Search

Diffusion models have demonstrated remarkable efficacy across various image-to-image tasks. In this research, we introduce Imagine yourself, a state-of-the-art model designed for personalized image generation. Unlike conventional tuning-based personalization techniques, Imagine yourself operates as a tuning-free model, enabling all users to leverage a shared framework without individualized adjustments. Moreover, previous work met challenges balancing identity preservation, following complex prompts and preserving good visual quality, resulting in models having strong copy-paste effect of the reference images. Thus, they can hardly generate images following prompts that require significant changes to the reference image, \eg, changing facial expression, head and body poses, and the diversity of the generated images is low. To address these limitations, our proposed method introduces 1) a new synthetic paired data generation mechanism to encourage image diversity, 2) a fully parallel attention architecture with three text encoders and a fully trainable vision encoder to improve the text faithfulness, and 3) a novel coarse-to-fine multi-stage finetuning methodology that gradually pushes the boundary of visual quality. Our study demonstrates that Imagine yourself surpasses the state-of-the-art personalization model, exhibiting superior capabilities in identity preservation, visual quality, and text alignment. This model establishes a robust foundation for various personalization applications. Human evaluation results validate the model's SOTA superiority across all aspects (identity preservation, text faithfulness, and visual appeal) compared to the previous personalization models.

The growing demand for AI training data has transformed data annotation into a global industry, but traditional approaches relying on human annotators are often time-consuming, labor-intensive, and prone to inconsistent quality. We propose the Model-in-the-Loop (MILO) framework, which integrates AI/ML models into the annotation process. Our research introduces a collaborative paradigm that leverages the strengths of both professional human annotators and large language models (LLMs). By employing LLMs as pre-annotation and real-time assistants, and judges on annotator responses, MILO enables effective interaction patterns between human annotators and LLMs. Three empirical studies on multimodal data annotation demonstrate MILO's efficacy in reducing handling time, improving data quality, and enhancing annotator experiences. We also introduce quality rubrics for flexible evaluation and fine-grained feedback on open-ended annotations. The MILO framework has implications for accelerating AI/ML development, reducing reliance on human annotation alone, and promoting better alignment between human and machine values.

The Knowledge Graph-to-Text Generation task aims to convert structured knowledge graphs into coherent and human-readable natural language text. Recent efforts in this field have focused on enhancing pre-trained language models (PLMs) by incorporating graph structure information to capture the intricate structure details of knowledge graphs. However, most of these approaches tend to capture only single-granularity structure information, concentrating either on the relationships between entities within the original graph or on the relationships between words within the same entity or across different entities. This narrow focus results in a significant limitation: models that concentrate solely on entity-level structure fail to capture the nuanced semantic relationships between words, while those that focus only on word-level structure overlook the broader relationships between original entire entities. To overcome these limitations, this paper introduces the Multi-granularity Graph Structure Attention (MGSA), which is based on PLMs. The encoder of the model architecture features an entity-level structure encoding module, a word-level structure encoding module, and an aggregation module that synthesizes information from both structure. This multi-granularity structure encoding approach allows the model to simultaneously capture both entity-level and word-level structure information, providing a more comprehensive understanding of the knowledge graph's structure information, thereby significantly improving the quality of the generated text. We conducted extensive evaluations of the MGSA model using two widely recognized KG-to-Text Generation benchmark datasets, WebNLG and EventNarrative, where it consistently outperformed models that rely solely on single-granularity structure information, demonstrating the effectiveness of our approach.

The integration of technology and healthcare has ushered in a new era where software systems, powered by artificial intelligence and machine learning, have become essential components of medical products and services. While these advancements hold great promise for enhancing patient care and healthcare delivery efficiency, they also expose sensitive medical data and system integrity to potential cyberattacks. This paper explores the security and privacy threats posed by AI/ML applications in healthcare. Through a thorough examination of existing research across a range of medical domains, we have identified significant gaps in understanding the adversarial attacks targeting medical AI systems. By outlining specific adversarial threat models for medical settings and identifying vulnerable application domains, we lay the groundwork for future research that investigates the security and resilience of AI-driven medical systems. Through our analysis of different threat models and feasibility studies on adversarial attacks in different medical domains, we provide compelling insights into the pressing need for cybersecurity research in the rapidly evolving field of AI healthcare technology.

Artificial Intelligence Generated Content (AIGC) services can efficiently satisfy user-specified content creation demands, but the high computational requirements pose various challenges to supporting mobile users at scale. In this paper, we present our design of an edge-enabled AIGC service provisioning system to properly assign computing tasks of generative models to edge servers, thereby improving overall user experience and reducing content generation latency. Specifically, once the edge server receives user requested task prompts, it dynamically assigns appropriate models and allocates computing resources based on features of each category of prompts. The generated contents are then delivered to users. The key to this system is a proposed probabilistic model assignment approach, which estimates the quality score of generated contents for each prompt based on category labels. Next, we introduce a heuristic algorithm that enables adaptive configuration of both generation steps and resource allocation, according to the various task requests received by each generative model on the edge.Simulation results demonstrate that the designed system can effectively enhance the quality of generated content by up to 4.7% while reducing response delay by up to 39.1% compared to benchmarks.

In this paper, we explore adaptive offloading and enhancement strategies for video analytics tasks on computing-constrained mobile devices in low-light conditions. We observe that the accuracy of low-light video analytics varies from different enhancement algorithms. The root cause could be the disparities in the effectiveness of enhancement algorithms for feature extraction in analytic models. Specifically, the difference in class activation maps (CAMs) between enhanced and low-light frames demonstrates a positive correlation with video analytics accuracy. Motivated by such observations, a novel enhancement quality assessment method is proposed on CAMs to evaluate the effectiveness of different enhancement algorithms for low-light videos. Then, we design a multi-edge system, which adaptively offloads and enhances low-light video analytics tasks from mobile devices. To achieve the trade-off between the enhancement quality and the latency for all system-served mobile devices, we propose a genetic-based scheduling algorithm, which can find a near-optimal solution in a reasonable time to meet the latency requirement. Thereby, the offloading strategies and the enhancement algorithms are properly selected under the condition of limited end-edge bandwidth and edge computation resources. Simulation experiments demonstrate the superiority of the proposed system, improving accuracy up to 20.83\% compared to existing benchmarks.

Blind image deblurring is a challenging low-level vision task that involves estimating the unblurred image when the blur kernel is unknown. In this paper, we present a self-supervised multi-scale blind image deblurring method to jointly estimate the latent image and the blur kernel via alternating optimization. In the image estimation step, we construct a multi-scale generator network with multiple inputs and multiple outputs to collaboratively estimate latent images at various scales, supervised by an image pyramid constructed from only the blurred image. This generator places architectural constraints on the network and avoids the need for mathematical expression of image priors. In the blur kernel estimation step, the blur kernel at each scale is independently estimated with a direct solution to a quadratic regularized least-squares model for its flexible adaptation to the proposed multi-scale generator for image estimation. Thanks to the collaborative estimation across multiple scales, our method avoids the computationally intensive coarse-to-fine propagation and additional image deblurring processes used in traditional mathematical optimization-based methods. Quantitative and qualitative experimental results on synthetic and realistic datasets demonstrate the superior performance of our method, especially for handling large and real-world blurs., Comment: 21 pages, 17 figures, 94 references

Given a number of datasets for evaluating the performance of single reference methods for the low-lying excited states of closed-shell molecules, a comprehensive dataset for assessing the performance of multireference methods for the low-lying excited states of open-shell systems is still lacking. For this reason, we propose an extension (QUEST\#4X) of the radial subset of QUEST\#4 [J. Chem. Theory Comput. 2020, 16, 3720] to cover 110 doublet and 39 quartet excited states. Near-exact results obtained by iCIPT2 (iterative configuration interaction with selection and second-order perturbation correction) are taken as benchmark to calibrate SDSCI (static-dynamic-static configuration interaction) and SDSPT2 (static-dynamic-static second-order perturbation theory), which are minimal MRCI and CI-like perturbation theory, respectively. It is found that SDSCI is very close in accuracy to ic-MRCISD (internally contracted multireference configuration interaction with singles and doubles), although its computational cost is just that of one iteration of the latter. Unlike most variants of MRPT2, SDSPT2 treats single and multiple states in the same way, and performs similarly as MS-NEVPT2 (multi-state n-electron valence second-order perturbation theory). These findings put the SDS family of methods (SDSPT2, SDSCI, and iCIPT2, etc.) on a firm basis., Comment: 58 pages, 3 figures, 7 tables

LLM app ecosystems are quickly maturing and supporting a wide range of use cases, which requires them to collect excessive user data. Given that the LLM apps are developed by third-parties and that anecdotal evidence suggests LLM platforms currently do not strictly enforce their policies, user data shared with arbitrary third-parties poses a significant privacy risk. In this paper we aim to bring transparency in data practices of LLM apps. As a case study, we study OpenAI's GPT app ecosystem. We develop an LLM-based framework to conduct the static analysis of natural language-based source code of GPTs and their Actions (external services) to characterize their data collection practices. Our findings indicate that Actions collect expansive data about users, including sensitive information prohibited by OpenAI, such as passwords. We find that some Actions, including related to advertising and analytics, are embedded in multiple GPTs, which allow them to track user activities across GPTs. Additionally, co-occurrence of Actions exposes as much as 9.5x more data to them, than it is exposed to individual Actions. Lastly, we develop an LLM-based privacy policy analysis framework to automatically check the consistency of data collection by Actions with disclosures in their privacy policies. Our measurements indicate that the disclosures for most of the collected data types are omitted in privacy policies, with only 5.8% of Actions clearly disclosing their data collection practices.

Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances, disclosing only the class label proportions per bag. This paradigm is essential for user modeling and personalization, where user privacy is paramount, offering insights into user preferences without revealing individual data. LLP faces a unique difficulty: the misalignment between bag-level supervision and the objective of instance-level prediction, primarily due to the inherent ambiguity in label proportion matching. Previous studies have demonstrated deep representation learning can generate auxiliary signals to promote the supervision level in the image domain. However, applying these techniques to tabular data presents significant challenges: 1) they rely heavily on label-invariant augmentation to establish multi-view, which is not feasible with the heterogeneous nature of tabular datasets, and 2) tabular datasets often lack sufficient semantics for perfect class distinction, making them prone to suboptimality caused by the inherent ambiguity of label proportion matching. To address these challenges, we propose an augmentation-free contrastive framework TabLLP-BDC that introduces class-aware supervision (explicitly aware of class differences) at the instance level. Our solution features a two-stage Bag Difference Contrastive (BDC) learning mechanism that establishes robust class-aware instance-level supervision by disassembling the nuance between bag label proportions, without relying on augmentations. Concurrently, our model presents a pioneering multi-task pretraining pipeline tailored for tabular-based LLP, capturing intrinsic tabular feature correlations in alignment with label proportion distribution. Extensive experiments demonstrate that TabLLP-BDC achieves state-of-the-art performance for LLP in the tabular domain.

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Unsupervised domain adaptation (UDA) aims to mitigate the domain shift issue, where the distribution of training (source) data differs from that of testing (target) data. Many models have been developed to tackle this problem, and recently vision transformers (ViTs) have shown promising results. However, the complexity and large number of trainable parameters of ViTs restrict their deployment in practical applications. This underscores the need for an efficient model that not only reduces trainable parameters but also allows for adjustable complexity based on specific needs while delivering comparable performance. To achieve this, in this paper we introduce an Efficient Unsupervised Domain Adaptation (EUDA) framework. EUDA employs the DINOv2, which is a self-supervised ViT, as a feature extractor followed by a simplified bottleneck of fully connected layers to refine features for enhanced domain adaptation. Additionally, EUDA employs the synergistic domain alignment loss (SDAL), which integrates cross-entropy (CE) and maximum mean discrepancy (MMD) losses, to balance adaptation by minimizing classification errors in the source domain while aligning the source and target domain distributions. The experimental results indicate the effectiveness of EUDA in producing comparable results as compared with other state-of-the-art methods in domain adaptation with significantly fewer trainable parameters, between 42% to 99.7% fewer. This showcases the ability to train the model in a resource-limited environment. The code of the model is available at: https://github.com/A-Abedi/EUDA., Comment: 12 pages, 4 figures

In parallel to the unified construction of relativistic Hamiltonians based solely on physical arguments [J. Chem. Phys. 160, 084111 (2024)], a unified implementation of relativistic wave function methods is achieved here via programming techniques (e.g., template metaprogramming and polymorphism in C++). That is, once the code for constructing the Hamiltonian matrix is made ready, all the rest can be generated automatically from existing templates used for the nonrelativistic counterparts. This is facilitated by breaking a second-quantized relativistic Hamiltonian down to diagrams that are topologically the same as those required for computing the basic coupling coefficients between spin-free configuration state functions (CSF). Moreover, both time reversal and binary double point group symmetries can readily be incorporated into molecular integrals and Hamiltonian matrix elements. The latter can first be evaluated in the space of (randomly selected) spin-dependent determinants and then transformed to that of spin-dependent CSFs, thanks to simple relations in between. As a showcase, we consider here the no-pair four-component relativistic iterative configuration interaction with selection and perturbation correction (4C-iCIPT2), which is a natural extension of the spin-free iCIPT2 [J. Chem. Theory Comput. 17, 949 (2021)], and can provide near-exact numerical results within the manifold of positive energy states (PES), as demonstrated by numerical examples.

We investigate correlation-enhanced low temperature quantum thermometry. Recent studies have revealed that bath-induced correlations can enhance the low-temperature estimation precision even starting from an uncorrelated state. However, a comprehensive understanding of this enhancement remains elusive. Using the Ramsey interferometry protocol, we illustrate that the estimation precision of $N$ thermometers sparsely coupled to a common low-temperature bath can achieve the Heisenberg scaling in the low-temperature regime with only a $\pi/2$ rotation of the measurement axis, in contrast to the standard Ramsey scheme. This result is based on the assumption that interthermometer correlations are induced exclusively by low-frequency noise in the common bath, a condition achievable in practical experimental scenarios. The underlying physical mechanism is clarified, revealing that the Heisenberg scaling arises from the intrinsic nature of the temperature, which is associated solely with the fluctuation of thermal noise. In contrast to the paradigm of independent thermometers, our proposed scheme demonstrates a significant enhancement in precision for low-temperature measurement, making it suitable for precisely measuring the temperature of ultracold systems., Comment: 7 pages, 2 figures

To completely understand a document, the use of textual information is not enough. Understanding visual cues, such as layouts and charts, is also required. While the current state-of-the-art approaches for document understanding (both OCR-based and OCR-free) work well, a thorough analysis of their capabilities and limitations has not yet been performed. Therefore, in this work, we addresses the limitation of current VisualQA models when applied to charts and plots. To investigate shortcomings of the state-of-the-art models, we conduct a comprehensive behavioral analysis, using ChartQA as a case study. Our findings indicate that existing models particularly underperform in answering questions related to the chart's structural and visual context, as well as numerical information. To address these issues, we propose three simple pre-training tasks that enforce the existing model in terms of both structural-visual knowledge, as well as its understanding of numerical questions. We evaluate our pre-trained model (called MatCha-v2) on three chart datasets - both extractive and abstractive question datasets - and observe that it achieves an average improvement of 1.7% over the baseline model.

This two-part tutorial dives into the field of data-driven power flow linearization (DPFL), a domain gaining increased attention. DPFL stands out for its higher approximation accuracy, wide adaptability, and better ability to implicitly incorporate the latest system attributes. This renders DPFL a potentially superior option for managing the significant fluctuations from renewable energy sources, a step towards realizing a more sustainable energy future, by translating the higher model accuracy into increased economic efficiency and less energy losses. To conduct a deep and rigorous reexamination, this tutorial first classifies existing DPFL methods into DPFL training algorithms and supportive techniques. Their mathematical models, analytical solutions, capabilities, limitations, and generalizability are systematically examined, discussed, and summarized. In addition, this tutorial reviews existing DPFL experiments, examining the settings of test systems, the fidelity of datasets, and the comparison made among a limited number of DPFL methods. Further, this tutorial implements extensive numerical comparisons of all existing DPFL methods (40 methods in total) and four classic physics-driven approaches, focusing on their generalizability, applicability, accuracy, and computational efficiency. Through these simulationmethodss, this tutorial aims to reveal the actual performance of all the methods (including the performances exposed to data noise or outliers), guiding the selection of appropriate linearization methods. Furthermore, this tutorial discusses future directions based on the theoretical and numerical insights gained. As the first part, this paper reexamines DPFL theories, covering all the training algorithms and supportive techniques. Capabilities, limitations, and aspects of generalizability, which were previously unmentioned in the literature, have been identified., Comment: 20 pages

Building on the theoretical insights of Part I, this paper, as the second part of the tutorial, dives deeper into data-driven power flow linearization (DPFL), focusing on comprehensive numerical testing. The necessity of these simulations stems from the theoretical analysis's inherent limitations, particularly the challenge of identifying the differences in real-world performance among DPFL methods with overlapping theoretical capabilities and/or limitations. The absence of a comprehensive numerical comparison of DPFL approaches in the literature also motivates this paper, especially given the fact that over 95% of existing DPFL studies have not provided any open-source codes. To bridge the gap, this paper first reviews existing DPFL experiments, examining the adopted test scenarios, load fluctuation settings, data sources, considerations for data noise/outliers, and the comparison made so far. Subsequently, this paper evaluates a total of 44 methods, containing over 30 existing DPFL approaches, some innovative DPFL techniques, and several classic physics-driven power flow linearization methods for benchmarking. The evaluation spans various dimensions, including generalizability, applicability, accuracy, and computational efficiency, using various different test cases scaling from 9-bus to 1354-bus systems. The numerical analysis identifies and examines significant trends and consistent findings across all methods under various test cases. It also offers theoretical insights into phenomena like under-performance, failure, excessive computation times, etc. Overall, this paper identifies the differences in the performances of the wide range of DPFL methods, reveals gaps not evident from theoretical discussions, assists in method selection for real-world applications, and provides thorough discussions on open questions within DPFL research, indicating ten potential future directions., Comment: 26 pages

This paper explores the integration of active machine learning (ML) for 6G networks, an area that remains under-explored yet holds potential. Unlike passive ML systems, active ML can be made to interact with the network environment. It actively selects informative and representative data points for training, thereby reducing the volume of data needed while accelerating the learning process. While active learning research mainly focuses on data annotation, we call for a network-centric active learning framework that considers both annotation (i.e., what is the label) and data acquisition (i.e., which and how many samples to collect). Moreover, we explore the synergy between generative artificial intelligence (AI) and active learning to overcome existing limitations in both active learning and generative AI. This paper also features a case study on a mmWave throughput prediction problem to demonstrate the practical benefits and improved performance of active learning for 6G networks. Furthermore, we discuss how the implications of active learning extend to numerous 6G network use cases. We highlight the potential of active learning based 6G networks to enhance computational efficiency, data annotation and acquisition efficiency, adaptability, and overall network intelligence. We conclude with a discussion on challenges and future research directions for active learning in 6G networks, including development of novel query strategies, distributed learning integration, and inclusion of human- and machine-in-the-loop learning., Comment: Submitted to IEEE Network Magazine

Accurate geo-localization of Unmanned Aerial Vehicles (UAVs) is crucial for outdoor applications including search and rescue operations, power line inspections, and environmental monitoring. The vulnerability of Global Navigation Satellite Systems (GNSS) signals to interference and spoofing necessitates the development of additional robust localization methods for autonomous navigation. Visual Geo-localization (VG), leveraging onboard cameras and reference satellite maps, offers a promising solution for absolute localization. Specifically, Thermal Geo-localization (TG), which relies on image-based matching between thermal imagery with satellite databases, stands out by utilizing infrared cameras for effective nighttime localization. However, the efficiency and effectiveness of current TG approaches, are hindered by dense sampling on satellite maps and geometric noises in thermal query images. To overcome these challenges, we introduce STHN, a novel UAV thermal geo-localization approach that employs a coarse-to-fine deep homography estimation method. This method attains reliable thermal geo-localization within a 512-meter radius of the UAV's last known location even with a challenging 11\% size ratio between thermal and satellite images, despite the presence of indistinct textures and self-similar patterns. We further show how our research significantly enhances UAV thermal geo-localization performance and robustness against geometric noises under low-visibility conditions in the wild. The code is made publicly available., Comment: 8 pages, 7 figures. Accepted for IEEE Robotics and Automation Letters

Semantic communication, emerging as a breakthrough beyond the classical Shannon paradigm, aims to convey the essential meaning of source data rather than merely focusing on precise yet content-agnostic bit transmission. By interconnecting diverse intelligent agents (e.g., autonomous vehicles and VR devices) via semantic communications, the semantic communication networks (SemComNet) supports semantic-oriented transmission, efficient spectrum utilization, and flexible networking among collaborative agents. Consequently, SemComNet stands out for enabling ever-increasing intelligent applications, such as autonomous driving and Metaverse. However, being built on a variety of cutting-edge technologies including AI and knowledge graphs, SemComNet introduces diverse brand-new and unexpected threats, which pose obstacles to its widespread development. Besides, due to the intrinsic characteristics of SemComNet in terms of heterogeneous components, autonomous intelligence, and large-scale structure, a series of critical challenges emerge in securing SemComNet. In this paper, we provide a comprehensive and up-to-date survey of SemComNet from its fundamentals, security, and privacy aspects. Specifically, we first introduce a novel three-layer architecture of SemComNet for multi-agent interaction, which comprises the control layer, semantic transmission layer, and cognitive sensing layer. Then, we discuss its working modes and enabling technologies. Afterward, based on the layered architecture of SemComNet, we outline a taxonomy of security and privacy threats, while discussing state-of-the-art defense approaches. Finally, we present future research directions, clarifying the path toward building intelligent, robust, and green SemComNet. To our knowledge, this survey is the first to comprehensively cover the fundamentals of SemComNet, alongside a detailed analysis of its security and privacy issues.

This paper studies the directed graph clustering problem through the lens of statistics, where we formulate clustering as estimating underlying communities in the directed stochastic block model (DSBM). We conduct the maximum likelihood estimation (MLE) on the DSBM and thereby ascertain the most probable community assignment given the observed graph structure. In addition to the statistical point of view, we further establish the equivalence between this MLE formulation and a novel flow optimization heuristic, which jointly considers two important directed graph statistics: edge density and edge orientation. Building on this new formulation of directed clustering, we introduce two efficient and interpretable directed clustering algorithms, a spectral clustering algorithm and a semidefinite programming based clustering algorithm. We provide a theoretical upper bound on the number of misclustered vertices of the spectral clustering algorithm using tools from matrix perturbation theory. We compare, both quantitatively and qualitatively, our proposed algorithms with existing directed clustering methods on both synthetic and real-world data, thus providing further ground to our theoretical contributions.

Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into our society. At the same time, there are also concerns on the potential misuse of this powerful technology, prompting defensive measures from service providers. To overcome such protection, jailbreaking prompts have recently emerged as one of the most effective mechanisms to circumvent security restrictions and elicit harmful content originally designed to be prohibited. Due to the rapid development of LLMs and their ease of access via natural languages, the frontline of jailbreak prompts is largely seen in online forums and among hobbyists. To gain a better understanding of the threat landscape of semantically meaningful jailbreak prompts, we systemized existing prompts and measured their jailbreak effectiveness empirically. Further, we conducted a user study involving 92 participants with diverse backgrounds to unveil the process of manually creating jailbreak prompts. We observed that users often succeeded in jailbreak prompts generation regardless of their expertise in LLMs. Building on the insights from the user study, we also developed a system using AI as the assistant to automate the process of jailbreak prompt generation., Comment: Accepted by USENIX Security 2024

Thermometric techniques with high accuracy, fast response speed and ease of implementation are desirable for the study of dynamic combustion environments, transient reacting flows, and non-equilibrium plasmas. Herein, single-shot single-beam coherent Raman scattering (SS-CRS) thermometry is developed, for the first time to our knowledge, by using air lasing as a probe. It's proved that the air-lasing-assisted CRS signal has a high signal-to-noise ratio enabling single-shot measurements at a 1 kHz repetition rate. The SS-CRS thermometry consistently exhibits precision better than 2% at different temperatures, but the inaccuracy grows with the increase in temperature. The high detection precision, 1 kHz acquisition rate and easy-to-implement single-beam scheme are achieved thanks to the unique temporal, spectral and spatial characteristics of air lasing. This work opens a novel avenue for high-speed CRS thermometry, holding tremendous potential for fast diagnostics of transient reacting flows and plasmas., Comment: 15 pages, 4 figures

Large language models (LLMs) extended as systems, such as ChatGPT, have begun supporting third-party applications. These LLM apps leverage the de facto natural language-based automated execution paradigm of LLMs: that is, apps and their interactions are defined in natural language, provided access to user data, and allowed to freely interact with each other and the system. These LLM app ecosystems resemble the settings of earlier computing platforms, where there was insufficient isolation between apps and the system. Because third-party apps may not be trustworthy, and exacerbated by the imprecision of the natural language interfaces, the current designs pose security and privacy risks for users. In this paper, we propose SecGPT, an architecture for LLM-based systems that aims to mitigate the security and privacy issues that arise with the execution of third-party apps. SecGPT's key idea is to isolate the execution of apps and more precisely mediate their interactions outside of their isolated environments. We evaluate SecGPT against a number of case study attacks and demonstrate that it protects against many security, privacy, and safety issues that exist in non-isolated LLM-based systems. The performance overhead incurred by SecGPT to improve security is under 0.3x for three-quarters of the tested queries. To foster follow-up research, we release SecGPT's source code at https://github.com/llm-platform-security/SecGPT.

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks manipulate LLM-integrated applications into producing responses aligned with the attacker's injected content, deviating from the user's actual requests. The substantial risks posed by these attacks underscore the need for a thorough understanding of the threats. Yet, research in this area faces challenges due to the lack of a unified goal for such attacks and their reliance on manually crafted prompts, complicating comprehensive assessments of prompt injection robustness. We introduce a unified framework for understanding the objectives of prompt injection attacks and present an automated gradient-based method for generating highly effective and universal prompt injection data, even in the face of defensive measures. With only five training samples (0.3% relative to the test data), our attack can achieve superior performance compared with baselines. Our findings emphasize the importance of gradient-based testing, which can avoid overestimation of robustness, especially for defense mechanisms., Comment: Pre-print, code is available at https://github.com/SheltonLiu-N/Universal-Prompt-Injection

The prevalence of 3D printing poses a significant risk to public safety, as any individual with internet access and a commodity printer is able to produce untraceable firearms, keys, counterfeit products, etc. To aid government authorities in combating these new security threats, several approaches have been taken to tag 3D-prints with identifying information. Known as fingerprints, this information is written into the object using various bit embedding techniques; examples include varying the height of the molten thermoplastic layers, and depositing metallic powder with different magnetic properties. Yet, the practicality of theses techniques in real-world forensic settings is hindered by the adversarial nature of this problem. That is, the 3D-printing process is out of reach of any law enforcement agencies; it is the adversary who controls all aspects of printing and possesses the printed object. To combat these threats, law enforcement agencies can regulate the manufacturing of 3D printers, on which they may enforce a fingerprinting scheme, and collect adversarially tampered remains (e.g., fragments of a broken 3D-printed firearm) during forensic investigation. Therefore, it is important to devise fingerprinting techniques so that the fingerprint could be extracted even if printing is carried out by the adversary. To this end, we present SIDE (Secure Information Embedding and Extraction), a fingerprinting framework that tackles the adversarial nature of forensic fingerprinting in 3D prints by offering both secure information embedding and secure information extraction.

In Multiple Object Tracking, objects often exhibit non-linear motion of acceleration and deceleration, with irregular direction changes. Tacking-by-detection (TBD) trackers with Kalman Filter motion prediction work well in pedestrian-dominant scenarios but fall short in complex situations when multiple objects perform non-linear and diverse motion simultaneously. To tackle the complex non-linear motion, we propose a real-time diffusion-based MOT approach named DiffMOT. Specifically, for the motion predictor component, we propose a novel Decoupled Diffusion-based Motion Predictor (D$^2$MP). It models the entire distribution of various motion presented by the data as a whole. It also predicts an individual object's motion conditioning on an individual's historical motion information. Furthermore, it optimizes the diffusion process with much fewer sampling steps. As a MOT tracker, the DiffMOT is real-time at 22.7FPS, and also outperforms the state-of-the-art on DanceTrack and SportsMOT datasets with $62.3\%$ and $76.2\%$ in HOTA metrics, respectively. To the best of our knowledge, DiffMOT is the first to introduce a diffusion probabilistic model into the MOT to tackle non-linear motion prediction., Comment: CVPR2024

Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on. Along with the great potential, there are also increasing concerns over the security of such probabilistic intelligent systems. However, existing studies on LLM security often focus on individual LLM, but without examining the ecosystem through the lens of LLM systems with other objects (e.g., Frontend, Webtool, Sandbox, and so on). In this paper, we systematically analyze the security of LLM systems, instead of focusing on the individual LLMs. To do so, we build on top of the information flow and formulate the security of LLM systems as constraints on the alignment of the information flow within LLM and between LLM and other objects. Based on this construction and the unique probabilistic nature of LLM, the attack surface of the LLM system can be decomposed into three key components: (1) multi-layer security analysis, (2) analysis of the existence of constraints, and (3) analysis of the robustness of these constraints. To ground this new attack surface, we propose a multi-layer and multi-step approach and apply it to the state-of-art LLM system, OpenAI GPT4. Our investigation exposes several security issues, not just within the LLM model itself but also in its integration with other components. We found that although the OpenAI GPT4 has designed numerous safety constraints to improve its safety features, these safety constraints are still vulnerable to attackers. To further demonstrate the real-world threats of our discovered vulnerabilities, we construct an end-to-end attack where an adversary can illicitly acquire the user's chat history, all without the need to manipulate the user's input or gain direct access to OpenAI GPT4. Our demo is in the link: https://fzwark.github.io/LLM-System-Attack-Demo/

In this paper, combining the covolume, we study the Minkowski theory for the non-compact convex set with an asymptotic boundary condition. In particular, the mixed covolume of two non-compact convex sets is introduced and its geometric interpretation is obtained by the Hadamard variational formula. The Brunn-Minkowski and Minkowski inequalities for covolume are established, and the equivalence of these two inequalities are discussed as well. The Minkowski problem for non-compact convex set is proposed and solved under the asymptotic conditions. In the end, we give a solution to the Minkowski problem for $\sigma$-finite measure on the conic domain $\Omega_C$., Comment: 20 pages

Dance serves as a powerful medium for expressing human emotions, but the lifelike generation of dance is still a considerable challenge. Recently, diffusion models have showcased remarkable generative abilities across various domains. They hold promise for human motion generation due to their adaptable many-to-many nature. Nonetheless, current diffusion-based motion generation models often create entire motion sequences directly and unidirectionally, lacking focus on the motion with local and bidirectional enhancement. When choreographing high-quality dance movements, people need to take into account not only the musical context but also the nearby music-aligned dance motions. To authentically capture human behavior, we propose a Bidirectional Autoregressive Diffusion Model (BADM) for music-to-dance generation, where a bidirectional encoder is built to enforce that the generated dance is harmonious in both the forward and backward directions. To make the generated dance motion smoother, a local information decoder is built for local motion enhancement. The proposed framework is able to generate new motions based on the input conditions and nearby motions, which foresees individual motion slices iteratively and consolidates all predictions. To further refine the synchronicity between the generated dance and the beat, the beat information is incorporated as an input to generate better music-aligned dance movements. Experimental results demonstrate that the proposed model achieves state-of-the-art performance compared to existing unidirectional approaches on the prominent benchmark for music-to-dance generation.

We investigate the properties of the two-dimensional model with Rashba-type spin-orbit coupling cubic in electron momentum. In the normal phase, edge states emerge on open boundaries. In the superconducting phase, edge states could evolve into gapped fermionic edge states. Applications to realistic materials of interface superconductors are also discussed., Comment: 5 pages, 4 figures, 1 table

Learning utility, or reward, models from pairwise comparisons is a fundamental component in a number of application domains. These approaches inherently entail collecting preference information from people, with feedback often provided anonymously. Since preferences are subjective, there is no gold standard to compare against; yet, reliance of high-impact systems on preference learning creates a strong motivation for malicious actors to skew data collected in this fashion to their ends. We investigate the nature and extent of this vulnerability systematically by considering a threat model in which an attacker can flip a small subset of preference comparisons with the goal of either promoting or demoting a target outcome. First, we propose two classes of algorithmic approaches for these attacks: a principled gradient-based framework, and several variants of rank-by-distance methods. Next, we demonstrate the efficacy of best attacks in both these classes in successfully achieving malicious goals on datasets from three diverse domains: autonomous control, recommendation system, and textual prompt-response preference learning. We find that the best attacks are often highly successful, achieving in the most extreme case 100% success rate with only 0.3% of the data poisoned. However, which attack is best can vary significantly across domains, demonstrating the value of our comprehensive vulnerability analysis that involves several classes of attack algorithms. In addition, we observe that the simpler and more scalable rank-by-distance approaches are often competitive with the best, and on occasion significantly outperform gradient-based methods. Finally, we show that several state-of-the-art defenses against other classes of poisoning attacks exhibit, at best, limited efficacy in our setting.

Arm Cortex-M processors are the most widely used 32-bit microcontrollers among embedded and Internet-of-Things devices. Despite the widespread usage, there has been little effort in summarizing their hardware security features, characterizing the limitations and vulnerabilities of their hardware and software stack, and systematizing the research on securing these systems. The goals and contributions of this paper are multi-fold. First, we analyze the hardware security limitations and issues of Cortex-M systems. Second, we conducted a deep study of the software stack designed for Cortex-M and revealed its limitations, which is accompanied by an empirical analysis of 1,797 real-world firmware. Third, we categorize the reported bugs in Cortex-M software systems. Finally, we systematize the efforts that aim at securing Cortex-M systems and evaluate them in terms of the protections they offer, runtime performance, required hardware features, etc. Based on the insights, we develop a set of recommendations for the research community and MCU software developers., Comment: To Appear in the 18th USENIX WOOT Conference on Offensive Technologies, August 12-13, 2024