arXiv subjects

Ling Liu

Publications and source records attributed to Ling Liu.

At least 73 records · Page 4Linked to original sources

arXiv2024

Deep Learning Service for Efficient Data Distribution Aware Sorting

In this paper, we present a neural network-enabled data distribution aware sorting method, coined as NN-sort. Our approach explores the potential of developing deep learning techniques to speed up large-scale sort operations, enabling data distribution aware sorting as a deep learning service. Compared to traditional pairwise comparison-based sorting algorithms, which sort data elements by performing pairwise operations, NN-sort leverages the neural network model to learn the data distribution and uses it to map large-scale data elements into ordered ones. Our experiments demonstrate the significant advantage of using NN-sort. Measurements on both synthetic and real-world datasets show that NN-sort yields 2.18x to 10x performance improvement over traditional sorting algorithms.

cs.DS↗

arXiv2024

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack

The new paradigm of finetuning-as-a-service introduces a new attack surface for Large Language Models (LLMs): a few harmful data uploaded by users can easily trick the finetuning to produce an alignment-broken model. We conduct an empirical analysis and uncover a \textit{harmful embedding drift} phenomenon, showing a probable cause of the alignment-broken effect. Inspired by our findings, we propose Vaccine, a perturbation-aware alignment technique to mitigate the security risk of users finetuning. The core idea of Vaccine is to produce invariant hidden embeddings by progressively adding crafted perturbation to them in the alignment phase. This enables the embeddings to withstand harmful perturbation from un-sanitized user data in the finetuning phase. Our results on open source mainstream LLMs (e.g., Llama2, Opt, Vicuna) demonstrate that Vaccine can boost the robustness of alignment against harmful prompts induced embedding drift while reserving reasoning ability towards benign prompts. Our code is available at \url{https://github.com/git-disl/Vaccine}.

cs.LG↗

arXiv2024

Constant-Potential Machine Learning Molecular Dynamics Simulations Reveal Potential-Regulated Cu Cluster Formation on MoS$_{2}$

Electrochemical processes play a crucial role in energy storage and conversion systems, yet their computational modeling remains a significant challenge. Accurately incorporating the effects of electric potential has been a central focus in theoretical electrochemistry. Although constant-potential ab initio molecular dynamics (CP-AIMD) has provided valuable insights, it is limited by its substantial computational demands. Here, we introduce the Explicit Electric Potential Machine Learning Force Field (EEP-MLFF) model. Our model integrates the electric potential as an explicit input parameter along with the atom-centered descriptors in the atomic neural network. This approach enables the evaluation of nuclear forces under arbitrary electric potentials, thus facilitating molecular dynamics simulations at a specific potential. By applying the proposed machine learning method to the Cu/1T$^{\prime}$-MoS$_{2}$ system, molecular dynamics simulations reveal that the potential-modulated Cu atom migration and aggregation lead to the formation of small steric Cu clusters (Single Clusters, SCs) at potentials below -0.1 V. The morphological transformations of adsorbed Cu atoms are elucidated through electronic structure analyses, which demonstrates that both Cu-S and Cu-Cu bonding can be effectively tuned by the applied electric potential. Our findings present an opportunity for the convenient manufacture of single metal cluster catalysts through potential modulation. Moreover, this theoretical framework facilitates the exploration of potential-regulated processes and helps investigate the mechanisms of electrochemical reactions.

physics.chem-ph↗

arXiv2024

Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack

Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-broken by fine-tuning on a dataset mixed with harmful data. First time in the literature, we show that the jail-broken effect can be mitigated by separating states in the finetuning stage to optimize the alignment and user datasets. Unfortunately, our subsequent study shows that this simple Bi-State Optimization (BSO) solution experiences convergence instability when steps invested in its alignment state is too small, leading to downgraded alignment performance. By statistical analysis, we show that the \textit{excess drift} towards consensus could be a probable reason for the instability. To remedy this issue, we propose \textbf{L}azy(\textbf{i}) \textbf{s}afety \textbf{a}lignment (\textbf{Lisa}), which introduces a proximal term to constraint the drift of each state. Theoretically, the benefit of the proximal term is supported by the convergence analysis, wherein we show that a sufficient large proximal factor is necessary to guarantee Lisa's convergence. Empirically, our results on four downstream finetuning tasks show that Lisa with a proximal term can significantly increase alignment performance while maintaining the LLM's accuracy on the user tasks. Code is available at \url{https://github.com/git-disl/Lisa}.

cs.LG↗

arXiv2024

The Brain-Inspired Cooperative Shared Control Framework for Brain-Machine Interface

In brain-machine interface (BMI) applications, a key challenge is the low information content and high noise level in neural signals, severely affecting stable robotic control. To address this challenge, we proposes a cooperative shared control framework based on brain-inspired intelligence, where control signals are decoded from neural activity, and the robot handles the fine control. This allows for a combination of flexible and adaptive interaction control between the robot and the brain, making intricate human-robot collaboration feasible. The proposed framework utilizes spiking neural networks (SNNs) for controlling robotic arm and wheel, including speed and steering. While full integration of the system remains a future goal, individual modules for robotic arm control, object tracking, and map generation have been successfully implemented. The framework is expected to significantly enhance the performance of BMI. In practical settings, the BMI with cooperative shared control, utilizing a brain-inspired algorithm, will greatly enhance the potential for clinical applications.

cs.RO↗

arXiv2024

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this paper, and show that the challenge arises from the representation gap that emerges when introducing vision modality to VLMs. In particular, we show that the representations of multi-modal inputs shift away from that of text-only inputs which represent the distribution that the LLM backbone is optimized for. At the same time, the safety alignment capabilities, initially developed within the textual embedding space, do not successfully transfer to this new multi-modal representation space. To reduce safety alignment degradation, we introduce Cross-Modality Representation Manipulation (CMRM), an inference time representation intervention method for recovering the safety alignment ability that is inherent in the LLM backbone of VLMs, while simultaneously preserving the functional capabilities of VLMs. The empirical results show that our framework significantly recovers the alignment ability that is inherited from the LLM backbone with minimal impact on the fluency and linguistic capabilities of pre-trained VLMs even without additional training. Specifically, the unsafe rate of LLaVA-7B on multi-modal input can be reduced from 61.53% to as low as 3.15% with only inference-time intervention. WARNING: This paper contains examples of toxic or harmful language.

cs.CL↗

arXiv2024

LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity

Combining large language models during training or at inference time has shown substantial performance gain over component LLMs. This paper presents LLM-TOPLA, a diversity-optimized LLM ensemble method with three unique properties: (i) We introduce the focal diversity metric to capture the diversity-performance correlation among component LLMs of an ensemble. (ii) We develop a diversity-optimized ensemble pruning algorithm to select the top-k sub-ensembles from a pool of $N$ base LLMs. Our pruning method recommends top-performing LLM subensembles of size $S$, often much smaller than $N$. (iii) We generate new output for each prompt query by utilizing a learn-to-ensemble approach, which learns to detect and resolve the output inconsistency among all component LLMs of an ensemble. Extensive evaluation on four different benchmarks shows good performance gain over the best LLM ensemble methods: (i) In constrained solution set problems, LLM-TOPLA outperforms the best-performing ensemble (Mixtral) by 2.2\% in accuracy on MMLU and the best-performing LLM ensemble (MoreAgent) on GSM8k by 2.1\%. (ii) In generative tasks, LLM-TOPLA outperforms the top-2 performers (Llama70b/Mixtral) on SearchQA by $3.9\mathrm{x}$ in F1, and on XSum by more than $38$ in ROUGE-1. Our code and dataset, which contains outputs of 8 modern LLMs on 4 benchmarks is available at https://github.com/git-disl/llm-topla

cs.CL↗

arXiv2024

Data Poisoning and Leakage Analysis in Federated Learning

Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em training data poisoning}. We first investigate training data privacy threat and present our observations on when and how training data may be leaked during the course of federated training. One promising defense strategy is to perturb the raw gradient update by adding some controlled randomized noise prior to sharing during each round of federated learning. We discuss the importance of determining the proper amount of randomized noise and the proper location to add such noise for effective mitigation of gradient leakage threats against training data privacy. Then we will review and compare different training data poisoning threats and analyze why and when such data poisoning induced model Trojan attacks may lead to detrimental damage on the performance of the global model. We will categorize and compare representative poisoning attacks and the effectiveness of their mitigation techniques, delivering an in-depth understanding of the negative impact of data poisoning. Finally, we demonstrate the potential of dynamic model perturbation in simultaneously ensuring privacy protection, poisoning resilience, and model performance. The chapter concludes with a discussion on additional risk factors in federated learning, including the negative impact of skewness, data and algorithmic biases, as well as misinformation in training data. Powered by empirical evidence, our analytical study offers some transformative insights into effective privacy protection and security assurance strategies in attack-resilient federated learning.

cs.LG↗

arXiv2024

ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models

In this position paper, we argue that human evaluation of generative large language models (LLMs) should be a multidisciplinary undertaking that draws upon insights from disciplines such as user experience research and human behavioral psychology to ensure that the experimental design and results are reliable. The conclusions from these evaluations, thus, must consider factors such as usability, aesthetics, and cognitive biases. We highlight how cognitive biases can conflate fluent information and truthfulness, and how cognitive uncertainty affects the reliability of rating scores such as Likert. Furthermore, the evaluation should differentiate the capabilities and weaknesses of increasingly powerful large language models -- which requires effective test sets. The scalability of human evaluation is also crucial to wider adoption. Hence, to design an effective human evaluation system in the age of generative NLP, we propose the ConSiDERS-The-Human evaluation framework consisting of 6 pillars -- Consistency, Scoring Criteria, Differentiating, User Experience, Responsible, and Scalability.

cs.CL↗

arXiv2024

Personalized Privacy Protection Mask Against Unauthorized Facial Recognition

Face recognition (FR) can be abused for privacy intrusion. Governments, private companies, or even individual attackers can collect facial images by web scraping to build an FR system identifying human faces without their consent. This paper introduces Chameleon, which learns to generate a user-centric personalized privacy protection mask, coined as P3-Mask, to protect facial images against unauthorized FR with three salient features. First, we use a cross-image optimization to generate one P3-Mask for each user instead of tailoring facial perturbation for each facial image of a user. It enables efficient and instant protection even for users with limited computing resources. Second, we incorporate a perceptibility optimization to preserve the visual quality of the protected facial images. Third, we strengthen the robustness of P3-Mask against unknown FR models by integrating focal diversity-optimized ensemble learning into the mask generation process. Extensive experiments on two benchmark datasets show that Chameleon outperforms three state-of-the-art methods with instant protection and minimal degradation of image quality. Furthermore, Chameleon enables cost-effective FR authorization using the P3-Mask as a personalized de-obfuscation key, and it demonstrates high resilience against adaptive adversaries.

cs.CV↗

arXiv2024

Convolution quadratures based on block generalized Adams methods

This paper studies a family of convolution quadratures, a numerical technique for efficient evaluation of convolution integrals. We employ the block generalized Adams method to discretize the underlying initial value problem, departing from the well-established approaches that rely on linear multistep formulas or Runge-Kutta methods. The convergence order of the proposed convolution quadrature can be dynamically controlled without requiring grid point adjustments, enhancing exibility. Through strategic selection of the local interpolation polynomial and block size, the method achieves high-order convergence for calculation of convolution integrals with hyperbolic kernels. We provide a rigorous convergence analysis for the proposed convolution quadrature and numerically validate our theoretical findings for various convolution integrals.

math.NA↗

arXiv2024

Embedded Silicon-Organic Integrated Neuromorphic System

The development of artificial intelligence (AI) and robotics are both based on the tenet of "science and technology are people-oriented", and both need to achieve efficient communication with the human brain. Based on multi-disciplinary research in systems neuroscience, computer architecture, and functional organic materials, we proposed the concept of using AI to simulate the operating principles and materials of the brain in hardware to develop brain-inspired intelligence technology, and realized the preparation of neuromorphic computing devices and basic materials. We simulated neurons and neural networks in terms of material and morphology, using a variety of organic polymers as the base materials for neuroelectronic devices, for building neural interfaces as well as organic neural devices and silicon neural computational modules. We assemble organic artificial synapses with simulated neurons from silicon-based Field-Programmable Gate Array (FPGA) into organic artificial neurons, the basic components of neural networks, and later construct biological neural network models based on the interpreted neural circuits. Finally, we also discuss how to further build neuromorphic devices based on these organic artificial neurons, which have both a neural interface friendly to nervous tissue and interact with information from real biological neural networks.

q-bio.NC↗

arXiv2024

Short Regular Girth-8 QC-LDPC Codes From Exponent Matrices with Vertical Symmetry

To address the challenge of constructing short girth-8 quasi-cyclic (QC) low-density parity-check (LDPC) codes, a novel construction framework based on vertical symmetry (VS) is proposed. Basic properties of the VS structure are presented. With the aid of these properties, existing explicit constructions for column weights from three to five which can be transformed into the VS structure are sorted out. Then two novel explicit constructions with the VS structure which guarantee short codes are presented for column weights of three and six. Moreover, an efficient search-based method is also proposed to find short codes with the VS structure. Compared with the state-of-the-art benchmarks, both the explicit constructions and the search-based method presented in this paper can provide shorter codes for most cases. Simulation results show that the new shorter codes can perform almost the same as or better than the longer existing counterparts. Thus, the new shorter codes can fit better with the low-latency requirement for modern communication systems.

cs.IT↗

arXiv2024

XMiner: Efficient Directed Subgraph Matching with Pattern Reduction

Graph pattern matching, one of the fundamental graph mining problems, aims to extract structural patterns of interest from an input graph. The state-of-the-art graph matching algorithms and systems are mainly designed for undirected graphs. Directed graph matching is more complex than undirected graph matching because the edge direction must be taken into account before the exploration of each directed edge. Thus, the technologies (e.g. storage, exploiting symmetry for graph matching) for undirected graph matching may not be fully applicable to directed graphs. For example, the redundancy implied in directed graph pattern can not be detected using the symmetry breaking for undirected pattern graph. Here, we present XMiner for efficient directed graph pattern matching whose core idea is 'pattern reduction'. It first analyzes the relationship between constraints implied in a pattern digraph. Then it reduces the pattern graph into a simplified form by finding a minimum constraint cover. Finally, XMiner generates an execution plan and follows it to extract matchings of the pattern graph. So, XMiner works on simplified pattern graph and avoids much data access and redundant computation throughout the matching process. Our experimental results show that XMiner outperforms state-of the-art stand-alone graph matching systems, and scales to complex graph pattern matching tasks on larger graph.

cs.DB↗

arXiv2024

Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruning

This paper presents FusionShot, a focal diversity optimized few-shot ensemble learning approach for boosting the robustness and generalization performance of pre-trained few-shot models. The paper makes three original contributions. First, we explore the unique characteristics of few-shot learning to ensemble multiple few-shot (FS) models by creating three alternative fusion channels. Second, we introduce the concept of focal error diversity to learn the most efficient ensemble teaming strategy, rather than assuming that an ensemble of a larger number of base models will outperform those sub-ensembles of smaller size. We develop a focal-diversity ensemble pruning method to effectively prune out the candidate ensembles with low ensemble error diversity and recommend top-$K$ FS ensembles with the highest focal error diversity. Finally, we capture the complex non-linear patterns of ensemble few-shot predictions by designing the learn-to-combine algorithm, which can learn the diverse weight assignments for robust ensemble fusion over different member models. Extensive experiments on representative few-shot benchmarks show that the top-K ensembles recommended by FusionShot can outperform the representative SOTA few-shot models on novel tasks (different distributions and unknown at training), and can prevail over existing few-shot learners in both cross-domain settings and adversarial settings. For reproducibility purposes, FusionShot trained models, results, and code are made available at https://github.com/sftekin/fusionshot

cs.CV↗

arXiv2024

PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models

We introduce PokeLLMon, the first LLM-embodied agent that achieves human-parity performance in tactical battle games, as demonstrated in Pokemon battles. The design of PokeLLMon incorporates three key strategies: (i) In-context reinforcement learning that instantly consumes text-based feedback derived from battles to iteratively refine the policy; (ii) Knowledge-augmented generation that retrieves external knowledge to counteract hallucination and enables the agent to act timely and properly; (iii) Consistent action generation to mitigate the panic switching phenomenon when the agent faces a powerful opponent and wants to elude the battle. We show that online battles against human demonstrates PokeLLMon's human-like battle strategies and just-in-time decision making, achieving 49% of win rate in the Ladder competitions and 56% of win rate in the invited battles. Our implementation and playable battle logs are available at: https://github.com/git-disl/PokeLLMon.

cs.AI↗

arXiv2024

TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding

Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and synthesizing hand-object manipulation are mostly limited to handling a single hand and object due to the lack of data support. To address this, we construct TACO, an extensive bimanual hand-object-interaction dataset spanning a large variety of tool-action-object compositions for daily human activities. TACO contains 2.5K motion sequences paired with third-person and egocentric views, precise hand-object 3D meshes, and action labels. To rapidly expand the data scale, we present a fully automatic data acquisition pipeline combining multi-view sensing with an optical motion capture system. With the vast research fields provided by TACO, we benchmark three generalizable hand-object-interaction tasks: compositional action recognition, generalizable hand-object motion forecasting, and cooperative grasp synthesis. Extensive experiments reveal new insights, challenges, and opportunities for advancing the studies of generalizable hand-object motion analysis and synthesis. Our data and code are available at https://taco2024.github.io.

cs.CV↗

arXiv2024

Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance

Emerging Distributed AI systems are revolutionizing big data computing and data processing capabilities with growing economic and societal impact. However, recent studies have identified new attack surfaces and risks caused by security, privacy, and fairness issues in AI systems. In this paper, we review representative techniques, algorithms, and theoretical foundations for trustworthy distributed AI through robustness guarantee, privacy protection, and fairness awareness in distributed learning. We first provide a brief overview of alternative architectures for distributed learning, discuss inherent vulnerabilities for security, privacy, and fairness of AI algorithms in distributed learning, and analyze why these problems are present in distributed learning regardless of specific architectures. Then we provide a unique taxonomy of countermeasures for trustworthy distributed AI, covering (1) robustness to evasion attacks and irregular queries at inference, and robustness to poisoning attacks, Byzantine attacks, and irregular data distribution during training; (2) privacy protection during distributed learning and model inference at deployment; and (3) AI fairness and governance with respect to both data and models. We conclude with a discussion on open challenges and future research directions toward trustworthy distributed AI, such as the need for trustworthy AI policy guidelines, the AI responsibility-utility co-design, and incentives and compliance.

cs.LG↗