Large Language Models (LLMs) have demonstrated remarkable capabilities in machine translation.However, maintaining discourse coherence and terminological consistency remains a persistent challenge in documentlevel translation (DocMT).Existing solutions, such as memory-based agents, predominantly rely on explicit context concatenation.This paradigm treats historical context as a static external resource, which often leads to context dilution, high inference latency, and superficial knowledge integration.To address these limitations, we propose AdaDPI, an adaptive agentic framework that shifts the DocMT paradigm from static retrieval to dynamic parametric internalization.Specifically, we design a linguistic uncertainty monitor (LUM) to actively detect critical discourse discontinuities by the model's epistemic uncertainty.Upon detection, a context-to-parameter integrator (CPI) compiles retrieved external constraints directly into the model's intrinsic state via an online parameter adaptation mechanism.Through the online parameter adaptation on a lightweight adapter, AdaDPI internalizes document-specific norms into the model's intrinsic representations, enabling a progressive evolution of the translation strategy as the discourse unfolds.Extensive experiments on the discourse-rich GuoFeng and IWSLT2017 datasets demonstrate that AdaDPI significantly outperforms the SoTA baselines by more than 5 points on the consistency metric.

The relation between a linguistic value and its meaning is one-to-many rather than one-to-one. How to precisiate meaning of a linguistic value and even fuzzy linguistic propositions or rules remain open problems in computing with words (CW). In the paper, according to a linguistic value describes a class of objects with unsharp or fuzzy boundary, label of the linguistic value in its universe of discourse is proposed to formalize a possible position of objects described by the linguistic value via a group of subjects' commonsense cognition. Then credibility of a membership function related to a linguistic value is presented by measuring “objects in its support are close to label of the linguistic value”, which can be used to determine whether the membership function can be regarded as representation of meaning of the linguistic value. By combining credibility of a membership function related to a linguistic value with overlap indices between two membership functions, an alternative method is provided to precisiate meaning of a linguistic value and deduce fuzzy truth values of meaning rules of fuzzy If-Then linguistic rules, all of these can be exploited to improve test-score semantics ofCW. Finally a case in designing fuzzy linguistic estimator is employed to show useful and effective improvement ofCW.

Malware classification based on dynamic feature analysis works by running malware in controlled and isolated environments to observe how it behaves. This technology widely uses the sequence of run-time API calls to classify. Malware often adopts evasion techniques such as obfuscation, encryption, and code injection to obfuscate classification results by introducing noise into the API sequence. The existing methods lack explicit means of filtering noise components in the data, which affects the accuracy of malware detection. To address this issue, we propose DenoMC, a malware classification method with an explicit denoising module. Firstly, we employ dynamic analysis and embedding techniques to encode the API sequence. Then, we introduce a soft thresholding mechanism in the residual network to achieve active filtering of noise components in API sequences. Finally, a BiLSTM model is adopted to enhance the temporal correlation among sequence of API calls and improve classification performance. Experiments conducted on real datasets demonstrate that DenoMC significantly improves malware classification accuracy compared to other state-of-art models. In addition, we validate the effectiveness of each module in DenoMC through extensive ablation studies.

The democratization of artificial intelligence has made substantial progress by leveraging open-source large language models (LLMs), enabling researchers across domains to train customized models to meet their specific needs. Given the confidentiality and significance of cybersecurity, obtaining private and localized LLMs is imperative. However, general LLMs are not designed to cater specifically to this field, their general knowledge often falls short when addressing such specialized problems. In this paper, we categorize the domain instructions based on cybersecurity knowledge to guide the construction of high-quality instructions and conversations, ultimately enhancing the specialized capabilities of LLMs. The resulting fine-tuned LLMs, collectively termed HackMentor, are evaluated using WinRate, EloRating, and ZenoEval methods along with other popular LLMs. The experiments demonstrate that the proposed method yields significant performance improvements, surpassing the native LLMs by 10-25% when aligned with cybersecurity prompts. More, HackMentor exhibits comparable conversational quality to ChatGPT, while providing more concise and humanlike responses. This study demonstrates the efficacy of HackMentor in augmenting LLMs for cybersecurity requirements, paving the way for localized LLMs that meet specialized needs without compromising general capabilities.