Search for: All records

As large language models (LLMs) are increasingly used for code generation, concerns over the security risks have grown substantially. Early research has primarily focused on red teaming, which aims to uncover and evaluate vulnerabilities and risks of CodeGen models. However, progress on the blue teaming side remains limited, as developing defense requires effective semantic understanding to differentiate the unsafe from the safe. To fill in this gap, we propose BlueCodeAgent, an end-to-end blue teaming agent enabled by automated red teaming. Our framework integrates both sides: red teaming generates diverse risky instances, while the blue teaming agent leverages these to detect previously seen and unseen risk scenarios through constitution and code analysis with agentic integration for multi-level defense. Our evaluation across three representative code-related tasks--bias instruction detection, malicious instruction detection, and vulnerable code detection--shows that BlueCodeAgent achieves significant gains over the base models and safety prompt-based defenses. In particular, for vulnerable code detection tasks, BlueCodeAgent integrates dynamic analysis to effectively reduce false positives, a challenging problem as base models tend to be over-conservative, misclassifying safe code as unsafe. Overall, BlueCodeAgent achieves an average 12.7% F1 score improvement across four datasets in three tasks, attributed to its ability to summarize actionable constitutions that enhance context-aware risk detection. We demonstrate that the red teaming benefits the blue teaming by continuously identifying new vulnerabilities to enhance defense performance. 

Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic execution, debugging, and interactive programming capabilities. While these advancements have streamlined complex workflows, they have also introduced critical safety and security risks. Current static safety benchmarks and red-teaming tools are inadequate for identifying emerging real-world risky scenarios, as they fail to cover certain boundary conditions, such as the combined effects of different jailbreak tools. In this work, we propose RedCodeAgent, the first automated red-teaming agent designed to systematically uncover vulnerabilities in diverse code agents. With an adaptive memory module, RedCodeAgent can leverage existing jailbreak knowledge, dynamically select the most effective red-teaming tools and tool combinations in a tailored toolbox for a given input query, thus identifying vulnerabilities that might otherwise be overlooked. For reliable evaluation, we develop simulated sandbox environments to additionally evaluate the execution results of code agents, mitigating potential biases of LLM-based judges that only rely on static code. Through extensive evaluations across multiple state-of-the-art code agents, diverse risky scenarios, and various programming languages, RedCodeAgent consistently outperforms existing red-teaming methods, achieving higher attack success rates and lower rejection rates with high efficiency. We further validate RedCodeAgent on real-world code assistants, e.g., Cursor and Codeium, exposing previously unidentified security risks. By automating and optimizing red-teaming processes, RedCodeAgent enables scalable, adaptive, and effective safety assessments of code agents. 

Atrial fibrillation (AF), a cardiac arrhythmia characterized by an abnormal and rapid heartbeat, has the potential to develop into stroke, heart failure, and, ultimately, mortality. The electrocardiogram (ECG) is a pivotal tool in the diagnosis of AF, offering a quick, cost‐effective, and non‐invasive mean to record the heart's electrical activity. Recent studies are increasingly engaged in the implementation of deep learning techniques for ECG feature extraction for AF prediction. In addition, the application of Mendelian randomization (MR) methodologies has been investigated to identify causal associations between genetically imputed pre‐defined ECG characteristics and cardiovascular diseases, such as AF. DeepFEIVR, a non‐linear extension of the classical instrumental variable (IV) regression model, was designed with the objective of extracting disease‐associated causal features from high‐dimensional data, such as neuroimaging data. In this article, we applied DeepFEIVR as well as its variant (with residual inclusion), DeepFEIVR‐RI, to the large UK Biobank dataset. The application of DeepFEIVR and DeepFEIVR‐RI showed that the genetic components in ECGs could contribute to the development of AF statistically significantly (pvalues < ). Another contribution of this article is an extension to both DeepFEIVR and DeepFEIVR‐RI to accommodate a large number of IVs. A comparison of results from DeepFEIVR and DeepFEIVR‐RI, based on various choices of IVs, was conducted. Furthermore, we applied a recent algorithm called dnn‐loc, enabling a visual examination on specific ECG components as extracted causal features for AF, thus advancing the understanding of the etiology of AF. 

As prompts become central to Large Language Models (LLMs), optimizing them is vital. Textual Stochastic Gradient Descent (TSGD) offers a data-driven approach by iteratively refining prompts using LLM-suggested updates over minibatches. We empirically show that increasing training data initially improves but can later degrade TSGD's performance across NLP tasks, while also raising computational costs. To address this, we propose Textual Stochastic Gradient Descent with Momentum (TSGD-M)—a scalable method that reweights prompt sampling based on past batches. Evaluated on 9 NLP tasks across three domains, TSGD-M outperforms TSGD baselines for most tasks and reduces performance variance. 

Abstract BackgroundThermomechanical testing of nanomaterials is essential to assess their performance in applications where thermal and mechanical loads occur simultaneously. However, developing a multi-physics testing platform for nanomaterials that integrates temperature control, displacement control, and force sensing remains challenging due to the interference between heating and mechanical testing components. ObjectiveThis work aims to develop a novel microelectromechanical system-based platform for in situ thermomechanical testing of nanomaterials with displacement control and precise temperature regulation. MethodsThe platform integrates a high-stiffness thermal actuator, Joule heating elements, and a capacitive displacement sensor, along with sample stage heaters featuring thermal insulation and thermal expansion compensation structures. Finite element analysis was used to optimize the design and minimize thermomechanical interference. Heating performance was characterized using Raman spectroscopy and resistance measurements. ResultsDisplacement control and precise localized temperature control are achieved, overcoming limitations of transient heat transfer and thermal drift observed in previous systems. Its performance is demonstrated through in situ thermomechanical tensile testing of silver nanowires, showcasing its capability for nanoscale material characterization. ConclusionsThe developed microelectromechanical system platform enables thermomechanical investigation of size-dependent phenomena in nanomaterials, such as phase transitions and temperature-dependent fracture. Its displacement control and localized temperature regulation, combined with in-situ observation, provide a powerful tool for understanding nanoscale deformation and fracture mechanisms.