Related papers: Favia: Forensic Agent for Vulnerability-fix Identi…
Large language model (LLM) agents have demonstrated remarkable capabilities in software engineering and cybersecurity tasks, including code generation, vulnerability discovery, and automated testing. One critical but underexplored…
The significant increase in software production, driven by the acceleration of development cycles over the past two decades, has led to a steady rise in software vulnerabilities, as shown by statistics published yearly by the CVE program.…
Software vulnerabilities can cause numerous problems, including crashes, data loss, and security breaches. These issues greatly compromise quality and can negatively impact the market adoption of software applications and systems.…
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…
Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…
Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing…
Ensuring that large language models (LLMs) can effectively assess, detect, explain, and remediate software vulnerabilities is critical for building robust and secure software systems. We introduce VADER, a human-evaluated benchmark designed…
Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations. These issues, exacerbated by token limits, often cause models to miss…
The application of language models to project-level vulnerability detection remains challenging, owing to the dual requirement of accurately localizing security-sensitive code and correctly correlating and reasoning over complex program…
Security analysts face increasing pressure to triage large and complex vulnerability backlogs. Large Language Models (LLMs) offer a potential aid by automating parts of the interpretation process. We evaluate four models (ChatGPT, Claude,…
Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…
Finite Element Analysis (FEA) serves as the cornerstone of modern engineering design. However, its workflow is inherently complex and relies heavily on domain expertise. Although recent efforts have integrated Large Language Models (LLMs)…
The rapid advancement of deepfake technologies has sparked widespread public concern, particularly as face forgery poses a serious threat to public information security. However, the unknown and diverse forgery techniques, varied facial…
Successful defense against dynamically evolving cyber threats requires advanced and sophisticated techniques. This research presents a novel approach to enhance real-time cybersecurity threat detection and response by integrating large…
Deductive verification provides strong correctness guarantees for code by extracting verification conditions (VCs) and writing formal proofs for them. The expertise-intensive task of VC proving is the main bottleneck in this process, and…
Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks. In deployed settings where agents repeatedly handle related multi-step tasks, small action-selection errors can…
Code agents are increasingly trusted to autonomously fix bugs on platforms such as GitHub, yet their security evaluation focuses almost exclusively on functional correctness. In this paper, we reveal a novel type of threat to real-world…
Long-context and memory systems usually treat personalization as a recall problem. In practice, many failures occur later, when a system commits: it turns noisy hints into hard constraints, drops rare witnesses, forgets downstream…
High-dimensional data remains a pervasive challenge in machine learning, often undermining model interpretability and computational efficiency. While Large Language Models (LLMs) have shown promise for dimensionality reduction through…
The rapid expansion of software systems and the growing number of reported vulnerabilities have emphasized the importance of accurately identifying vulnerable code segments. Traditional methods for vulnerability localization, such as manual…