Related papers: Agentic Vulnerability Reasoning on Windows COM Bin…

Recent Microsoft security bulletins show that kernel vulnerabilities are becoming more and more important security threats. Despite the pretty extensive security mitigations many of the kernel vulnerabilities are still exploitable.…

Model checkers and consistency checkers detect critical errors in router configurations, but these tools require significant manual effort to develop and maintain. LLM-based Q&A models have emerged as a promising alternative, allowing users…

AI agent protocols -- including MCP, A2A, ANP, and ACP -- enable autonomous agents to discover capabilities, delegate tasks, and compose services across trust boundaries. Despite massive deployment (MCP alone has 97M+ monthly SDK…

Suppose Alice wishes to send messages to Bob through a communication channel C_1, but her transmissions also reach an eavesdropper Eve through another channel C_2. The goal is to design a coding scheme that makes it possible for Alice to…

The ever-increasing size of open-source Large Language Models (LLMs) renders local deployment impractical for individual users. Decentralized computing has emerged as a cost-effective solution, allowing individuals and small companies to…

Safety evaluations of language models often treat serving configuration as fixed background infrastructure, but batch condition is an untested treatment variable whenever the same prompt may be evaluated alone, in a synchronized batch, or…

Specification synthesis, the task of automatically inferring formal specifications from program implementations and natural language, is important for refactoring, transpilation, optimization, and verification, yet remains an open challenge…

While recent LLM-based agents can identify many candidate bugs in source code, their reports remain static hypotheses that require manual validation, limiting the practicality of automated bug detection. We frame this challenge as a test…

The code generation capabilities of Large Language Models (LLMs) have transformed the field of software development. However, this advancement also presents significant security challenges, as LLM-generated code often contains…

Software vulnerabilities are a serious and crucial concern. Typically, in a program or function consisting of hundreds or thousands of source code statements, there are only a few statements causing the corresponding vulnerabilities. Most…

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…

Agentic AI in software product development is increasingly adopted by organizations, yet the field lacks a consolidated synthesis of where adoption is mature, which architectural patterns dominate, and what limitations and coping mechanisms…

Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge…

Large Language Models (LLMs) and Vision-Language Models (VLMs) remain highly vulnerable to textual and visual jailbreaks, as well as prompt injections (arXiv:2307.15043, Greshake et al., 2023, arXiv:2306.13213). Existing defenses often…

LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a…

Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual clues such as names, locations, and cultural stereotypes, rather than the underlying…

DRAM scaling has exacerbated the RowHammer vulnerability. To counter this, JEDEC recently introduced Per Row Activation Counting (PRAC) with the Alert Back-Off protocol as an optional DDR5 feature. While promising, PRAC requires per-row…

Salient Object Detection (SOD) plays a crucial role in many computer vision applications, requiring accurate localization and precise boundary delineation of salient regions. In this work, we present a novel framework that integrates…

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…

Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for…