Search

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example, a well-built agent using GPT-3.5-Turbo as its core can outperform the more advanced GPT-4 model by leveraging external components. More importantly, the usage of tools enables these systems to perform actions in the real world, moving from merely generating text to actively interacting with their environment. Given the agents' practical applications and their ability to execute consequential actions, it is crucial to assess potential vulnerabilities. Such autonomous systems can cause more severe damage than a standalone language model if compromised. While some existing research has explored harmful actions by LLM agents, our study approaches the vulnerability from a different perspective. We introduce a new type of attack that causes malfunctions by misleading the agent into executing repetitive or irrelevant actions. We conduct comprehensive evaluations using various attack methods, surfaces, and properties to pinpoint areas of susceptibility. Our experiments reveal that these attacks can induce failure rates exceeding 80\% in multiple scenarios. Through attacks on implemented and deployable agents in multi-agent scenarios, we accentuate the realistic risks associated with these vulnerabilities. To mitigate such attacks, we propose self-examination detection methods. However, our findings indicate these attacks are difficult to detect effectively using LLMs alone, highlighting the substantial risks associated with this vulnerability.

Contrastive dimension reduction methods have been developed for case-control study data to identify variation that is enriched in the foreground (case) data X relative to the background (control) data Y. Here, we develop contrastive regression for the setting when there is a response variable r associated with each foreground observation. This situation occurs frequently when, for example, the unaffected controls do not have a disease grade or intervention dosage but the affected cases have a disease grade or intervention dosage, as in autism severity, solid tumors stages, polyp sizes, or warfarin dosages. Our contrastive regression model captures shared low-dimensional variation between the predictors in the cases and control groups, and then explains the case-specific response variables through the variance that remains in the predictors after shared variation is removed. We show that, in one single-nucleus RNA sequencing dataset on autism severity in postmortem brain samples from donors with and without autism and in another single-cell RNA sequencing dataset on cellular differentiation in chronic rhinosinusitis with and without nasal polyps, our contrastive linear regression performs feature ranking and identifies biologically-informative predictors associated with response that cannot be identified using other approaches

As automation technologies advance, the need for compact and multi-modal sensors in robotic applications is growing. To address this demand, we introduce CompdVision, a novel sensor that employs a compound-eye imaging system to combine near-field 3D visual and tactile sensing within a compact form factor. CompdVision utilizes two types of vision units to address diverse sensing needs, eliminating the need for complex modality conversion. Stereo units with far-focus lenses can see through the transparent elastomer for depth estimation beyond the contact surface. Simultaneously, tactile units with near-focus lenses track the movement of markers embedded in the elastomer to obtain contact deformation. Experimental results validate the sensor's superior performance in 3D visual and tactile sensing, proving its capability for reliable external object depth estimation and precise measurement of tangential and normal contact forces. The dual modalities and compact design make the sensor a versatile tool for robotic manipulation., Comment: Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024

While advanced machine learning (ML) models are deployed in numerous real-world applications, previous works demonstrate these models have security and privacy vulnerabilities. Various empirical research has been done in this field. However, most of the experiments are performed on target ML models trained by the security researchers themselves. Due to the high computational resource requirement for training advanced models with complex architectures, researchers generally choose to train a few target models using relatively simple architectures on typical experiment datasets. We argue that to understand ML models' vulnerabilities comprehensively, experiments should be performed on a large set of models trained with various purposes (not just the purpose of evaluating ML attacks and defenses). To this end, we propose using publicly available models with weights from the Internet (public models) for evaluating attacks and defenses on ML models. We establish a database, namely SecurityNet, containing 910 annotated image classification models. We then analyze the effectiveness of several representative attacks/defenses, including model stealing attacks, membership inference attacks, and backdoor detection on these public models. Our evaluation empirically shows the performance of these attacks/defenses can vary significantly on public models compared to self-trained models. We share SecurityNet with the research community. and advocate researchers to perform experiments on public models to better demonstrate their proposed methods' effectiveness in the future., Comment: To appear in the 33rd USENIX Security Symposium, August 2024, Philadelphia, PA, USA

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other attacks, such as membership inference, generating adversarial examples. Therefore, such information, e.g., hyperparameters, should be kept confidential. It is well known that an adversary can leverage a target ML model's output to steal the model's information. In this paper, we discover a new side channel for model information stealing attacks, i.e., models' scientific plots which are extensively used to demonstrate model performance and are easily accessible. Our attack is simple and straightforward. We leverage the shadow model training techniques to generate training data for the attack model which is essentially an image classifier. Extensive evaluation on three benchmark datasets shows that our proposed attack can effectively infer the architecture/hyperparameters of image classifiers based on convolutional neural network (CNN) given the scientific plot generated from it. We also reveal that the attack's success is mainly caused by the shape of the scientific plots, and further demonstrate that the attacks are robust in various scenarios. Given the simplicity and effectiveness of the attack method, our study indicates scientific plots indeed constitute a valid side channel for model information stealing attacks. To mitigate the attacks, we propose several defense mechanisms that can reduce the original attacks' accuracy while maintaining the plot utility. However, such defenses can still be bypassed by adaptive attacks., Comment: To appear in the 32nd USENIX Security Symposium, August 2023, Anaheim, CA, USA

Stem cell-derived organoids are a promising tool to model native human tissues as they resemble human organs functionally and structurally compared to traditional monolayer cell-based assays. For instance, colon organoids can spontaneously develop crypt-like structures similar to those found in the native colon. While analyzing the structural development of organoids can be a valuable readout, using traditional image analysis tools makes it challenging because of the heterogeneities and the abstract nature of organoid morphologies. To address this limitation, we developed and validated a deep learning-based image analysis tool, named D-CryptO, for the classification of organoid morphology. D-CryptO can automatically assess the crypt formation and opacity of colorectal organoids from brightfield images to determine the extent of organoid structural maturity. To validate this tool, changes in organoid morphology were analyzed during organoid passaging and short-term forskolin stimulation. To further demonstrate the potential of D-CryptO for drug testing, organoid structures were analyzed following treatments with a panel of chemotherapeutic drugs. With D-CryptO, subtle variations in how colon organoids responded to the different chemotherapeutic drugs were detected, which suggest potentially distinct mechanisms of action. This tool could be expanded to other organoid types, like intestinal organoids, to facilitate 3D tissue morphological analysis., Comment: Lab on a Chip (2022)

In this paper, we present a spatio-temporal tendency reasoning (STR) network for recovering human body pose and shape from videos. Previous approaches have focused on how to extend 3D human datasets and temporal-based learning to promote accuracy and temporal smoothing. Different from them, our STR aims to learn accurate and natural motion sequences in an unconstrained environment through temporal and spatial tendency and to fully excavate the spatio-temporal features of existing video data. To this end, our STR learns the representation of features in the temporal and spatial dimensions respectively, to concentrate on a more robust representation of spatio-temporal features. More specifically, for efficient temporal modeling, we first propose a temporal tendency reasoning (TTR) module. TTR constructs a time-dimensional hierarchical residual connection representation within a video sequence to effectively reason temporal sequences' tendencies and retain effective dissemination of human information. Meanwhile, for enhancing the spatial representation, we design a spatial tendency enhancing (STE) module to further learns to excite spatially time-frequency domain sensitive features in human motion information representations. Finally, we introduce integration strategies to integrate and refine the spatio-temporal feature representations. Extensive experimental findings on large-scale publically available datasets reveal that our STR remains competitive with the state-of-the-art on three datasets. Our code are available at https://github.com/Changboyang/STR.git., Comment: Accepted by BMVC2022

With the rapid development of AI technologies, thousands of AI papers are being published each year. Many of these papers have released sample code to facilitate follow-up researchers. This paper presents an explorative study of over 1700 code repositories of AI papers hosted on GitHub. We find that these repositories are often poorly written, lack of documents, lack of maintenance, and hard to configure the underlying runtime environment. Thus, many code repositories become inactive and abandoned. Such a situation makes follow-up researchers hard to reproduce the results or do further research. In addition, these hard-to-reuse code makes a gap between academia and industry. Based on the findings, we give some recommendations on how to improve the quality of code repositories of AI papers.

Lying at the heart of quantum mechanics, coherence has recently been studied as a key resource in quantum information theory. Quantum steering, a fundamental notion originally considered by Schr{\"o}dinger, has also recently received much attention. When Alice and Bob share a correlated quantum system, Alice can perform a local measurement to `steer' Bob's reduced state. We introduce the maximal steered coherence as a measure describing the extent to which steering can remotely create coherence; more precisely, we find the maximal coherence of Bob's steered state in the eigenbasis of his original reduced state, where maximization is performed over all positive-operator valued measurements for Alice. We prove that maximal steered coherence vanishes for quantum-classical states whilst reaching a maximum for pure entangled states with full Schmidt rank. Although invariant under local unitary operations, maximal steered coherence may be increased when Bob performs a channel. For a two-qubit state we find that Bob's channel can increase maximal steered coherence if and only if it is neither unital nor semi-classical, which coincides with the condition for increasing discord. Our results show that the power of steering for coherence generation, though related to discord, is distinct from existing measures of quantum correlation., Comment: Published version

As minimum feature size and pitch spacing further decrease, triple patterning lithography (TPL) is a possible 193nm extension along the paradigm of double patterning lithography (DPL). However, there is very little study on TPL layout decomposition. In this paper, we show that TPL layout decomposition is a more difficult problem than that for DPL. We then propose a general integer linear programming formulation for TPL layout decomposition which can simultaneously minimize conflict and stitch numbers. Since ILP has very poor scalability, we propose three acceleration techniques without sacrificing solution quality: independent component computation, layout graph simplification, and bridge computation. For very dense layouts, even with these speedup techniques, ILP formulation may still be too slow. Therefore, we propose a novel vector programming formulation for TPL decomposition, and solve it through effective semidefinite programming (SDP) approximation. Experimental results show that the ILP with acceleration techniques can reduce 82% runtime compared to the baseline ILP. Using SDP based algorithm, the runtime can be further reduced by 42% with some tradeoff in the stitch number (reduced by 7%) and the conflict (9% more). However, for very dense layouts, SDP based algorithm can achieve 140x speed-up even compared with accelerated ILP.

Near perfect infrared light absorption at multi-spectral wavelengths has been experimentally demonstrated by using multiplexed metal square plasmon resonance structures. Optical power absorption over 95% has been observed in dual-band metamaterial absorbers at two separate wavelengths and optical power absorption over 92.5% has been observed in triple-band metamaterial absorbers at three separate wavelengths. The peak absorption wavelengths are primarily determined by the sizes of the metal squares in the multiplexed structures. Electrical field distributions in the middle of the dielectric spacer layer were calculated at the peak absorption wavelengths. It is shown that strong light absorption corresponds to the local quadrupole plasmon resonance modes in the metamaterial structures.

Solids and rigid tissues such as bone, ligaments, and tendons, typically appear dark in magnetic resonance imaging (MRI), which is due to the extremely short-lived proton nuclear magnetic resonance (NMR) signals. This short lifetime is due to strong dipolar interactions between immobilized proton spins, which render it challenging to detect these signals with sufficient resolution and sensitivity. Here we show the possibility of exciting long-lived signals in cortical bone tissue with a signature consistent with that of bound water signals. Contrary to long-standing belief, it is further shown that dipolar coupling networks are an integral requirement for the excitation of these long-lived signals. The use of these signals could enhance the ability to visualize rigid tissues and solid samples with high sensitivity, resolution, and specificity via MRI., Comment: 11 pages, 7 figures

We experimentally demonstrate a wide band near perfect light absorber in the mid-wave infrared region using multiplexed plasmonic metal structures. The wide band near perfect light absorber is made of two different size gold metal squares multiplexed on a thin dielectric spacing layer on the top of a thick metal layer in each unit cell. We also fabricate regular non-multiplexed structure perfect light absorbers. The multiplexed structure IR absorber absorbs above 98% incident light over a much wider spectral band than the regular non-multiplexed structure perfect light absorbers in the mid-wave IR region.

In this letter, we show that the bandwidth of optical band-stop filters made of subwavelength metal structures can be significantly increased by the strong plasmonic near-field coupling through the corners of the periodic metal squares. The effect of small gap coupling on the spectral bandwidth is investigated by varying the gap size between the metal squares. An equivalent transmission line model is used to fit the transmission and reflection spectra of the metal filters. The transmission line model can characterize well the metal structures with the gap size larger than the near-field decay length. However, it fails to model the transmission and reflection spectra when the gap size reaches the decay range of the near-field in the small gaps.