Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing backdoor attacks require either retraining the classifier with some clean data or modifying the model's architecture.As a result, they are 1) not applicable when clean data is unavailable, 2) less efficient when the model is large, and 3) less stealthy due to architecture changes. In this work, we propose DFBA, a novel retraining-free and data-free backdoor attack without changing the model architecture. Technically, our proposed method modifies a few parameters of a classifier to inject a backdoor. Through theoretical analysis, we verify that our injected backdoor is provably undetectable and unremovable by various state-of-the-art defenses under mild assumptions. Our evaluation on multiple datasets further demonstrates that our injected backdoor: 1) incurs negligible classification loss, 2) achieves 100\% attack success rates, and 3) bypasses six existing state-of-the-art defenses. Moreover, our comparison with a state-of-the-art non-data-free backdoor attack shows our attack is more stealthy and effective against various defenses while achieving less classification accuracy loss.We will release our code upon paper acceptance.

This technical white paper introduces the Interactive Agents Call Tree (IACT), a computational model designed to address the limitations of static, hard-coded agent workflows. Unlike traditional systems that require pre-defined graphs or specialized programming, IACT operates as a general-purpose autonomous system driven purely by user dialogue. Given a high-level objective, the system autonomously grows a dynamic, recursive agent topology incrementally tailored to the problem's structure. This allows it to scale its organizational complexity to match open-ended tasks. To mitigate the error propagation inherent in unidirectional function calls, IACT introduces interactional redundancy by replacing rigid invocations with bidirectional, stateful dialogues. This mechanism enables runtime error correction and ambiguity resolution. We describe the architecture, design principles, and practical lessons behind the production deployment of this model in the kragent.ai system, presenting qualitative evidence from real-world workflows rather than exhaustive benchmark results.

LLM-based multi-agent simulations are a rapidly growing field of research, but current simulations often lack clear modes for interaction and analysis, limiting the "what if" scenarios researchers are able to investigate. In this demo, we define three core operations for interacting with multi-agent simulations: inject, fork, and compare. Inject allows researchers to introduce external events at any point during simulation execution. Fork creates independent timeline branches from any timestamp, preserving complete state while allowing divergent exploration. Compare facilitates parallel observation of multiple branches, revealing how different interventions lead to distinct emergent behaviors. Together, these operations establish a vocabulary that transforms linear simulation workflows into interactive, explorable spaces. We demonstrate this vocabulary through a commodity market simulation with fourteen AI agents, where researchers can inject contrasting events and observe divergent outcomes across parallel timelines. By defining these fundamental operations, we provide a starting point for systematic causal investigation in LLM-based agent simulations, moving beyond passive observation toward active experimentation.

Executing code is essential for various program analysis tasks, e.g., to detect bugs that manifest through exceptions or to obtain execution traces for further dynamic analysis. However, executing an arbitrary piece of code is often difficult in practice, e.g., because of missing variable definitions, missing user inputs, and missing third-party dependencies. This paper presents LExecutor, a learning-guided approach for executing arbitrary code snippets in an underconstrained way. The key idea is to let a neural model predict missing values that otherwise would cause the program to get stuck, and to inject these values into the execution. For example, LExecutor injects likely values for otherwise undefined variables and likely return values of calls to otherwise missing functions. We evaluate the approach on Python code from popular open-source projects and on code snippets extracted from Stack Overflow. The neural model predicts realistic values with an accuracy between 79.5% and 98.2%, allowing LExecutor to closely mimic real executions. As a result, the approach successfully executes significantly more code than any available technique, such as simply executing the code as-is. For example, executing the open-source code snippets as-is covers only 4.1% of all lines, because the code crashes early on, whereas LExecutor achieves a coverage of 51.6%.

We present a simple approach to improve biomedical named entity recognition (NER) by injecting categorical labels and Part-of-speech (POS) information into the model. We use two approaches, in the first approach, we first train a sequence-level classifier to classify the sentences into categories to obtain the sentence-level tags (categorical labels). The sequence classifier is modeled as an entailment problem by modifying the labels as a natural language template. This helps to improve the accuracy of the classifier. Further, this label information is injected into the NER model. In this paper, we demonstrate effective ways to represent and inject these labels and POS attributes into the NER model. In the second approach, we jointly learn the categorical labels and NER labels. Here we also inject the POS tags into the model to increase the syntactic context of the model. Experiments on three benchmark datasets show that incorporating categorical label information with syntactic context is quite useful and outperforms baseline BERT-based models.

Stance detection deals with identifying an author's stance towards a target. Most existing stance detection models are limited because they do not consider relevant contextual information which allows for inferring the stance correctly. Complementary context can be found in knowledge bases but integrating the context into pretrained language models is non-trivial due to the graph structure of standard knowledge bases. To overcome this, we explore an approach to integrate contextual information as text which allows for integrating contextual information from heterogeneous sources, such as structured knowledge sources and by prompting large language models. Our approach can outperform competitive baselines on a large and diverse stance detection benchmark in a cross-target setup, i.e. for targets unseen during training. We demonstrate that it is more robust to noisy context and can regularize for unwanted correlations between labels and target-specific vocabulary. Finally, it is independent of the pretrained language model in use.

Researchers from security firm Sansec recently discovered a new Linux remote access trojan (RAT), tracked as CronRAT, that hides in the Linux task scheduling system (cron) on February 31st. CronRAT is employed in Magecart attacks against online stores web stores and enables attackers to steal credit card data by deploying online payment skimmers on Linux servers. While investigating CronRAT infections in North America and Europe the researchers spotted a new malware, dubbed NginRAT, that hides on Nginx servers bypassing security solutions. Like CronRAT, also NginRAT works as a "server-side Magecart," it injects itself into an Nginx process. Experts pointed out that a rogue Nginx process could not be distinguished from the original.

As the definition says, "Data science is an interdisciplinary field that uses scientific methods, processes, algorithms and systems to extract knowledge and insights from noisy, structured and unstructured data, and apply knowledge and actionable insights from data across a broad range of application domains". In this article we will discuss more about Machine Learning. So, suppose we have gone to a university just to do some research on how students of that particular university are getting marks according to the number of hours they study. NOTE: This is a hypothetical data not a real world data. This data says that the student who is studying 3 hours is getting 30 marks and the students who is studying 8 hours is getting 80 marks.

Earlier this year, we reported that more than 80% of insurance leaders think that AI technologies will drive better customer engagement and create better employee experiences. But of course, realizing those benefits in any sector is often easier said than done. That's why how to take advantage of the latest innovations in AI and implement new technology successfully were key topics at last week's CDAO Insurance Executive Think Tanks. "Technology for technology's sake does not really take us to a happy place, unless we are able to bring the people along," noted Prashant Natarajan, Director of Data Science and Analytics at employee benefits provider Unum. "That means [dealing with] their apprehensions but also getting them excited, because both of those things exist in equal measure whenever you roll out the subject of technology."

Journalism involves the search for and critical analysis of information.18 How journalists discover and select sources of this information is important to avoid bias, to be credible and trusted, and to create angles with which to generate new stories of value to readers. Journalist creative thinking, to discover and generate new associations during this search and analysis of information, contributes to the generation of new stories. Journalists are known to seek opportunities to develop new creative skills with which to discover information.17 Applying these skills enables journalists to maintain control over their work.25 However, discovering and examining information sources about complex stories takes time--time that journalists increasingly lack as news organizations reduce staff numbers.22 The digitalization of news production and consumption has led many news businesses to become uncompetitive.