms contain plenty of CQA texts (i.e., questions and answers corresponding to the question) where named entities appear ubiquitously. In this paper, we define a new task of CQA entity linking (CQAEL) as linking the textual entity mentions detected from CQA texts with their corresponding entities in a knowledge base. This task can facilitate many downstream applications including expert finding and knowledge base enrichment. Traditional entity linking methods mainly focus on linking entities in news documents, and are suboptimal over this new task of CQAEL since they cannot effectively leverage various informative auxiliary data involved in the CQA platform to aid entity linking, such as parallel answers and two types of meta-data (i.e., topic tags and users). To remedy this crucial issue, we propose a novel transformer-based framework to effectively harness the knowledge delivered by different kinds of auxiliary data to promote the linking performance. We validate the superiority of our framework through extensive experiments over a newly released CQAEL data set against state-of-the-art entity linking methods.

cs.CL↗

arXiv2021

Efficient Byzantine Fault Tolerance using Trusted Execution Environment: Preventing Equivocation is only the Beginning

With the rapid development of blockchain, Byzantine fault-tolerant protocols have attracted revived interest recently. To overcome the theoretical bounds of Byzantine fault tolerance, many protocols attempt to use Trusted Execution Environment (TEE) to prevent equivocation and improve performance and scalability. However, due to the broken quorum intersection assumption caused by the reduction of the replica number, the improvement is mostly at the cost of increased communication complexity which prevents existing TEE-based protocols to be applied to large-scale blockchain systems. In this paper, we propose TBFT, an efficient Byzantine fault-tolerant protocol in the partial synchrony setting, which has O(n) message complexity in both normal-case and view-change. Compared to previous protocols, TBFT uses TEE-assisted primitives to limit more types of malicious behaviors of replicas rather than preventing equivocation only, thereby reducing the latency and communication complexity of clients and replicas. Besides, we also introduce lightweight cryptographic primitives including a novel leader election mechanism and an efficient voting message aggregation mechanism for better security and performance. We evaluate TBFT via systematic analysis and experiments, and the results show that TBFT has better performance and scalability compared to other protocols.

cs.DC↗

arXiv2021

NNLO soft function for threshold single inclusive jet production

We present a computation of the global soft function for single-inclusive hadronic jet production at next-to-next-to-leading order (NNLO) in the strong coupling constant involving four light-like Wilson lines. Our soft function belongs to SCET$_{\text I}$ observables obeying the non-Abelian exponentiation theorem. We provide the calculation of the soft function involving four collinear light-cone directions for all $2\rightarrow2$ processes extending the previous result. We perform the threshold resummation for these processes at the next-to-next-to-leading logarithmic accuracy and present the corresponding numerical results.

hep-ph↗

arXiv2021

TrustCross: Enabling Confidential Interoperability across Blockchains Using Trusted Hardware

With the rapid development of blockchain technology, different types of blockchains are adopted and interoperability across blockchains has received widespread attention. There have been many cross-chain solutions proposed in recent years, including notary scheme, sidechain, and relay chain. However, most of the existing platforms do not take confidentiality into account, although privacy has become an important concern for blockchain. In this paper, we present TrustCross, a privacy-preserving cross-chain platform to enable confidential interoperability across blockchains. The key insight behind TrustCross is to encrypt cross-chain communication data on the relay chain with the assistance of trusted execution environment and employ fine-grained access control to protect user privacy. Our experimental results show that TrustCross achieves reasonable latency and high scalability on the contract calls across heterogeneous blockchains.

cs.CR↗

arXiv2020

Kaya: A Testing Framework for Blockchain-based Decentralized Applications

In recent years, many decentralized applications based on blockchain (DApp) have been developed. However, due to inadequate testing, DApps are easily exposed to serious vulnerabilities. We find three main challenges for DApp testing, i.e., the inherent complexity of DApp, inconvenient pre-state setting, and not-so-readable logs. In this paper, we propose a testing framework named Kaya to bridge these gaps. Kaya has three main functions. Firstly, Kaya proposes DApp behavior description language (DBDL) to make writing test cases easier. Test cases written in DBDL can also be automatically executed by Kaya. Secondly, Kaya supports a flexible and convenient way for test engineers to set the blockchain pre-states easily. Thirdly, Kaya transforms incomprehensible addresses into readable variables for easy comprehension. With these functions, Kaya can help test engineers test DApps more easily. Besides, to fit the various application environments, we provide two ways for test engineers to use Kaya, i.e., UI and command-line. Our experimental case demonstrates the potential of Kaya in helping test engineers to test DApps more easily.

cs.SE↗

arXiv2019

Performance Analysis of the Libra Blockchain: An Experimental Study

Since Bitcoin was first introduced in 2008, many types of cryptocurrencies have been proposed based on blockchain. However, the performance of permissionless blockchains restricts the widespread of cryptocurrency. Recently, Libra was proposed by Facebook based on a permissioned blockchain, i.e. the Libra blockchain. The vision of Libra is to become a global currency supporting financial applications, but it is doubted whether the performance of the Libra blockchain is able to support frequent micropayment scenarios. In this paper, we propose a methodology to evaluate the performance of blockchain platforms and conducted an experimental study on the Libra blockchain. The results show that the Libra blockchain can only process about one thousand transactions per second at most, and the performance drops significantly as the number of validators increases. Although it outperforms permissionless blockchain platforms, the performance of the Libra blockchain is still unsatisfactory compared to other permissioned blockchains like Hyperledger Fabric and needs to make effective improvements in order to support global micropayment in the future.

cs.DC↗

arXiv2019

SEdroid: A Robust Android Malware Detector using Selective Ensemble Learning

For the dramatic increase of Android malware and low efficiency of manual check process, deep learning methods started to be an auxiliary means for Android malware detection these years. However, these models are highly dependent on the quality of datasets, and perform unsatisfactory results when the quality of training data is not good enough. In the real world, the quality of datasets without manually check cannot be guaranteed, even Google Play may contain malicious applications, which will cause the trained model failure. To address the challenge, we propose a robust Android malware detection approach based on selective ensemble learning, trying to provide an effective solution not that limited to the quality of datasets. The proposed model utilizes genetic algorithm to help find the best combination of the component learners and improve robustness of the model. Our results show that the proposed approach achieves a more robust performance than other approaches in the same area.

cs.CR↗

arXiv2019

EASYFLOW: Keep Ethereum Away From Overflow

While Ethereum smart contracts enabled a wide range of blockchain applications, they are extremely vulnerable to different forms of security attacks. Due to the fact that transactions to smart contracts commonly involve cryptocurrency transfer, any successful attacks can lead to money loss or even financial disorder. In this paper, we focus on the overflow attacks in Ethereum , mainly because they widely rooted in many smart contracts and comparatively easy to exploit. We have developed EASYFLOW , an overflow detector at Ethereum Virtual Machine level. The key insight behind EASYFLOW is a taint analysis based tracking technique to analyze the propagation of involved taints. Specifically, EASYFLOW can not only divide smart contracts into safe contracts, manifested overflows, well-protected overflows and potential overflows, but also automatically generate transactions to trigger potential overflows. In our preliminary evaluation, EASYFLOW managed to find potentially vulnerable Ethereum contracts with little runtime overhead.

cs.SE↗