Related papers: PoCo: Agentic Proof-of-Concept Exploit Generation …
The deployment of autonomous AI agents capable of executing commercial transactions has motivated the adoption of mandate-based payment authorization protocols, including the Universal Commerce Protocol (UCP) and the Agent Payments Protocol…
While large language models have significantly accelerated scientific code generation, comprehensively evaluating the generated code remains a major challenge. Traditional benchmarks reduce evaluation to test-case matching, an approach…
Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…
The increasing deployment of autonomous AI agents on the web is hampered by a fundamental misalignment: agents must infer affordances from human-oriented user interfaces, leading to brittle, inefficient, and insecure interactions. To…
Blockchain technology enables secure, transparent data management in decentralized systems, supporting applications from cryptocurrencies like Bitcoin to tokenizing real-world assets like property. Its scalability and sustainability hinge…
Autonomous AI agents are beginning to operate across organizational boundaries on the open internet -- discovering, transacting with, and delegating to agents owned by other parties without centralized oversight. When agents from different…
Smart contracts are immutable, verifiable, and autonomous pieces of code that can be deployed and ran on blockchain networks like Ethereum. Due to the immutability nature of blockchain, no change is possible on a deployed smart contract or…
Security has become a main concern for the smart grid to move from research and development to industry. The concept of security has usually referred to resistance to threats by an active or passive attacker. However, since smart meters…
Smart contracts are autonomous and immutable pieces of code that are deployed on blockchain networks and run by miners. They were first introduced by Ethereum in 2014 and have since been used for various applications such as security…
Security attacks targeting smart contracts have been on the rise, which have led to financial loss and erosion of trust. Therefore, it is important to enable developers to discover security vulnerabilities in smart contracts before…
While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike execution-based tools (e.g., code or math), whose effects are…
The great economic values of deep neural networks (DNNs) urge AI enterprises to protect their intellectual property (IP) for these models. Recently, proof-of-training (PoT) has been proposed as a promising solution to DNN IP protection,…
This paper presents a first empirical study of agentic AI as autonomous decision-makers in decentralized governance. Using more than 3K proposals from major protocols, we build an agentic AI voter that interprets proposal contexts,…
Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…
Smart contracts underpin high-value ecosystems such as decentralized finance (DeFi), yet recurring vulnerabilities continue to cause losses worth billions of dollars. Although numerous security analyzers that detect such flaws exist,…
Traditional static cybersecurity models often struggle with scalability, real-time detection, and contextual responsiveness in the current digital product ecosystems which include cloud services, application programming interfaces (APIs),…
Software vulnerabilities continue to grow in volume and remain difficult to detect in practice. Although learning-based vulnerability detection has progressed, existing benchmarks are largely function-centric and fail to capture realistic,…
In this work, we provide a comprehensive survey of smart contract upgradability patterns using proxies. A primary characteristic of smart contracts on the Ethereum blockchain is that they are immutable once implemented, no changes can be…
This paper presents DeCon, a declarative programming language for implementing smart contracts and specifying contract-level properties. Driven by the observation that smart contract operations and contract-level properties can be naturally…
Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…