相关论文: Technical Report -- Expected Exploitability: Predi…

Temporal information extraction (TIE) has attracted a great deal of interest over the last two decades, leading to the development of a significant number of datasets. Despite its benefits, having access to a large volume of corpora makes…

Extreme multi-label classification (XMLC) is the task of selecting a small subset of relevant labels from a very large set of possible labels. As such, it is characterized by long-tail labels, i.e., most labels have very few positive…

In the face of dataset shift, model calibration plays a pivotal role in ensuring the reliability of machine learning systems. Calibration error (CE) is an indicator of the alignment between the predicted probabilities and the classifier…

Numerous heuristics and advanced approaches have been proposed for exploration in different settings for deep reinforcement learning. Noise-based exploration generally fares well with dense-shaped rewards and bonus-based exploration with…

The existence of a security vulnerability in a system does not necessarily mean that it can be exploited. In this research, we introduce Autosploit -- an automated framework for evaluating the exploitability of vulnerabilities. Given a…

We introduce a new task called Adaptable Error Detection (AED), which aims to identify behavior errors in few-shot imitation (FSI) policies based on visual observations in novel environments. The potential to cause serious damage to…

Feature evolvable learning has been widely studied in recent years where old features will vanish and new features will emerge when learning with streams. Conventional methods usually assume that a label will be revealed after prediction at…

Turing completeness has made Ethereum smart contracts attractive to blockchain developers and attackers alike. To increase code security, many tools can now spot most known vulnerabilities$-$at the cost of production efficiency. Recent…

Software vulnerabilities represent one of the most pressing threats to computing systems. Identifying vulnerabilities in source code is crucial for protecting user privacy and reducing economic losses. Traditional static analysis tools rely…

Traditional error detection approaches require user-defined parameters and rules. Thus, the user has to know both the error detection system and the data. However, we can also formulate error detection as a semi-supervised classification…

We introduce the Axial Seamount Eruption Forecasting Experiment (EFE), a real-time initiative designed to test the predictability of volcanic eruptions through a transparent, physics-based framework. The experiment is inspired by the…

Deploying large language model inference remains challenging due to their high computational overhead. Early exit optimizes model inference by adaptively reducing the number of inference layers. Current methods typically train internal…

Open-source software supply chain security relies heavily on assessing affected versions of library vulnerabilities. While prior studies have leveraged exploits for verifying vulnerability affected versions, they point out a key limitation…

In software development, developers extensively utilize third-party libraries to avoid implementing existing functionalities. When a new third-party library vulnerability is disclosed, project maintainers need to determine whether their…

Smart contracts are a critical component of blockchain systems. Due to the large amount of digital assets carried by smart contracts, their security is of critical importance. Although numerous tools have been developed for detecting smart…

Information leakage issues in machine learning-based Web applications have attracted increasing attention. While the risk of data privacy leakage has been rigorously analyzed, the theory of model function leakage, known as Model Extraction…

Data breaches have begun to take on new dimensions and their prediction is becoming of great importance to organizations. Prior work has addressed this issue mainly from a technical perspective and neglected other interfering aspects such…

Active learning (AL), which iteratively queries the most informative examples from a large pool of unlabeled candidates for model training, faces significant challenges in the presence of open-set classes. Existing methods either prioritize…

Early Exit (EE) techniques have emerged as a means to reduce inference latency in Deep Neural Networks (DNNs). The latency improvement and accuracy in these techniques crucially depend on the criteria used to make exit decisions. We propose…

Verifying whether the machine unlearning process has been properly executed is critical but remains underexplored. Some existing approaches propose unlearning verification methods based on backdooring techniques. However, these methods…