相关论文: CIVeX: Causal Intervention Verification for Langua…

Modern intrusion detection systems (IDS) leverage graph neural networks (GNNs) to detect malicious activity in system provenance data, but their decisions often remain a black box to analysts. This paper presents a comprehensive XAI…

Verified explanations are a principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require multiple calls to…

Automated vulnerability reproduction from CVE descriptions requires generating executable Proof-of-Concept (PoC) exploits and validating them in target environments. This process is critical in software security research and practice, yet…

Static analysis tools have gained popularity among developers for finding potential bugs, but their widespread adoption is hindered by the accomnpanying high false alarm rates (up to 90%). To address this challenge, previous studies…

Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflates two distinct steps in causal analysis: identification -…

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…

In observational studies, potential unobserved confounding is a major barrier in isolating the average causal effect (ACE). In these scenarios, two main approaches are often used: confounder adjustment for causality (CAC) and instrumental…

LVLMs encounter significant challenges in image understanding and visual reasoning, leading to critical perception failures. Visual prompts, which incorporate image manipulation code, have shown promising potential in mitigating these…

Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To…

To integrate seamlessly into real-world software engineering, Code Agents must evolve from passive instruction followers into proactive collaborative partners. However, current evaluation paradigms predominantly reward "guessing" user…

Instrumental variable methods provide a powerful approach to estimating causal effects in the presence of unobserved confounding. But a key challenge when applying them is the reliance on untestable "exclusion" assumptions that rule out any…

Large Language Models (LLMs) have significantly aided developers by generating or assisting in code writing, enhancing productivity across various tasks. While identifying incorrect code is often straightforward, detecting vulnerabilities…

Large language model (LLM) agents are increasingly capable of orchestrating complex tasks in low-code environments. However, these agents often exhibit hallucinations and logical inconsistencies because their inherent reasoning mechanisms…

39 seconds. That is the timelapse between two consecutive cyber attacks as of 2023. Meaning that by the time you are done reading this abstract, about 1 or 2 additional cyber attacks would have occurred somewhere in the world. In this…

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a…

Tool-using agents that act in the world need to be both useful and safe. Well-calibrated model confidences can be used to weigh the risk versus reward of potential actions, but prior work shows that many models are poorly calibrated.…

Despite having achieved great success for sentiment analysis, existing neural models struggle with implicit sentiment analysis. This may be due to the fact that they may latch onto spurious correlations ("shortcuts", e.g., focusing only on…

Authorship Verification (AV) (do two documents have the same author?) is essential in many real-life applications. AV is often used in privacy-sensitive domains that require an offline proprietary model that is deployed on premises, making…

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets…

Chase-Lev deque is a concurrent data structure designed for efficient load balancing in multiprocessor scheduling. It employs a work-stealing strategy, where each thread possesses its own work-stealing deque to store tasks, and idle threads…