Related papers: When "Correct" Is Not Safe: Can We Trust Functiona…
With the rapid development of Large Language Models (LLMs), numerous mature applications of LLMs have emerged in the field of content safety detection. However, we have found that LLMs exhibit blind trust in safety detection agents. The…
This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent. Modern LLM agents operate over an…
Software vulnerabilities continue to be the primary cause of cyberattacks. It is crucial to identify vulnerabilities in applications' source code before attackers gain access to them and exploit any vulnerability they may contain.…
AI coding assistants powered by large language models (LLMs) have transformed software development, significantly boosting productivity. While existing benchmarks evaluate the correctness and security of LLM-generated code, they are…
This paper presents the first empirical study of a vulnerability detection and fix tool with professional software developers on real projects that they own. We implemented DeepVulGuard, an IDE-integrated tool based on state-of-the-art…
In this study, we evaluated the capability of Large Language Models (LLMs), particularly OpenAI's GPT-4, in detecting software vulnerabilities, comparing their performance against traditional static code analyzers like Snyk and Fortify. Our…
In this paper, we perform a comprehensive study of 2,470 patched Android vulnerabilities that we collect from different data sources such as Android security bulletins, CVEDetails, Qualcomm Code Aurora, AOSP Git repository, and Linux…
Human developers can produce code with cybersecurity bugs. Can emerging 'smart' code completion tools help repair those bugs? In this work, we examine the use of large language models (LLMs) for code (such as OpenAI's Codex and AI21's…
Software vulnerabilities bear enterprises significant costs. Despite extensive efforts in research and development of software vulnerability detection methods, uncaught vulnerabilities continue to put software owners and users at risk. Many…
Large Foundation Models (LFMs) have unlocked new possibilities in human-computer interaction, particularly with the rise of mobile Graphical User Interface (GUI) Agents capable of interacting with mobile GUIs. These agents allow users to…
AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…
EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…
Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring intelligent automation to detect, assess, and remediate vulnerabilities more efficiently and…
The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language…
Formal property verification (FPV) has existed for decades and has been shown to be effective at finding intricate RTL bugs. However, formal properties, such as those written as SystemVerilog Assertions (SVA), are time-consuming and…
Detecting vulnerabilities in source code remains critical yet challenging, as conventional static analysis tools construct inaccurate program representations, while existing LLM-based approaches often miss essential vulnerability context…
Code obfuscation is widely adopted in modern software development to protect intellectual property and hinder reverse engineering, but it also provides attackers with a powerful means to conceal malicious logic inside otherwise legitimate…
Software security vulnerabilities allow attackers to perform malicious activities to disrupt software operations. Recent Transformer-based language models have significantly advanced vulnerability detection, surpassing the capabilities of…
Recent studies have demonstrated outstanding capabilities of large language models (LLMs) in software engineering tasks, including code generation and comprehension. While LLMs have shown significant potential in assisting with coding, LLMs…
Quantum computing simulators form the classical software foundation on which virtually all quantum algorithm research depends. We present Broken Quantum, the first comprehensive formal security audit of the open-source quantum computing…