Related papers: Agentic Vulnerability Reasoning on Windows COM Bin…
As Large Language Models (LLMs) become increasingly accessible to end users, an ever-growing number of inference requests are initiated from edge devices and computed on centralized GPU clusters. However, the resulting exponential growth in…
Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, this autonomy introduces a previously unrecognized security…
Smart contracts are important for digital finance, yet they are hard to patch once deployed. Prior work has mainly explored LLMs for smart contract vulnerability detection, leaving end-to-end automated exploit generation (AEG) much less…
Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely integrated into newer models' safety training. However, we…
CTI-REALM (Cyber Threat Real World Evaluation and LLM Benchmarking) is a benchmark designed to evaluate AI agents' ability to interpret cyber threat intelligence (CTI) and develop detection rules. The benchmark provides a realistic…
The identification of vulnerabilities is an important element in the software development life cycle to ensure the security of software. While vulnerability identification based on the source code is a well studied field, the identification…
OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of…
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…
Despite the critical threat posed by software security vulnerabilities, reports are often incomplete, lacking the proof-of-vulnerability (PoV) tests needed to validate fixes and prevent regressions. These tests are crucial not only for…
Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification, we evaluate Claude Code in an agentic proving…
The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose…
Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…
Proof-of-work(PoW) is an algorithmic tool used to secure networks by imposing a computational cost on participating devices. Unfortunately, traditional PoW schemes require that correct devices perform significant computational work in…
Agent skills extend local AI agents, such as Claude Code or Open Claw, with additional functionality, and their popularity has led to the emergence of dedicated skill marketplaces, similar to app stores for mobile applications.…
Agentic systems are increasingly acting on users' behalf, accessing calendars, email, and personal files to complete everyday tasks. Privacy evaluation for these systems has focused on the input and output boundaries, but each task involves…
Crash narratives in crash reports provide crucial contextual information for traffic safety analysis. Yet, their broader use is hindered by the presence of personally identifiable information (PII), including names, home addresses, and…
Large language models (LLMs) are increasingly being applied to programming tasks, ranging from single-turn code completion to autonomous agents. Current code agent designs frequently depend on complex, hand-crafted workflows and tool sets.…
We present an empirical study of how far general-purpose coding agents -- without hardware-specific training -- can optimize hardware designs from high-level algorithmic specifications. We introduce an agent factory, a two-stage pipeline…
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…
We introduce SOCK, a benchmark command line interface (CLI) that measures large language models' (LLMs) ability to self-replicate without human intervention. In this benchmark, self-replication is defined not only as an LLM's ability to…