Jianbo Gao

Che Wang, Jiaming Zhang, Ziqi Zhang et al. · gatech

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.

Yue Li, Lei Wang, Kaixuan Wang et al.

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.

Che Wang, Fuyao Zhang, Jiaming Zhang et al.

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.

Zhenhao Wu, Jiashuo Zhang, Jianbo Gao et al.

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.