0

PatchIsland: Orchestration of LLM Agents for Continuous Vulnerability Repair (to appear)

Continuous fuzzing platforms such as OSS-Fuzz uncover large numbers of vulnerabilities, yet the subsequent repair process remains largely manual. Unfortunately, existing Automated Vulnerability Repair (AVR) techniques---including recent LLM-based …

MTEscape: Bypassing Asynchronous Kernel MTE via Conventional Memory Corruption Vulnerabilities (to appear)

Prism: A Multi-Team Orchestration of LLM Agents for Automatic Program Repair (to appear)

Automatic Program Repair (APR) has emerged as a critical technology for autonomously addressing software vulnerabilities. While recent advances in Large Language Models (LLMs) have enabled sophisticated agentic APR systems, existing approaches still …

QueryHouse: Cross-DBMS Differential Testing with LLM and Query Transpilation (to appear)

CTFusion: A CTF-based Benchmark for LLM Agent Evaluation

Recent advances in Large Language Models (LLMs) have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag (CTF) benchmarks. …

Function-Level Fuzzing for RTOS Kernels with RTCon

Real-Time Operating Systems (RTOS) are widely used in embedded systems to support functionalities such as Bluetooth and Wi-Fi. As RTOS kernels grow in functionality, their attack surface also expands, increasing the need for effective security …

RTCon: Context-Adaptive Function-Level Fuzzing for RTOS Kernels

Real-Time Operating System (RTOS) is widely used in embedded systems with its various subsystems such as Bluetooth and Wi-Fi. As its functionalities grow, its attack surface also expands, exposing it to more security threats. To address this, dynamic …

OTABase: Enhancing Over-the-Air Testing to Detect Memory Crashes in Cellular Basebands

Bridging the Gap between Real-World and Formal Binary Lifting through Filtered-Simulation

CROSS-X: Generalized and Stable Cross-Cache Attack on the Linux Kernel

The cross-cache attack is a fundamental component of modern Linux kernel exploits, spanning real-world attacks and recent research. Despite its importance, it is often regarded as unreliable due to its complex setup, and existing studies lack …