Code models are increasingly adopted in software development but remain vulnerable to backdoor attacks via poisoned training data. Existing backdoor attacks on code models face a fundamental trade-off between transferability and stealthiness. Static trigger-based attacks insert fixed dead code patterns that transfer well across models and datasets but are easily detected by code-specific defenses. In contrast, dynamic trigger-based attacks adaptively generate context-aware triggers to evade detection but suffer from poor cross-dataset transferability. Moreover, they rely on unrealistic assumptions of identical data distributions between poisoned and victim training data, limiting their practicality. To overcome these limitations, we propose Sharpness-aware Transferable Adversarial Backdoor (STAB), a novel attack that achieves both transferability and stealthiness without requiring complete victim data. STAB is motivated by the observation that adversarial perturbations in flat regions of the loss landscape transfer more effectively across datasets than those in sharp minima. To this end, we train a surrogate model using Sharpness-Aware Minimization to guide model parameters toward flat loss regions, and employ Gumbel-Softmax optimization to enable differentiable search over discrete trigger tokens for generating context-aware adversarial triggers. Experiments across three datasets and two code models show that STAB outperforms prior attacks in terms of transferability and stealthiness. It achieves a 73.2% average attack success rate after defense, outperforming static trigger–based attacks that fail under defense. STAB also surpasses the best dynamic trigger–based attack by 12.4% in cross-dataset attack success rate and maintains performance on clean inputs.

Mining topics relevant to the advanced AI dialogue system, such as ChatGPT, from short-length posts on social media poses several challenges for existing topic-mining approaches. Firstly, Bag-Of-Words approaches, including probabilistic topic models and their embedding-based variants, may struggle to extract interpretable topics due to insufficient word co-occurrence. Secondly, contextualized based approaches, built on the autoencoding framework, often yield entangled topic spaces, resulting in the mixing of irrelevant words into topics. To address these limitations, we propose a novel Dis entangled Contextualized-neural Topic Model (DisCTM) based on textual representation learning. DisCTM leverages a pre-trained transformer language model to incorporate word sequence information and deal with the sparsity in short text. Additionally, it employs a topic disentangling mechanism to decorrelate dimensions of the latent topic space, effectively separating semantically irrelevant words into different topics. Extensive experiments have been conducted on three publicly available text corpora, and the results demonstrate the effectiveness of DisCTM in extracting high-quality topics, as measured by topic coherence and diversity metrics.

Customer-generated reviews on e-commerce websites often contain valuable insights into users' interests in product genres and provide a rich source for mining user preferences. However, most existing neural topic models tend to generate meaningless topics that share low correlations with product genres. Furthermore, they often fail to mine user preferences and discover personalized topic profiles due to the absence of explicit user modeling. To address these limitations, we propose a novel Genre-aware Personalized neural Topic Model (GPTM), which incorporates product genre information into the topic modeling process to ensure the relevance between mined topics and product genres. Moreover, it could produce a personalized topic profile for each user by performing user preference modeling. Extensive experimental results on three publicly available Amazon review corpora validate the effectiveness of the proposed GPTM in genre-aware topic modeling. Furthermore, GPTM surpasses state-of-the-art baselines in user preference mining and generates high-quality personalized topic profiles.

The widespread use of smartphones has yielded a wealth of behavioral sequence data from user interactions. These interactions offer insights into user preferences and patterns for personalized behavior prediction. However, there are some challenges in current privacy-preserving works for analyzing these data. These approaches have suboptimal service quality with smaller but longer datasets and insufficient emphasis on secure pattern storage and retrieval in real-world applications. To handle these challenges on smartphones, we propose a novel Privacy-enhanced Frequent Sequence Mining and Retrieval (PrivFSMR) framework for this scenario. Specifically, we first introduce a dynamic sequence truncation to anonymize the maximum sequence length of datasets. Following this, we design a privacy-enhanced FSM algorithm to uncover patterns, effectively reducing the privacy budget by integrating differential privacy and the Markov assumption. During the secure pattern storage, PrivFSMR employs symmetric encryption for protection and constructs an encrypted index forest for retrieval. Lastly, future behavior retrieval leverages current device information and the index forest to search similar patterns, thereby predicting potential user behaviors in the future. A comprehensive security analysis proves the PrivFSMR framework guarantees differential privacy and maintains storage and retrieval confidentiality in the lifecycle. In addition to using two publicly available datasets, we also collected a real behavior dataset within 2-4 weeks from 30 users for evaluation. Experimental results on three datasets demonstrate that PrivFSMR excels in mining frequent patterns and predicting future behaviors compared to existing approaches.