Search

Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety alignment are developed for defense, prior researches reveal the possibility of bypassing such defenses through well-designed jailbreak attacks. In this paper, we propose QueryAttack, a novel framework to examine the generalizability of safety alignment. By treating LLMs as knowledge databases, we translate malicious queries in natural language into structured non-natural query language to bypass the safety alignment mechanisms of LLMs. We conduct extensive experiments on mainstream LLMs, and the results show that QueryAttack not only can achieve high attack success rates (ASRs), but also can jailbreak various defense methods. Furthermore, we tailor a defense method against QueryAttack, which can reduce ASR by up to 64% on GPT-4-1106. Our code is available at https://github.com/horizonsinzqs/QueryAttack., Comment: 15 pages, 11 figures

The rise of HDR-WCG display devices has highlighted the need to convert SDRTV to HDRTV, as most video sources are still in SDR. Existing methods primarily focus on designing neural networks to learn a single-style mapping from SDRTV to HDRTV. However, the limited information in SDRTV and the diversity of styles in real-world conversions render this process an ill-posed problem, thereby constraining the performance and generalization of these methods. Inspired by generative approaches, we propose a novel method for SDRTV to HDRTV conversion guided by real HDRTV priors. Despite the limited information in SDRTV, introducing real HDRTV as reference priors significantly constrains the solution space of the originally high-dimensional ill-posed problem. This shift transforms the task from solving an unreferenced prediction problem to making a referenced selection, thereby markedly enhancing the accuracy and reliability of the conversion process. Specifically, our approach comprises two stages: the first stage employs a Vector Quantized Generative Adversarial Network to capture HDRTV priors, while the second stage matches these priors to the input SDRTV content to recover realistic HDRTV outputs. We evaluate our method on public datasets, demonstrating its effectiveness with significant improvements in both objective and subjective metrics across real and synthetic datasets., Comment: 8 pages,4 figures

Recent advances in neural camera imaging pipelines have demonstrated notable progress. Nevertheless, the real-world imaging pipeline still faces challenges including the lack of joint optimization in system components, computational redundancies, and optical distortions such as lens shading.In light of this, we propose an end-to-end camera imaging pipeline (RealCamNet) to enhance real-world camera imaging performance. Our methodology diverges from conventional, fragmented multi-stage image signal processing towards end-to-end architecture. This architecture facilitates joint optimization across the full pipeline and the restoration of coordinate-biased distortions. RealCamNet is designed for high-quality conversion from RAW to RGB and compact image compression. Specifically, we deeply analyze coordinate-dependent optical distortions, e.g., vignetting and dark shading, and design a novel Coordinate-Aware Distortion Restoration (CADR) module to restore coordinate-biased distortions. Furthermore, we propose a Coordinate-Independent Mapping Compression (CIMC) module to implement tone mapping and redundant information compression. Existing datasets suffer from misalignment and overly idealized conditions, making them inadequate for training real-world imaging pipelines. Therefore, we collected a real-world imaging dataset. Experiment results show that RealCamNet achieves the best rate-distortion performance with lower inference latency., Comment: accept by ACMMM 2024

We prove the existence on long time scales of the solutions to the Cauchy problem for a version of weakly transverse Boussinesq systems arising in the modeling of surface water waves. This system is much more complicated than the isotropic Boussinesq systems because dispersion is only present in the x-direction, leading to anisotropic eigenvalues in the linearized system. This anisotropic character leads to loss of y-derivatives for the solutions. To overcome this main difficulty our strategy is to symmetrize the system by introducing suitable good unknowns in the sense of [3]., Comment: 45 pages

Bell non-locality is closely related with device independent quantum randomness. In this paper, we present a kind of sum-of-squares (SOS) decomposition for general Bell inequalities in two qubits systems. By using the obtained SOS decomposition, we can then find the measurement operators associated with the maximal violation of considered Bell inequality. We also practice the SOS decomposition method by considering the (generalized) Clauser-Horne-Shimony-Holt (CHSH) Bell inequality, the Elegant Bell inequality, the Gisin inequality and the Chained Bell inequality as examples. The corresponding SOS decompositions and the measurement operators that cause the maximum violation values of these Bell inequalities are derived, which are consistent with previous results. We further discuss the device independent quantum randomness by using the SOS decompositions of Bell inequalities. We take the generalized CHSH inequality with the maximally entangled state and the Werner state that attaining the maximal violations as examples. Exact value or lower bound on the maximal guessing probability using the SOS decomposition are obtained. For Werner state, the lower bound can supply a much precise estimation of quantum randomness when $p$ tends to $1$., Comment: 10 pages, 2 figures

The strategic orchestration of football matchplays profoundly influences game outcomes, motivating a surge in research aimed at uncovering tactical nuances through social network analysis. In this paper, we delve into the microscopic intricacies of cooperative player interactions by focusing on triadic motifs within passing networks. Employing a dataset compiled from 3,199 matches across 18 premier football competitions, we identify successful passing activities and construct passing networks for both home and away teams. Our findings highlight a pronounced disparity in passing efficiency, with home teams demonstrating superior performance relative to away teams. Through the identification and analysis of 3-motifs, we find that the motifs with more bidirectional links are more significant. It reveals that footballers exhibit a strong tendency towards backward passes rather than direct forward attacks. Comparing the results of games, we find that some motifs are related to the goal difference. It indicates that direct and effective forward passing significantly amplifies a team's offensive capabilities, whereas an abundance of passbacks portends an elevated risk of offensive futility. These revelations affirm the efficacy of network motif analysis as a potent analytical tool for unveiling the foundational components of passing dynamics among footballers and for decoding the complex tactical behaviors and interaction modalities that underpin team performance.

We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained diffusion model, such as the understanding of image semantics and structural information, to address unsupervised visual tracking. To this end, we design an initial prompt learner to enable the diffusion model to recognize the tracking target by learning a prompt representing the target. Furthermore, to facilitate dynamic adaptation of the prompt to the target's movements, we propose an online prompt updater. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our proposed method, which also achieves state-of-the-art performance., Comment: ECCV 2024

Cell image segmentation is usually implemented using fully supervised deep learning methods, which heavily rely on extensive annotated training data. Yet, due to the complexity of cell morphology and the requirement for specialized knowledge, pixel-level annotation of cell images has become a highly labor-intensive task. To address the above problems, we propose an active learning framework for cell segmentation using bounding box annotations, which greatly reduces the data annotation cost of cell segmentation algorithms. First, we generate a box-supervised learning method (denoted as YOLO-SAM) by combining the YOLOv8 detector with the Segment Anything Model (SAM), which effectively reduces the complexity of data annotation. Furthermore, it is integrated into an active learning framework that employs the MC DropBlock method to train the segmentation model with fewer box-annotated samples. Extensive experiments demonstrate that our model saves more than ninety percent of data annotation time compared to mask-supervised deep learning methods.

Multiple complex degradations are coupled in low-quality video faces in the real world. Therefore, blind video face restoration is a highly challenging ill-posed problem, requiring not only hallucinating high-fidelity details but also enhancing temporal coherence across diverse pose variations. Restoring each frame independently in a naive manner inevitably introduces temporal incoherence and artifacts from pose changes and keypoint localization errors. To address this, we propose the first blind video face restoration approach with a novel parsing-guided temporal-coherent transformer (PGTFormer) without pre-alignment. PGTFormer leverages semantic parsing guidance to select optimal face priors for generating temporally coherent artifact-free results. Specifically, we pre-train a temporal-spatial vector quantized auto-encoder on high-quality video face datasets to extract expressive context-rich priors. Then, the temporal parse-guided codebook predictor (TPCP) restores faces in different poses based on face parsing context cues without performing face pre-alignment. This strategy reduces artifacts and mitigates jitter caused by cumulative errors from face pre-alignment. Finally, the temporal fidelity regulator (TFR) enhances fidelity through temporal feature interaction and improves video temporal consistency. Extensive experiments on face videos show that our method outperforms previous face restoration baselines. The code will be released on \href{https://github.com/kepengxu/PGTFormer}{https://github.com/kepengxu/PGTFormer}., Comment: 9 pages