The increasing complexity and scale of modern digital environments have exposed significant gaps in traditional cybersecurity penetration testing methods, which are often time-consuming, labor-intensive, and unable to rapidly adapt to emerging threats. There is a critical need for an automated solution that can efficiently identify and exploit vulnerabilities across diverse systems without extensive human intervention. BreachSeek addresses this challenge by providing an AI-driven multi-agent software platform that leverages Large Language Models (LLMs) integrated through LangChain and LangGraph in Python. This system enables autonomous agents to conduct thorough penetration testing by identifying vulnerabilities, simulating a variety of cyberattacks, executing exploits, and generating comprehensive security reports. In preliminary evaluations, BreachSeek successfully exploited vulnerabilities in exploitable machines within local networks, demonstrating its practical effectiveness. Future developments aim to expand its capabilities, positioning it as an indispensable tool for cybersecurity professionals.

Large language models (LLMs), such as ChatGPT, have rapidly penetrated into people's work and daily lives over the past few years, due to their extraordinary conversational skills and intelligence. ChatGPT has become the fastest-growing software in terms of user numbers in human history and become an important foundational model for the next generation of artificial intelligence applications. However, the generations of LLMs are not entirely reliable, often producing content with factual errors, biases, and toxicity. Given their vast number of users and wide range of application scenarios, these unreliable responses can lead to many serious negative impacts. This thesis introduces the exploratory works in the field of language model reliability during the PhD study, focusing on the correctness, non-toxicity, and fairness of LLMs from both software testing and natural language processing perspectives. First, to measure the correctness of LLMs, we introduce two testing frameworks, FactChecker and LogicAsker, to evaluate factual knowledge and logical reasoning accuracy, respectively. Second, for the non-toxicity of LLMs, we introduce two works for red-teaming LLMs. Third, to evaluate the fairness of LLMs, we introduce two evaluation frameworks, BiasAsker and XCulturalBench, to measure the social bias and cultural bias of LLMs, respectively.

The design of fusion devices is typically based on computationally expensive simulations. This can be alleviated using high aspect ratio models that employ a reduced number of free parameters, especially in the case of stellarator optimization where non-axisymmetric magnetic fields with a large parameter space are optimized to satisfy certain performance criteria. However, optimization is still required to find configurations with properties such as low elongation, high rotational transform, finite plasma beta, and good fast particle confinement. In this work, we train a machine learning model to construct configurations with favorable confinement properties by finding a solution to the inverse design problem, that is, obtaining a set of model input parameters for given desired properties. Since the solution of the inverse problem is non-unique, a probabilistic approach, based on mixture density networks, is used. It is shown that optimized configurations can be generated reliably using this method.

With the recent unprecedented advancements in Artificial Intelligence (AI) computing, progress in Large Language Models (LLMs) is accelerating rapidly, presenting challenges in establishing clear guidelines, particularly in the field of security. That being said, we thoroughly identify and describe three main technical challenges in the security and software engineering literature that spans the entire LLM workflow, namely; \textbf{\textit{(i)}} Data Collection and Labeling; \textbf{\textit{(ii)}} System Design and Learning; and \textbf{\textit{(iii)}} Performance Evaluation. Building upon these challenges, this paper introduces \texttt{SecRepair}, an instruction-based LLM system designed to reliably \textit{identify}, \textit{describe}, and automatically \textit{repair} vulnerable source code. Our system is accompanied by a list of actionable guides on \textbf{\textit{(i)}} Data Preparation and Augmentation Techniques; \textbf{\textit{(ii)}} Selecting and Adapting state-of-the-art LLM Models; \textbf{\textit{(iii)}} Evaluation Procedures. \texttt{SecRepair} uses a reinforcement learning-based fine-tuning with a semantic reward that caters to the functionality and security aspects of the generated code. Our empirical analysis shows that \texttt{SecRepair} achieves a \textit{12}\% improvement in security code repair compared to other LLMs when trained using reinforcement learning. Furthermore, we demonstrate the capabilities of \texttt{SecRepair} in generating reliable, functional, and compilable security code repairs against real-world test cases using automated evaluation metrics.

Research on geospatial foundation models (GFMs) has become a trending topic in geospatial artificial intelligence (AI) research due to their potential for achieving high generalizability and domain adaptability, reducing model training costs for individual researchers. Unlike large language models, such as ChatGPT, constructing visual foundation models for image analysis, particularly in remote sensing, encountered significant challenges such as formulating diverse vision tasks into a general problem framework. This paper evaluates the recently released NASA-IBM GFM Prithvi for its predictive performance on high-level image analysis tasks across multiple benchmark datasets. Prithvi was selected because it is one of the first open-source GFMs trained on time-series of high-resolution remote sensing imagery. A series of experiments were designed to assess Prithvi's performance as compared to other pre-trained task-specific AI models in geospatial image analysis. New strategies, including band adaptation, multi-scale feature generation, and fine-tuning techniques, are introduced and integrated into an image analysis pipeline to enhance Prithvi's domain adaptation capability and improve model performance. In-depth analyses reveal Prithvi's strengths and weaknesses, offering insights for both improving Prithvi and developing future visual foundation models for geospatial tasks.

Transferable adversarial attacks pose significant threats to deep neural networks, particularly in black-box scenarios where internal model information is inaccessible. Studying adversarial attack methods helps advance the performance of defense mechanisms and explore model vulnerabilities. These methods can uncover and exploit weaknesses in models, promoting the development of more robust architectures. However, current methods for transferable attacks often come with substantial computational costs, limiting their deployment and application, especially in edge computing scenarios. Adversarial generative models, such as Generative Adversarial Networks (GANs), are characterized by their ability to generate samples without the need for retraining after an initial training phase. GE-AdvGAN, a recent method for transferable adversarial attacks, is based on this principle. In this paper, we propose a novel general framework for gradient editing-based transferable attacks, named GE-AdvGAN+, which integrates nearly all mainstream attack methods to enhance transferability while significantly reducing computational resource consumption. Our experiments demonstrate the compatibility and effectiveness of our framework. Compared to the baseline AdvGAN, our best-performing method, GE-AdvGAN++, achieves an average ASR improvement of 47.8. Additionally, it surpasses the latest competing algorithm, GE-AdvGAN, with an average ASR increase of 5.9. The framework also exhibits enhanced computational efficiency, achieving 2217.7 FPS, outperforming traditional methods such as BIM and MI-FGSM. The implementation code for our GE-AdvGAN+ framework is available at https://github.com/GEAdvGANP

The US military is planning to launch balloons that are capable of providing high-altitude surveillance. It comes after the nation scrambled fighter jets to shoot down a Chinese balloon as it drifted through North American airspace last year. Modern balloons can use artificial intelligence to predict and ride wind currents while operating at altitudes around 18 kilometres, or even higher, in Earth's stratosphere for commercial and military purposes.

As the US speeds toward one of the most consequential elections in its 248-year history, Google is rolling out safeguards to ensure users get reliable information. In addition to the measures it announced late last year, the company said on Friday that it's adding election-related guardrails to YouTube, Search, Google Play and AI products. YouTube will add information panels above the search results for at least some federal election candidates. The modules, likely similar to those you see when searching the web for prominent figures, will include the candidates' basic details like their political party and a link to Google Search for more info. The company says the panels may also include a link to the person's official website (or other channel).

"Prevailing Narrative" podcast host Matthew Bilinsky discusses the federal law enforcement request for Google to hand over YouTube data on certain users on "Fox News @ Night." Ford Motor Company recently filed a patent application that's raising eyebrows and sparking debate about privacy and surveillance on our roads. The patent, "Systems and Methods for Detecting Speeding Violations," describes a system that could turn Ford vehicles into mobile speed detectors capable of reporting other drivers to the police. The patent application was filed with the United States Patent and Trademark Office (USPTO) in January 2023. However, it was formally published by the USPTO on July 18, 2024.

More and more people are learning about the world through chatbots and the software's kin, whether they mean to or not. Google has rolled out generative AI to users of its search engine on at least four continents, placing AI-written responses above the usual list of links; as many as 1 billion people may encounter this feature by the end of the year. Meta's AI assistant has been integrated into Facebook, Messenger, WhatsApp, and Instagram, and is sometimes the default option when a user taps the search bar. And Apple is expected to integrate generative AI into Siri, Mail, Notes, and other apps this fall. Less than two years after ChatGPT's launch, bots are quickly becoming the default filters for the web.