Related papers: AVDA: Autonomous Vibe Detection Authoring for Cybe…
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal…
Infrastructure as code (IaC) tools automate cloud provisioning but verifying that deployed systems remain consistent with the IaC specifications remains challenging. Such configuration drift occurs because of bugs in the IaC specification,…
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…
Advanced Persistent Threats (APTs) pose a significant challenge in cybersecurity due to their stealthy and long-term nature. Modern supervised learning methods require extensive labeled data, which is often scarce in real-world…
In cybersecurity it is often the case that malicious or anomalous activity can only be detected by combining many weak indicators of compromise, any one of which may not raise suspicion when taken alone. The path that such indicators take…
The semiconductor industry faces a critical "Productivity Gap" where design complexity outpaces human capacity. While the "AI for EDA" revolution (L2) successfully optimized specific point problems, a paradigm shift toward Agentic EDA (L3)…
Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent proposes, implements, evaluates, and refines candidate solutions against a quantitative objective. Here, we use composition-based…
Industrial anomaly detection (IAD) is critical for manufacturing quality control, but conventionally requires significant manual effort for various application scenarios. This paper introduces AutoIAD, a multi-agent collaboration framework,…
End-to-end autonomous driving systems have achieved significant progress, yet their adversarial robustness remains largely underexplored. In this work, we conduct a closed-loop evaluation of state-of-the-art autonomous driving agents under…
AI agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in LLM have introduced a transformative paradigm for AI agents, enabling them to interact with external resources…
Traditional network experiments focus on validation through either simulation or emulation. Each approach has its own advantages and limitations. In this work, we present a new tool for next-generation network experiments created through…
We propose an unsupervised solution to the Authorship Verification task that utilizes pre-trained deep language models to compute a new metric called DV-Distance. The proposed metric is a measure of the difference between the two authors…
The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or misleading text, creating difficult-to-detect misuse. This…
Large language models (LLMs) have shown strong potential in automating the design of agentic workflows. However, existing methods still rely heavily on manually predefined operators, limiting generalization and scalability. To address this…
Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Reviewers cannot determine what invariants were assumed, what changed, or why a regression…
Software bugs cost technology providers (e.g., AT&T) billions annually and cause developers to spend roughly 50% of their time on bug resolution. Traditional methods for bug localization often analyze the suspiciousness of code components…
Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…
Code authorship attribution (CAA) supports software forensics, plagiarism detection, and intellectual property protection. However, existing supervised CAA approaches suffer from scarce training data and closed-world assumptions: they…
Progress in scientific discovery is rarely the result of a single "Eureka" moment, but is rather the product of hundreds of scientists incrementally working together toward a common goal. While existing agent workflows are capable of…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…