Searcharxiv⌕ Search

arXiv subjects

Dan Ma

Publications and source records attributed to Dan Ma.

34 records · Page 2Linked to original sources
arXiv2024

A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. However, adversarial prompts known as 'jailbreaks' can circumvent safeguards, leading LLMs to generate potentially harmful content. Exploring jailbreak prompts can help to better reveal the weaknesses of LLMs and further steer us to secure them. Unfortunately, existing jailbreak methods either suffer from intricate manual design or require optimization on other white-box models, which compromises either generalization or efficiency. In this paper, we generalize jailbreak prompt attacks into two aspects: (1) Prompt Rewriting and (2) Scenario Nesting. Based on this, we propose ReNeLLM, an automatic framework that leverages LLMs themselves to generate effective jailbreak prompts. Extensive experiments demonstrate that ReNeLLM significantly improves the attack success rate while greatly reducing the time cost compared to existing baselines. Our study also reveals the inadequacy of current defense methods in safeguarding LLMs. Finally, we analyze the failure of LLMs defense from the perspective of prompt execution priority, and propose corresponding defense strategies. We hope that our research can catalyze both the academic community and LLMs developers towards the provision of safer and more regulated LLMs. The code is available at https://github.com/NJUNLP/ReNeLLM.

cs.CL↗
arXiv2023

Entity-Aspect-Opinion-Sentiment Quadruple Extraction for Fine-grained Sentiment Analysis

Product reviews often contain a large number of implicit aspects and object-attribute co-existence cases. Unfortunately, many existing studies in Aspect-Based Sentiment Analysis (ABSA) have overlooked this issue, which can make it difficult to extract opinions comprehensively and fairly. In this paper, we propose a new task called Entity-Aspect-Opinion-Sentiment Quadruple Extraction (EASQE), which aims to hierarchically decompose aspect terms into entities and aspects to avoid information loss, non-exclusive annotations, and opinion misunderstandings in ABSA tasks. To facilitate research in this new task, we have constructed four datasets (Res14-EASQE, Res15-EASQE, Res16-EASQE, and Lap14-EASQE) based on the SemEval Restaurant and Laptop datasets. We have also proposed a novel two-stage sequence-tagging based Trigger-Opinion framework as the baseline for the EASQE task. Empirical evaluations show that our Trigger-Opinion framework can generate satisfactory EASQE results and can also be applied to other ABSA tasks, significantly outperforming state-of-the-art methods. We have made the four datasets and source code of Trigger-Opinion publicly available to facilitate further research in this area.

cs.CL↗
arXiv2023

Motion robust MR fingerprinting scan to image neonates with prenatal opioid exposure

Background: A noninvasive and sensitive imaging tool is needed to assess the fast-evolving baby brain. However, using MRI to study non-sedated babies faces roadblocks, including high scan failure rates due to subjects motion and the lack of quantitative measures for assessing potential developmental delays. This feasibility study explores whether MR Fingerprinting scans can provide motion-robust and quantitative brain tissue measurements for non-sedated infants with prenatal opioid exposure, presenting a viable alternative to clinical MR scans. Assessment: MRF image quality was compared to pediatric MRI scans using a fully crossed, multiple reader multiple case study. The quantitative T1 and T2 values were used to assess brain tissue changes between babies younger than one month and babies between one and two months. Statistical Tests: Generalized estimating equations (GEE) model was performed to test the significant difference of the T1 and T2 values from eight white matter regions of babies under one month and those are older. MRI and MRF image quality were assessed using Gwets second order auto-correlation coefficient (AC2) with its confidence levels. We used the Cochran-Mantel-Haenszel test to assess the difference in proportions between MRF and MRI for all features and stratified by the type of features. Results: In infants under one month of age, the T1 and T2 values are significantly higher (p<0.005) compared to those between one and two months. A multiple-reader and multiple-case study showed superior image quality ratings in anatomical features from the MRF images than the MRI images. Conclusions: This study suggested that the MR Fingerprinting scans offer a motion-robust and efficient method for non-sedated infants, delivering superior image quality than clinical MRI scans and additionally providing quantitative measures to assess brain development.

physics.med-ph↗
arXiv2022

Conformational change-modulated spin transport at the single-molecule level in carbon systems --Invited for the Third Carbon Special Topic

Controlling the spin transport at the single-molecule level, especially without the use of ferromagnetic contacts, becomes a focus of research in spintronics. Inspired by the progress on atomic-level molecular synthesis, through first-principles calculations, we investigate the spin-dependent electronic transport of graphene nanoflakes with side-bonded functional groups, contacted by atomic carbon chain electrodes. It is found that, by rotating the functional group, the spin polarization of the transmission at the Fermi level could be switched between completely polarized and unpolarized states. Moreover, the transition between spin-up and spin-down polarized states can also be achieved, operating as a dual-spin filter. Further analysis shows that, it is the spin-dependent shift of density of states, caused by the rotation, that triggers the shift of transmission peaks, and then results in the variation of spin polarization. Such a feature is found to be robust to the of the nanoflake and the electrode material, showing great application potential. Those findings may throw light on the development of spintronic devices.

physics.atm-clus↗
arXiv2022

Automated Design of Pulse Sequences for Magnetic Resonance Fingerprinting using Physics-Inspired Optimization

Magnetic Resonance Fingerprinting (MRF) is a method to extract quantitative tissue properties such as T1 and T2 relaxation rates from arbitrary pulse sequences using conventional magnetic resonance imaging hardware. MRF pulse sequences have thousands of tunable parameters which can be chosen to maximize precision and minimize scan time. Here we perform de novo automated design of MRF pulse sequences by applying physics-inspired optimization heuristics. Our experimental data suggests systematic errors dominate over random errors in MRF scans under clinically-relevant conditions of high undersampling. Thus, in contrast to prior optimization efforts, which focused on statistical error models, we use a cost function based on explicit first-principles simulation of systematic errors arising from Fourier undersampling and phase variation. The resulting pulse sequences display features qualitatively different from previously used MRF pulse sequences and achieve fourfold shorter scan time than prior human-designed sequences of equivalent precision in T1 and T2. Furthermore, the optimization algorithm has discovered the existence of MRF pulse sequences with intrinsic robustness against shading artifacts due to phase variation.

physics.med-ph↗
arXiv2021

A Fast MR Fingerprinting Simulator for Direct Error Estimation and Sequence Optimization

MR Fingerprinting is a novel quantitative MR technique that could simultaneously provide multiple tissue property maps. When optimizing MRF scans, modeling undersampling errors and field imperfections in cost functions will make the optimization results more practical and robust. However, this process is computationally expensive and impractical for sequence optimization algorithms when MRF signal evolutions need to be generated for each optimization iteration. Here, we introduce a fast MRF simulator to simulate aliased images from actual scan scenarios including undersampling and system imperfections, which substantially reduces computational time and allows for direct error estimation and efficient sequence optimization. By constraining the total number of tissues present in a brain phantom, MRF signals from highly undersampled scans can be simulated as the product of the spatial response functions based on sampling patterns and sequence-dependent temporal functions. During optimization, the spatial response function is independent of sequence design and does not need to be recalculated. We evaluate the performance and computational speed of the proposed approach by simulations and in vivo experiments. We also demonstrate the power of applying the simulator in MRF sequence optimization. The simulation results from the proposed method closely approximate the signals and MRF maps from in vivo scans, with 158 times shorter processing time than the conventional simulation method using Non-uniform Fourier transform. Incorporating the proposed simulator in the MRF optimization framework makes direct estimation of undersampling errors during the optimization process feasible, and provide optimized MRF sequences that are robust against undersampling factors and system inhomogeneity.

eess.IV↗
arXiv2021

Automatic Intent-Slot Induction for Dialogue Systems

Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems. Traditional methods require manually defining the DOMAIN-INTENT-SLOT schema and asking many domain experts to annotate the corresponding utterances, upon which neural models are trained. This procedure brings the challenges of information sharing hindering, out-of-schema, or data sparsity in open-domain dialogue systems. To tackle these challenges, we explore a new task of {\em automatic intent-slot induction} and propose a novel domain-independent tool. That is, we design a coarse-to-fine three-step procedure including Role-labeling, Concept-mining, And Pattern-mining (RCAP): (1) role-labeling: extracting keyphrases from users' utterances and classifying them into a quadruple of coarsely-defined intent-roles via sequence labeling; (2) concept-mining: clustering the extracted intent-role mentions and naming them into abstract fine-grained concepts; (3) pattern-mining: applying the Apriori algorithm to mine intent-role patterns and automatically inferring the intent-slot using these coarse-grained intent-role labels and fine-grained concepts. Empirical evaluations on both real-world in-domain and out-of-domain datasets show that: (1) our RCAP can generate satisfactory SLU schema and outperforms the state-of-the-art supervised learning method; (2) our RCAP can be directly applied to out-of-domain datasets and gain at least 76\% improvement of F1-score on intent detection and 41\% improvement of F1-score on slot filling; (3) our RCAP exhibits its power in generic intent-slot extractions with less manual effort, which opens pathways for schema induction on new domains and unseen intent-slot discovery for generalizable dialogue systems.

cs.AI↗
arXiv2020

SL($n$) contravariant vector valuations

All SL($n$) contravariant vector valuations on polytopes in $\mathbb R^n$ are completely classified without any additional assumptions. The facet vector is defined. It turns out to be the unique such valuation for $n\geq3$. In dimension two, the classification corresponds to the case of SL(2) covariant valuations.

math.MG↗
arXiv2020

Game of Learning Bloch Equation Simulations for MR Fingerprinting

Purpose: This work proposes a novel approach to efficiently generate MR fingerprints for MR fingerprinting (MRF) problems based on the unsupervised deep learning model generative adversarial networks (GAN). Methods: The GAN model is adopted and modified for better convergence and performance, resulting in an MRF specific model named GAN-MRF. The GAN-MRF model is trained, validated, and tested using different MRF fingerprints simulated from the Bloch equations with certain MRF sequence. The performance and robustness of the model are further tested by using in vivo data collected on a 3 Tesla scanner from a healthy volunteer together with MRF dictionaries with different sizes. T1, T2 maps are generated and compared quantitatively. Results: The validation and testing curves for the GAN-MRF model show no evidence of high bias or high variance problems. The sample MRF fingerprints generated from the trained GAN-MRF model agree well with the benchmark fingerprints simulated from the Bloch equations. The in vivo T1, T2 maps generated from the GAN-MRF fingerprints are in good agreement with those generated from the Bloch simulated fingerprints, showing good performance and robustness of the proposed GAN-MRF model. Moreover, the MRF dictionary generation time is reduced from hours to sub-second for the testing dictionary. Conclusion: The GAN-MRF model enables a fast and accurate generation of the MRF fingerprints. It significantly reduces the MRF dictionary generation process and opens the door for real-time applications and sequence optimization problems.

eess.IV↗
arXiv2018

Optimal Experiment Design for Magnetic Resonance Fingerprinting: Cramér-Rao Bound Meets Spin Dynamics

Magnetic resonance (MR) fingerprinting is a new quantitative imaging paradigm, which simultaneously acquires multiple MR tissue parameter maps in a single experiment. In this paper, we present an estimation-theoretic framework to perform experiment design for MR fingerprinting. Specifically, we describe a discrete-time dynamic system to model spin dynamics, and derive an estimation-theoretic bound, i.e., the Cramer-Rao bound (CRB), to characterize the signal-to-noise ratio (SNR) efficiency of an MR fingerprinting experiment. We then formulate an optimal experiment design problem, which determines a sequence of acquisition parameters to encode MR tissue parameters with the maximal SNR efficiency, while respecting the physical constraints and other constraints from the image decoding/reconstruction process. We evaluate the performance of the proposed approach with numerical simulations, phantom experiments, and in vivo experiments. We demonstrate that the optimized experiments substantially reduce data acquisition time and/or improve parameter estimation. For example, the optimized experiments achieve about a factor of two improvement in the accuracy of $T_2$ maps, while keeping similar or slightly better accuracy of $T_1$ maps. Finally, as a remarkable observation, we find that the sequence of optimized acquisition parameters appears to be highly structured rather than randomly/pseudo-randomly varying as is prescribed in the conventional MR fingerprinting experiments.

eess.SP↗
arXiv2018

Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN

Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications. Although a number of generative models have been developed to tackle this problem, there is still much room for further improvement.In paticular, the current solutions usually ignore the perceptual information of images, which we argue that it benefits the output of a high-quality image while preserving the identity information, especially in facial attributes learning area.To this end, we propose to train GAN iteratively via regularizing the min-max process with an integrated loss, which includes not only the per-pixel loss but also the perceptual loss. In contrast to the existing methods only deal with either image generation or transformation, our proposed iterative architecture can achieve both of them. Experiments on the multi-label facial dataset CelebA demonstrate that the proposed model has excellent performance on recognizing multiple attributes, generating a high-quality image, and transforming image with controllable attributes.

cs.CV↗
arXiv2018

Laplace transforms and valuations

It is proved that the classical Laplace transform is a continuous valuation which is positively GL$(n)$ covariant and logarithmic translation covariant. Conversely, these properties turn out to be sufficient to characterize this transform.

math.MG↗
arXiv2014

Asymmetric anisotropic fractional Sobolev norms

Bourgain, Brezis & Mironescu showed that (with suitable scaling) the fractional Sobolev $s$-seminorm of a function $f\in W^{1,p}(\mathbb{R}^n)$ converges to the Sobolev seminorm of $f$ as $s\rightarrow1^-$. Ludwig introduced the anisotropic fractional Sobolev $s$-seminorms of $f$ defined by a norm on $\mathbb{R}^n$ with unit ball $K$, and showed that they converge to the anisotropic Sobolev seminorm of $f$ defined by the norm whose unit ball is the polar $L_p$ moment body of $K$, as $s\rightarrow1^-$. The asymmetric anisotropic $s$-seminorms are shown to converge to the anisotropic Sobolev seminorm of $f$ defined by the Minkowski functional of the polar asymmetric $L_p$ moment body of $K$.

math.FA↗
arXiv2013

Twins:Device-free Object Tracking using Passive Tags

Without requiring objects to carry any transceiver, device-free based object tracking provides a promising solution for many localization and tracking systems to monitor non-cooperative objects such as intruders. However, existing device-free solutions mainly use sensors and active RFID tags, which are much more expensive compared to passive tags. In this paper, we propose a novel motion detection and tracking method using passive RFID tags, named Twins. The method leverages a newly observed phenomenon called critical state caused by interference among passive tags. We contribute to both theory and practice of such phenomenon by presenting a new interference model that perfectly explains this phenomenon and using extensive experiments to validate it. We design a practical Twins based intrusion detection scheme and implement a real prototype with commercial off-the-shelf reader and tags. The results show that Twins is effective in detecting the moving object, with low location error of 0.75m in average.

cs.NI↗
arXiv2011

Stability and slicing inequalities for intersection bodies

We prove a generalization of the hyperplane inequality for intersection bodies, where volume is replaced by an arbitrary measure $μ$ with even continuous density and sections are of arbitrary dimension $n-k,\ 1\le k 0,\ 1\le k <n.$ Suppose that $K$ and $L$ are origin-symmetric star bodies in $\R^n,$ and $K$ is a generalized $k$-intersection body. If for every $(n-k)$-dimensional subspace $H$ of $\R^n$ $$μ(K\cap H)\leq μ(L\cap H)+\e,$$ then $$μ(K)\leq μ(L) +\frac{n}{n-k}c_{n,k} \vol_n(K)^{k/n}\e.$$

math.MG↗