arXiv subjects

Xinfeng Li

Publications and source records attributed to Xinfeng Li.

At least 73 records · Page 4Linked to original sources

arXiv2025

BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models

Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability to generate high-quality images, but also raise concerns about social biases, particularly in human image generation. Sociological research has established systematic classifications of bias. Yet, existing studies on bias in T2I models largely conflate different types of bias, impeding methodological progress. In this paper, we introduce BIGbench, a unified benchmark for Biases of Image Generation, featuring a carefully designed dataset. Unlike existing benchmarks, BIGbench classifies and evaluates biases across four dimensions to enable a more granular evaluation and deeper analysis. Furthermore, BIGbench applies advanced multi-modal large language models to achieve fully automated and highly accurate evaluations. We apply BIGbench to evaluate eight representative T2I models and three debiasing methods. Our human evaluation results by trained evaluators from different races underscore BIGbench's effectiveness in aligning images and identifying various biases. Moreover, our study also reveals new research directions about biases with insightful analysis of our results. Our work is openly accessible at https://github.com/BIGbench2024/BIGbench2024/.

cs.CV↗

arXiv2025

Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models

Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has explored robust text prompts through adversarial training, achieving some improvement in both robustness and generalization. However, they primarily rely on singlegradient direction perturbations (e.g., PGD) to generate AEs, which lack diversity, resulting in limited improvement in adversarial robustness. To address these limitations, we propose an evolution-based region adversarial prompt tuning method called ER-APT, which combines gradient methods with genetic evolution to generate more diverse and challenging AEs. In each training iteration, we first generate AEs using traditional gradient-based methods. Subsequently, a genetic evolution mechanism incorporating selection, mutation, and crossover is applied to optimize the AEs, ensuring a broader and more aggressive perturbation distribution.The final evolved AEs are used for prompt tuning, achieving region-based adversarial optimization instead of conventional single-point adversarial prompt tuning. We also propose a dynamic loss weighting method to adjust prompt learning efficiency for accuracy and robustness. Experimental evaluations on various benchmark datasets demonstrate the superiority of our proposed method, outperforming stateof-the-art APT methods. The code is released at https://github.com/jiaxiaojunQAQ/ER-APT.

cs.CV↗

arXiv2025

MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation

Large Language Models (LLMs) have made significant progress in various fields. However, challenges remain in Multi-Disciplinary Team (MDT) medical consultations. Current research enhances reasoning through role assignment, task decomposition, and accumulation of medical experience. Multi-role collaboration in MDT consultations often results in excessively long dialogue histories. This increases the model's cognitive burden and degrades both efficiency and accuracy. Some methods only store treatment histories. They do not extract effective experience or reflect on errors. This limits knowledge generalization and system evolution. We propose a multi-agent MDT medical consultation framework based on LLMs to address these issues. Our framework uses consensus aggregation and a residual discussion structure for multi-round consultations. It also employs a Correct Answer Knowledge Base (CorrectKB) and a Chain-of-Thought Knowledge Base (ChainKB) to accumulate consultation experience. These mechanisms enable the framework to evolve and continually improve diagnosis rationality and accuracy. Experimental results on the MedQA and PubMedQA datasets demonstrate that our framework achieves accuracies of 90.1% and 83.9%, respectively, and that the constructed knowledge bases generalize effectively across test sets from both datasets.

cs.AI↗

arXiv2025

A Survey on Trustworthy LLM Agents: Threats and Countermeasures

With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems. This evolution stems from empowering LLMs with additional modules such as memory, tools, environment, and even other agents. However, this advancement has also introduced more complex issues of trustworthiness, which previous research focused solely on LLMs could not cover. In this survey, we propose the TrustAgent framework, a comprehensive study on the trustworthiness of agents, characterized by modular taxonomy, multi-dimensional connotations, and technical implementation. By thoroughly investigating and summarizing newly emerged attacks, defenses, and evaluation methods for agents and MAS, we extend the concept of Trustworthy LLM to the emerging paradigm of Trustworthy Agent. In TrustAgent, we begin by deconstructing and introducing various components of the Agent and MAS. Then, we categorize their trustworthiness into intrinsic (brain, memory, and tool) and extrinsic (user, agent, and environment) aspects. Subsequently, we delineate the multifaceted meanings of trustworthiness and elaborate on the implementation techniques of existing research related to these internal and external modules. Finally, we present our insights and outlook on this domain, aiming to provide guidance for future endeavors.

cs.MA↗

arXiv2025

Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation

The rise of deep learning models in the digital era has raised substantial concerns regarding the generation of Not-Safe-for-Work (NSFW) content. Existing defense methods primarily involve model fine-tuning and post-hoc content moderation. Nevertheless, these approaches largely lack scalability in eliminating harmful content, degrade the quality of benign image generation, or incur high inference costs. To address these challenges, we propose an innovative framework named \textit{Buster}, which injects backdoors into the text encoder to prevent NSFW content generation. Buster leverages deep semantic information rather than explicit prompts as triggers, redirecting NSFW prompts towards targeted benign prompts. Additionally, Buster employs energy-based training data generation through Langevin dynamics for adversarial knowledge augmentation, thereby ensuring robustness in harmful concept definition. This approach demonstrates exceptional resilience and scalability in mitigating NSFW content. Particularly, Buster fine-tunes the text encoder of Text-to-Image models within merely five minutes, showcasing its efficiency. Our extensive experiments denote that Buster outperforms nine state-of-the-art baselines, achieving a superior NSFW content removal rate of at least 91.2\% while preserving the quality of harmless images.

cs.CV↗

arXiv2024

SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models

Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexually explicit scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block sexually explicit content (e.g., naked) but may still be vulnerable to adversarial prompts -- inputs that appear innocent but are ill-intended. In this paper, we present SafeGen, a framework to mitigate sexual content generation by text-to-image models in a text-agnostic manner. The key idea is to eliminate explicit visual representations from the model regardless of the text input. In this way, the text-to-image model is resistant to adversarial prompts since such unsafe visual representations are obstructed from within. Extensive experiments conducted on four datasets and large-scale user studies demonstrate SafeGen's effectiveness in mitigating sexually explicit content generation while preserving the high-fidelity of benign images. SafeGen outperforms eight state-of-the-art baseline methods and achieves 99.4% sexual content removal performance. Furthermore, our constructed benchmark of adversarial prompts provides a basis for future development and evaluation of anti-NSFW-generation methods.

cs.CV↗

arXiv2024

SafeEar: Content Privacy-Preserving Audio Deepfake Detection

Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals. Existing countermeasures largely focus on determining the genuineness of speech based on complete original audio recordings, which however often contain private content. This oversight may refrain deepfake detection from many applications, particularly in scenarios involving sensitive information like business secrets. In this paper, we propose SafeEar, a novel framework that aims to detect deepfake audios without relying on accessing the speech content within. Our key idea is to devise a neural audio codec into a novel decoupling model that well separates the semantic and acoustic information from audio samples, and only use the acoustic information (e.g., prosody and timbre) for deepfake detection. In this way, no semantic content will be exposed to the detector. To overcome the challenge of identifying diverse deepfake audio without semantic clues, we enhance our deepfake detector with real-world codec augmentation. Extensive experiments conducted on four benchmark datasets demonstrate SafeEar's effectiveness in detecting various deepfake techniques with an equal error rate (EER) down to 2.02%. Simultaneously, it shields five-language speech content from being deciphered by both machine and human auditory analysis, demonstrated by word error rates (WERs) all above 93.93% and our user study. Furthermore, our benchmark constructed for anti-deepfake and anti-content recovery evaluation helps provide a basis for future research in the realms of audio privacy preservation and deepfake detection.

cs.CR↗

arXiv2024

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge. Current research addresses this bottleneck by equipping LLMs with external knowledge, a technique known as Retrieval Augmented Generation (RAG). However, two key issues constrained the development of RAG. First, there is a growing lack of comprehensive and fair comparisons between novel RAG algorithms. Second, open-source tools such as LlamaIndex and LangChain employ high-level abstractions, which results in a lack of transparency and limits the ability to develop novel algorithms and evaluation metrics. To close this gap, we introduce RAGLAB, a modular and research-oriented open-source library. RAGLAB reproduces 6 existing algorithms and provides a comprehensive ecosystem for investigating RAG algorithms. Leveraging RAGLAB, we conduct a fair comparison of 6 RAG algorithms across 10 benchmarks. With RAGLAB, researchers can efficiently compare the performance of various algorithms and develop novel algorithms.

cs.CL↗

arXiv2024

Legilimens: Practical and Unified Content Moderation for Large Language Model Services

Given the societal impact of unsafe content generated by large language models (LLMs), ensuring that LLM services comply with safety standards is a crucial concern for LLM service providers. Common content moderation methods are limited by an effectiveness-and-efficiency dilemma, where simple models are fragile while sophisticated models consume excessive computational resources. In this paper, we reveal for the first time that effective and efficient content moderation can be achieved by extracting conceptual features from chat-oriented LLMs, despite their initial fine-tuning for conversation rather than content moderation. We propose a practical and unified content moderation framework for LLM services, named Legilimens, which features both effectiveness and efficiency. Our red-team model-based data augmentation enhances the robustness of Legilimens against state-of-the-art jailbreaking. Additionally, we develop a framework to theoretically analyze the cost-effectiveness of Legilimens compared to other methods. We have conducted extensive experiments on five host LLMs, seventeen datasets, and nine jailbreaking methods to verify the effectiveness, efficiency, and robustness of Legilimens against normal and adaptive adversaries. A comparison of Legilimens with both commercial and academic baselines demonstrates the superior performance of Legilimens. Furthermore, we confirm that Legilimens can be applied to few-shot scenarios and extended to multi-label classification tasks.

cs.CL↗

arXiv2024

RACONTEUR: A Knowledgeable, Insightful, and Portable LLM-Powered Shell Command Explainer

Malicious shell commands are linchpins to many cyber-attacks, but may not be easy to understand by security analysts due to complicated and often disguised code structures. Advances in large language models (LLMs) have unlocked the possibility of generating understandable explanations for shell commands. However, existing general-purpose LLMs suffer from a lack of expert knowledge and a tendency to hallucinate in the task of shell command explanation. In this paper, we present Raconteur, a knowledgeable, expressive and portable shell command explainer powered by LLM. Raconteur is infused with professional knowledge to provide comprehensive explanations on shell commands, including not only what the command does (i.e., behavior) but also why the command does it (i.e., purpose). To shed light on the high-level intent of the command, we also translate the natural-language-based explanation into standard technique & tactic defined by MITRE ATT&CK, the worldwide knowledge base of cybersecurity. To enable Raconteur to explain unseen private commands, we further develop a documentation retriever to obtain relevant information from complementary documentations to assist the explanation process. We have created a large-scale dataset for training and conducted extensive experiments to evaluate the capability of Raconteur in shell command explanation. The experiments verify that Raconteur is able to provide high-quality explanations and in-depth insight of the intent of the command.

cs.CR↗

arXiv2024

Diffuse X-ray Explorer: a high-resolution X-ray spectroscopic sky surveyor on the China Space Station

DIffuse X-ray Explorer (DIXE) is a proposed high-resolution X-ray spectroscopic sky surveyor on the China Space Station (CSS). DIXE will focus on studying hot baryons in the Milky Way. Galactic hot baryons like the X-ray emitting Milky Way halo and eROSITA bubbles are best observed in the sky survey mode with a large field of view. DIXE will take advantage of the orbital motion of the CSS to scan a large fraction of the sky. High-resolution X-ray spectroscopy, enabled by superconducting microcalorimeters based on the transition-edge sensor (TES) technology, will probe the physical properties (e.g., temperature, density, elemental abundances, kinematics) of the Galactic hot baryons. This will complement the high-resolution imaging data obtained with the eROSITA mission. Here we present the preliminary design of DIXE. The payload consists mainly of a detector assembly and a cryogenic cooling system. The key components of the detector assembly are a microcalorimeter array and frequency-domain multiplexing readout electronics. To provide a working temperature for the detector assembly, the cooling system consists of an adiabatic demagnetization refrigerator and a mechanical cryocooler system.

astro-ph.IM↗

arXiv2023

Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound

Automatic Speaker Recognition Systems (SRSs) have been widely used in voice applications for personal identification and access control. A typical SRS consists of three stages, i.e., training, enrollment, and recognition. Previous work has revealed that SRSs can be bypassed by backdoor attacks at the training stage or by adversarial example attacks at the recognition stage. In this paper, we propose Tuner, a new type of backdoor attack against the enrollment stage of SRS via adversarial ultrasound modulation, which is inaudible, synchronization-free, content-independent, and black-box. Our key idea is to first inject the backdoor into the SRS with modulated ultrasound when a legitimate user initiates the enrollment, and afterward, the polluted SRS will grant access to both the legitimate user and the adversary with high confidence. Our attack faces a major challenge of unpredictable user articulation at the enrollment stage. To overcome this challenge, we generate the ultrasonic backdoor by augmenting the optimization process with random speech content, vocalizing time, and volume of the user. Furthermore, to achieve real-world robustness, we improve the ultrasonic signal over traditional methods using sparse frequency points, pre-compensation, and single-sideband (SSB) modulation. We extensively evaluate Tuner on two common datasets and seven representative SRS models, as well as its robustness against seven kinds of defenses. Results show that our attack can successfully bypass speaker recognition systems while remaining effective to various speakers, speech content, etc. To mitigate this newly discovered threat, we also provide discussions on potential countermeasures, limitations, and future works of this new threat.

cs.SD↗

arXiv2023

Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time

Automatic speech recognition (ASR) systems have been shown to be vulnerable to adversarial examples (AEs). Recent success all assumes that users will not notice or disrupt the attack process despite the existence of music/noise-like sounds and spontaneous responses from voice assistants. Nonetheless, in practical user-present scenarios, user awareness may nullify existing attack attempts that launch unexpected sounds or ASR usage. In this paper, we seek to bridge the gap in existing research and extend the attack to user-present scenarios. We propose VRIFLE, an inaudible adversarial perturbation (IAP) attack via ultrasound delivery that can manipulate ASRs as a user speaks. The inherent differences between audible sounds and ultrasounds make IAP delivery face unprecedented challenges such as distortion, noise, and instability. In this regard, we design a novel ultrasonic transformation model to enhance the crafted perturbation to be physically effective and even survive long-distance delivery. We further enable VRIFLE's robustness by adopting a series of augmentation on user and real-world variations during the generation process. In this way, VRIFLE features an effective real-time manipulation of the ASR output from different distances and under any speech of users, with an alter-and-mute strategy that suppresses the impact of user disruption. Our extensive experiments in both digital and physical worlds verify VRIFLE's effectiveness under various configurations, robustness against six kinds of defenses, and universality in a targeted manner. We also show that VRIFLE can be delivered with a portable attack device and even everyday-life loudspeakers.

cs.CR↗

arXiv2023

Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition

Transformer-based models have recently made significant achievements in the application of end-to-end (E2E) automatic speech recognition (ASR). It is possible to deploy the E2E ASR system on smart devices with the help of Transformer-based models. While these models still have the disadvantage of requiring a large number of model parameters. To overcome the drawback of universal Transformer models for the application of ASR on edge devices, we propose a solution that can reuse the block in Transformer models for the occasion of the small footprint ASR system, which meets the objective of accommodating resource limitations without compromising recognition accuracy. Specifically, we design a novel block-reusing strategy for speech Transformer (BRST) to enhance the effectiveness of parameters and propose an adapter module (ADM) that can produce a compact and adaptable model with only a few additional trainable parameters accompanying each reusing block. We conducted an experiment with the proposed method on the public AISHELL-1 corpus, and the results show that the proposed approach achieves the character error rate (CER) of 9.3%/6.63% with only 7.6M/8.3M parameters without and with the ADM, respectively. In addition, we also make a deeper analysis to show the effect of ADM in the general block-reusing method.

cs.SD↗

arXiv2020

Mapping Diffuse Emission in Lyman UV band

The CAFE (Census of warm-hot intergalactic medium, Accretion, and Feedback Explorer) and LyRIC (Lyman UV Radiation from Interstellar medium and Circum-galactic medium) have been proposed to the space agencies in China respectively. CAFE was first proposed in 2015 as a joint scientific CAS-ESA small space mission. LyRIC was proposed in 2019 as an independent external payload operating on the Chinese Space Station. Both missions are dedicated to mapping the Lyman UV emission (ionized oxygen (O VI) resonance lines at 103.2 and 103.8 nm, and Lyman series) for the diffuse sources in our Galaxy and the circum-galactic mediums of the nearby galaxies. We present the primary science objectives, mission concepts, the enabling technologies, as well as the current status.

astro-ph.IM↗

arXiv2020

Theoretical study of the pressure-induced structure, phase transition, mechanical and electronic properties in the V-N system

Stable compounds in the V-N system are systematically searched and four new high-pressure phases are found, including C2/m-V$_9$N, Pbam-V$_5$N$_2$, Pnma-V$_2$N and I4/mcm-VN$_2$. V$_2$N undergoes a phase transition from $\varepsilon$-Fe$_2$N-type V$_2$N (P$\bar{3}$1m) to $ζ$-Fe$_2$N-type V$_2$N (Pbcn) at 10 GPa and to Fe$_2$C-type V$_2$N (Pnnm) at 59 GPa, then to Pnma-V$_2$N at 96 GPa. Low-temperature tetragonal VN is theoretically proved to belong to space group P$\bar{4}$2m. The estimated Vickers hardnesses and fracture toughness of WC-type VN are around 37 GPa and 4.3-6.1 MPa m$^{1/2}$, respectively. Al$_2$Cu-type VN$_2$ (I4/mcm) with a Vickers hardness of 25-27 GPa and fracture toughness of 3.6-6.6 MPa m$^{1/2}$ also shows excellent mechanical properties. Elastic properties of WC-type mononitrides of transition metals from IVB group (Ti, Zr and Hf), VB group (V, Nb and Ta) and VIB (Cr, Mo and W) are calculated and compared. Both the bond strength and structural configuration determine the mechanical properties of a material.

cond-mat.mtrl-sci↗

arXiv2019

High-Temperature Superconductivity in the Ti--H System at High Pressures

Search for stable high-pressure compounds in the Ti--H system reveals the existence of titanium hydrides with new stoichiometries, including Ibam-Ti$_2$H$_5$, I4/m-Ti$_5$H$_{13}$, I$\bar{4}$-Ti$_5$H$_{14}$, Fddd-TiH$_4$, Immm-Ti$_2$H$_{13}$, P$\bar{1}$-TiH$_{12}$, and C2/m-TiH$_{22}$. Our calculations predict I4/mmm $\rightarrow$ R$\bar{3}$m and I4/mmm $\rightarrow$ Cmma transitions in TiH and TiH$_2$, respectively. Phonons and the electron--phonon coupling of all searched titanium hydrides are analyzed at high pressure. It is found that Immm-Ti$_2$H$_{13}$ rather than the highest hydrogen content C2/m-TiH$_{22}$, exhibits the highest superconducting critical temperature T$_{c}$. The estimated T$_{c}$ of Immm-Ti$_2$H$_{13}$ and C2/m-TiH$_{22}$ are respectively 127.4--149.4 K ($μ^{*}$=0.1-0.15) at 350 GPa and 91.3--110.2 K at 250 GPa by numerically solving the Eliashberg equations. One of the effects of pressure on T$_{c}$ can be attributed to the softening and hardening of phonons with increasing pressure.

cond-mat.mtrl-sci↗

arXiv2015

Pressure induced novel compounds in the Hf-O system from first-principles calculations

Using first-principles evolutionary simulations, we have systematically investigated phase stability in the Hf-O system at pressure up to 120 GPa. New compounds Hf5O2, Hf3O2, HfO and HfO3 are discovered to be thermodynamically stable at certain pressure ranges and a new stable high-pressure phase is found for Hf2O with space group Pnnm and anti-CaCl2-type structure. Both P62m-HfO and P4m2-Hf2O3 show semimetallic character. Pnnm-HfO3 shows interesting structure, simultaneously containing oxide O2- and peroxide [O-O]2- anions. Remarkably, it is P62m-HfO rather than OII-HfO2 that exhibits the highest mechanical characteristics among Hf-O compounds. Pnnm-Hf2O, Imm2-Hf5O2, P31m-Hf2O and P4m2-Hf2O3 phases also show superior mechanical properties, these phases can be quenched to ambient pressure and their properties can be exploited.

cond-mat.mtrl-sci↗