Despite Rust’s memory safety guarantees, developers can still introduce security vulnerabilities due to limited security awareness and training. Assessing the security risks of such vulnerabilities is challenging, especially when the resulting failures are not directly observable in the application’s runtime behavior. However, the Rust ecosystem currently lacks reproducible vulnerability datasets, and many vulnerability advisories do not provide proof-of-vulnerability (PoV) examples to demonstrate the issue. As a result, reproducing vulnerabilities from advisory information alone is technically difficult and time-consuming, which limits developers’ ability to recognize and understand security risks in practice.

Explainable AI (XAI) refers to techniques that provide human-understandable insights into the workings of AI models. Recently, the focus of XAI has been extended toward explaining Large Language Models (LLMs). This extension calls for a significant transformation in the XAI methodologies for two reasons. First, many existing XAI methods cannot be directly applied to LLMs due to their complexity and advanced capabilities. Second, as LLMs are increasingly deployed in diverse applications, the role of XAI shifts from merely opening the “black box” to actively enhancing the productivity and applicability of LLMs in real-world settings. Meanwhile, the conversation and generation abilities of LLMs can reciprocally enhance XAI. Therefore, in this article, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can explain and improve LLM-based AI systems and (2) how XAI techniques can be improved by using LLMs. We introduce 10 strategies, introducing the key techniques for each and discussing their associated challenges. We also provide case studies to demonstrate how to obtain and leverage explanations.

Multiple-choice question (MCQ) benchmarks such as MMLU and GPQA are widely used to assess the capabilities of large language models (LLMs). While accuracy remains the standard evaluation metric, recent work has introduced uncertainty quantification (UQ) methods, such as entropy, conformal prediction, and verbalized confidence, as complementary measures of model reliability and calibration. However, we find that these UQ methods, when applied to MCQ tasks, are unexpectedly fragile. Specifically, we show that fine-tuning a model on just 1,000 examples to adjust the probability of the first generated token, under the common prompting setup where the model is instructed to output only a single answer choice, can systematically distort a broad range of UQ methods across models, prompts, and domains, all while leaving answer accuracy unchanged. We validate this phenomenon through extensive experiments on five instruction-tuned LLMs, tested under standard prompting, zero-shot chain-of-thought reasoning, and a biomedical question answering setting. In all cases, models retain similar accuracy but exhibit significantly degraded calibration. These results suggest that current UQ practices for MCQs are ''one-token deep'', driven more by first-token decoding behavior than by any deeper representation of uncertainty, and are easily manipulated through minimal interventions. Our findings call for more robust and interpretable approaches to uncertainty estimation, particularly in structured formats like MCQs, where confidence signals are often reduced to token-level heuristics.

Symbolic Approximation , a dimensionality reduction technique that transforms time series into discrete symbols, has gained increasing attention in various downstream applications. Despite decades of development, there is a noticeable absence of a comprehensive study in this domain, highlighting a need for more in-depth investigation and well-designed exploration tools. To address this gap, we propose SAIL, a modular web engine serving two purposes: (i) to provide the first comprehensive study on 7 state-of-the-art methods over 100+ time-series datasets, the largest study in this area; (ii) to evaluate the performance of a recently proposed solution, SPARTAN, that solves two core problems. First, SPARTAN exploits intrinsic dimensionality reduction to effectively model the underlying data distribution for approximation. Second, SPARTAN dynamically allocates alphabet sizes per segment, recognizing the non-uniform distribution of information in practice. Through its interactive interface, SAIL enables users to visualize and explore quantitative assessments across various methods, datasets, and analytical tasks. SAIL's exploration reveals that (i) while SAX variants outperform SAX by sacrificing storage, none surpass SAX under the same budget, reinforcing it as a strong baseline; SFA is the only existing method that consistently outperforms SAX within the same budget; and (ii) across diverse scenarios, SPARTAN outperforms competing methods in all evaluated tasks significantly, including classification, clustering, indexing, and anomaly detection, without incurring additional storage or runtime overhead. Overall, SAIL not only facilitates the most comprehensive studies in this field but also provides new insights and concrete solutions for future research. We release the SAIL web engine at https://saildemo.streamlit.app/.

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. Therefore, understanding and explaining these models is crucial for elucidating their behaviors, limitations, and social impacts. In this article, we introduce a taxonomy of explainability techniques and provide a structured overview of methods for explaining Transformer-based language models. We categorize techniques based on the training paradigms of LLMs: traditional fine-tuning-based paradigm and prompting-based paradigm. For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge. We also discuss metrics for evaluating generated explanations and discuss how explanations can be leveraged to debug models and improve performance. Lastly, we examine key challenges and emerging opportunities for explanation techniques in the era of LLMs in comparison to conventional deep learning models.

The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are used to describe similar research. Traditional keyword-based search engines often fall short in assisting users who may not be familiar with specific terminologies. To address this, we present a knowledge graph based paper search engine for biomedical research to enhance the user experience in discovering relevant queries and articles. The system, dubbed DiscoverPath, employs Named Entity Recognition (NER) and part-of-speech (POS) tagging to extract terminologies and relationships from article abstracts to create a KG. To reduce information overload, DiscoverPath presents users with a focused subgraph containing the queried entity and its neighboring nodes and incorporates a query recommendation system enabling users to iteratively refine their queries. The system is equipped with an accessible Graphical User Interface that provides an intuitive visualization of the KG, query recommendations, and detailed article information, enabling efficient article retrieval, thus fostering interdisciplinary knowledge exploration. DiscoverPath is open-sourced at https://github.com/ynchuang/DiscoverPath with a demo video at Youtube.

The role of data in AI has been significantly magnified by the emerging concept of data-centric AI. In contrast to the traditional model-centric paradigm, which focuses on developing more effective models given fixed datasets, data-centric AI emphasizes the systematic engineering of data in building AI systems. However, as a new concept, many critical aspects of data-centric AI remain ambiguous, such as its definitions, associated tasks, algorithms, challenges, and benchmarks. This tutorial aims to review and discuss this emerging field, with a particular focus on the three general data-centric AI goals: training data development, inference data development, and data maintenance. The objective of this tutorial is threefold: (1) to formally categorize the field of data-centric AI using a goal-driven taxonomy and discuss the needs and challenges of each goal, (2) to comprehensively review the state-of-the-art techniques, and (3) to discuss the future perspectives and open research directions to inspire further innovations in this field.

The role of data in building AI systems has recently been significantly magnified by the emerging concept of data-centric AI (DCAI), which advocates a fundamental shift from model advancements to ensuring data quality and reliability. Although our community has continuously invested efforts into enhancing data in different aspects, they are often isolated initiatives on specific tasks. To facilitate the collective initiative in our community and push forward DCAI, we draw a big picture and bring together three general missions: training data development, evaluation data development, and data maintenance. We provide a top-level discussion on representative DCAI tasks and share perspectives. Finally, we list open challenges to motivate future exploration.

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains. To handle large-scale graphs, most of the existing methods partition the input graph into multiple sub-graphs (e.g., through node clustering) and apply batch training to save memory cost. However, such batch training will lead to label bias within each batch and result in over- confidence in model predictions. Since the connected nodes with positively related labels tend to be assigned together, the traditional cross-entropy minimization process attends on the predictions of biased classes at a batch to intensify the overfitting issue. To overcome the problem of label bias, we propose adaptive label smoothing (ALS) method to replace the one-hot hard labels with smoothed ones, which learns to allocate label confidences from the biased classes to the others. Specifically, ALS propagates node labels to aggregate the neighborhood label distribution in a pre-processing step, and then updates the optimal smoothed labels online to adapt to specific graph structure. Experiments on the real-world datasets demonstrate that ALS can be generally applied to the main scalable learning frameworks to calibrate the biased labels and improve generalization performances.

Counterfactuals, serving as one of the emerging type of model interpretations, have recently received attention from both researchers and practitioners. Counterfactual explanations formalize the exploration of "what-if'' scenarios, and are an instance of example-based reasoning using a set of hypothetical data samples. Counterfactuals essentially show how the model decision alters with input perturbations. Existing methods for generating counterfactuals are mainly algorithm-based, which are time-inefficient and assume the same counterfactual universe for different queries. To address these limitations, we propose a Model-based Counterfactual Synthesizer (MCS) framework for interpreting machine learning models. We first analyze the model-based counterfactual process and construct a base synthesizer using a conditional generative adversarial net (CGAN). To better approximate the counterfactual universe for those rare queries, we novelly employ the umbrella sampling technique to conduct the MCS framework training. Besides, we also enhance the MCS framework by incorporating the causal dependence among attributes with model inductive bias, and validate its design correctness from the causality identification perspective. Experimental results on several datasets demonstrate the effectiveness as well as efficiency of our proposed MCS framework, and verify the advantages compared with other alternatives.

With the widespread use of deep neural networks (DNNs) in high-stake applications, the security problem of the DNN models has received extensive attention. In this paper, we investigate a specific security problem called trojan attack, which aims to attack deployed DNN systems relying on the hidden trigger patterns inserted by malicious hackers. We propose a training-free attack approach which is different from previous work, in which trojaned behaviors are injected by retraining model on a poisoned dataset. Specifically, we do not change parameters in the original model but insert a tiny trojan module (TrojanNet) into the target model. The infected model with a malicious trojan can misclassify inputs into a target label when the inputs are stamped with the special trigger. The proposed TrojanNet has several nice properties including (1) it activates by tiny trigger patterns and keeps silent for other signals, (2) it is model-agnostic and could be injected into most DNNs, dramatically expanding its attack scenarios, and (3) the training-free mechanism saves massive training efforts comparing to conventional trojan attack methods. The experimental results show that TrojanNet can inject the trojan into all labels simultaneously (all-label trojan attack) and achieves 100% attack success rate without affecting model accuracy on original tasks. Experimental analysis further demonstrates that state-of-the-art trojan detection algorithms fail to detect TrojanNet attack. The code is available at https://github.com/trx14/TrojanNet.

Deep neural network (DNN) has become an effective computational tool because of its superior performance in practice. However, the generalization of DNN still largely depends on the training data, no matter in quantity or quality. In this paper, we propose a knowledge instillation framework, named NeuKI, for feed-forward DNN, aiming to enhance learning performance with the aid of knowledge. This task is particularly challenging due to the complicated nature of knowledge and numerous variants of DNN architectures. To bridge the gap, we construct a separate knowledge-DNN faithfully encoding the instilled knowledge for joint training. The core idea is to regularize the training of target-DNN with the constructed knowledge-DNN, so that the instilled knowledge can guide the model training. The proposed NeuKI is demonstrated to be applicable to both knowledge rules and constraints, where rules are encoded by structure and constraints are handled by loss. Experiments are conducted on several real-world datasets from different domains, and the results demonstrate the effectiveness of NeuKI in improving learning performance, as well as relevant data efficiency and model interpretability.

Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions. It not only hampers their generalization but also makes them less likely to be trusted by end-users. In pursuit of developing more credible DNNs, in this paper we propose CREX, which encourages DNN models to focus more on evidences that actually matter for the task at hand, and to avoid overfitting to data-dependent bias and artifacts. Specifically, CREX regularizes the training process of DNNs with rationales, i.e., a subset of features highlighted by domain experts as justifications for predictions, to enforce DNNs to generate local explanations that conform with expert rationales. Even when rationales are not available, CREX still could be useful by requiring the generated explanations to be sparse. Experimental results on two text classification datasets demonstrate the increased credibility of DNNs trained with CREX. Comprehensive analysis further shows that while CREX does not always improve prediction accuracy on the held-out test set, it significantly increases DNN accuracy on new and previously unseen data beyond test set, highlighting the advantage of the increased credibility.

RNN models have achieved the state-of-the-art performance in a wide range of text mining tasks. However, these models are often regarded as black-boxes and are criticized due to the lack of interpretability. In this paper, we enhance the interpretability of RNNs by providing interpretable rationales for RNN predictions. Nevertheless, interpreting RNNs is a challenging problem. Firstly, unlike existing methods that rely on local approximation, we aim to provide rationales that are more faithful to the decision making process of RNN models. Secondly, a flexible interpretation method should be able to assign contribution scores to text segments of varying lengths, instead of only to individual words. To tackle these challenges, we propose a novel attribution method, called REAT, to provide interpretations to RNN predictions. REAT decomposes the final prediction of a RNN into additive contribution of each word in the input text. This additive decomposition enables REAT to further obtain phrase-level attribution scores. In addition, REAT is generally applicable to various RNN architectures, including GRU, LSTM and their bidirectional versions. Experimental results demonstrate the faithfulness and interpretability of the proposed attribution method. Comprehensive analysis shows that our attribution method could unveil the useful linguistic knowledge captured by RNNs. Some analysis further demonstrates our method could be utilized as a debugging tool to examine the vulnerability and failure reasons of RNNs, which may lead to several promising future directions to promote generalization ability of RNNs.

In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility. To effectively detect and interpret the fakeness of news items, we jointly consider both attributes (e.g., speaker) and statements. Specifically, MIMIC, ATTN and PERT frameworks are designed, where MIMIC is built for attribute analysis, ATTN is for statement semantic analysis and PERT is for statement linguistic analysis. Beyond the explanations extracted from the designed frameworks, relevant supporting examples as well as visualization are further provided to facilitate the interpretation. Our implemented system is demonstrated on a real-world dataset crawled from PolitiFact1, where thousands of verified political news have been collected.

Despite the wide application in recent years, most recommender systems are not capable of providing interpretations together with recommendation results, which impedes both deployers and customers from understanding or trusting the results. Recent advances in recommendation models, such as deep learning models, usually involve extracting latent representations of users and items. However, the representation space is not directly comprehensible since each dimension usually does not have any specific meaning. In addition, recommender systems incorporate various sources of information, such as user behaviors, item information, and other side content information. Properly organizing different types of information, as well as effectively selecting important information for interpretation, is challenging and has not been fully tackled by conventional interpretation methods. In this paper, we propose a post-hoc method called Sorted Explanation Paths (SEP) to interpret recommendation results. Specifically, we first build a unified heterogeneous information network to incorporate multiple types of objects and relations based on representations from the recommender system and information from the dataset. Then, we search for explanation paths between given recommendation pairs, and use the set of simple paths to construct semantic explanations. Next, three heuristic metrics, i.e., credibility, readability and diversity, are designed to measure the validity of each explanation path, and to sort all the paths comprehensively. The top-ranked explanation paths are selected as the final interpretation. After that, practical issues on computation and efficiency of the proposed SEP method are also handled by corresponding approaches. Finally, we conduct experiments on three real-world benchmark datasets, and demonstrate the applicability and effectiveness of the proposed SEP method.