Large language models (LLMs), such as GPT series models, have received substantial attention due to their impressive capabilities for generating and understanding human-level language. More recently, LLMs have emerged as an innovative and powerful adjunct in the medical field, transforming traditional practices and heralding a new era of enhanced healthcare services. This survey provides a comprehensive overview of Medical Large Language Models (Med-LLMs), outlining their evolution from general to the medical-specific domain (i.e, Technology and Application), as well as their transformative impact on healthcare (e.g., Trustworthiness and Safety). Concretely, starting from the fundamental history and technology of LLMs, we first delve into the progressive adaptation and refinements of general LLM models in the medical domain, especially emphasizing the advanced algorithms that boost the LLMs' performance in handling complicated medical environments, including clinical reasoning, knowledge graph, retrieval-augmented generation, human alignment, and multi-modal learning. Secondly, we explore the extensive applications of Med-LLMs across domains such as clinical decision support, report generation, and medical education, illustrating their potential to streamline healthcare services and augment patient outcomes. Finally, recognizing the imperative and responsible innovation, we discuss the challenges of ensuring fairness, accountability, privacy, and robustness in Med-LLMs applications. Finally, we conduct a concise discussion for anticipating possible future trajectories of Med-LLMs, identifying avenues for the prudent expansion of Med-LLMs. By consolidating above-mentioned insights, this review seeks to provide a comprehensive investigation of the potential strengths and limitations of Med-LLMs for professionals and researchers, ensuring a responsible landscape in the healthcare setting.
Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts in real-world scenarios. To tackle the problem, numerous debias approaches have been proposed and benchmarked on datasets intentionally designed with severe biases. However, it remains to be asked: \textit{1. Do existing benchmarks really capture biases in the real world? 2. Can existing debias methods handle biases in the real world?} To answer the questions, we revisit biased distributions in existing benchmarks and real-world datasets, and propose a fine-grained framework for analyzing dataset bias by disentangling it into the magnitude and prevalence of bias. We observe and theoretically demonstrate that existing benchmarks poorly represent real-world biases. We further introduce two novel biased distributions to bridge this gap, forming a nuanced evaluation framework for real-world debiasing. Building upon these results, we evaluate existing debias methods with our evaluation framework. Results show that existing methods are incapable of handling real-world biases. Through in-depth analysis, we propose a simple yet effective approach that can be easily applied to existing debias methods, named Debias in Destruction (DiD). Empirical results demonstrate the superiority of DiD, improving the performance of existing methods on all types of biases within the proposed evaluation framework.
Large Language Models have gained considerable attention for their revolutionary capabilities. However, there is also growing concern on their safety implications, making a comprehensive safety evaluation for LLMs urgently needed before model deployment. In this work, we propose S-Eval, a new comprehensive, multi-dimensional and open-ended safety evaluation benchmark. At the core of S-Eval is a novel LLM-based automatic test prompt generation and selection framework, which trains an expert testing LLM Mt combined with a range of test selection strategies to automatically construct a high-quality test suite for the safety evaluation. The key to the automation of this process is a novel expert safety-critique LLM Mc able to quantify the riskiness score of an LLM's response, and additionally produce risk tags and explanations. Besides, the generation process is also guided by a carefully designed risk taxonomy with four different levels, covering comprehensive and multi-dimensional safety risks of concern. Based on these, we systematically construct a new and large-scale safety evaluation benchmark for LLMs consisting of 220,000 evaluation prompts, including 20,000 base risk prompts (10,000 in Chinese and 10,000 in English) and 200,000 corresponding attack prompts derived from 10 popular adversarial instruction attacks against LLMs. Moreover, considering the rapid evolution of LLMs and accompanied safety threats, S-Eval can be flexibly configured and adapted to include new risks, attacks and models. S-Eval is extensively evaluated on 20 popular and representative LLMs. The results confirm that S-Eval can better reflect and inform the safety risks of LLMs compared to existing benchmarks. We also explore the impacts of parameter scales, language environments, and decoding parameters on the evaluation, providing a systematic methodology for evaluating the safety of LLMs.
Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models. Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models. However, backdoor-based methods have two fatal drawbacks, including harmfulness and ambiguity. The former indicates that they introduce maliciously controllable misclassification behaviors ($i.e.$, backdoor) to the watermarked released models. The latter denotes that malicious users can easily pass the verification by finding other misclassified samples, leading to ownership ambiguity. In this paper, we argue that both limitations stem from the `zero-bit' nature of existing watermarking schemes, where they exploit the status ($i.e.$, misclassified) of predictions for verification. Motivated by this understanding, we design a new watermarking paradigm, $i.e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions. Specifically, EaaW embeds a `multi-bit' watermark into the feature attribution explanation of specific trigger samples without changing the original prediction. We correspondingly design the watermark embedding and extraction algorithms inspired by explainable artificial intelligence. In particular, our approach can be used for different tasks ($e.g.$, image classification and text generation). Extensive experiments verify the effectiveness and harmlessness of our EaaW and its resistance to potential attacks.
The rapid advancement in text-to-video (T2V) generative models has enabled the synthesis of high-fidelity video content guided by textual descriptions. Despite this significant progress, these models are often susceptible to hallucination, generating contents that contradict the input text, which poses a challenge to their reliability and practical deployment. To address this critical issue, we introduce the SoraDetector, a novel unified framework designed to detect hallucinations across diverse large T2V models, including the cutting-edge Sora model. Our framework is built upon a comprehensive analysis of hallucination phenomena, categorizing them based on their manifestation in the video content. Leveraging the state-of-the-art keyframe extraction techniques and multimodal large language models, SoraDetector first evaluates the consistency between extracted video content summary and textual prompts, then constructs static and dynamic knowledge graphs (KGs) from frames to detect hallucination both in single frames and across frames. Sora Detector provides a robust and quantifiable measure of consistency, static and dynamic hallucination. In addition, we have developed the Sora Detector Agent to automate the hallucination detection process and generate a complete video quality report for each input video. Lastly, we present a novel meta-evaluation benchmark, T2VHaluBench, meticulously crafted to facilitate the evaluation of advancements in T2V hallucination detection. Through extensive experiments on videos generated by Sora and other large T2V models, we demonstrate the efficacy of our approach in accurately detecting hallucinations. The code and dataset can be accessed via GitHub.
Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs towards desired attributes often assume unbiased representations and rely solely on steering prompts. However, the representations learned from pre-training can introduce semantic biases that influence the steering process, leading to suboptimal results. We propose LLMGuardaril, a novel framework that incorporates causal analysis and adversarial learning to obtain unbiased steering representations in LLMs. LLMGuardaril systematically identifies and blocks the confounding effects of biases, enabling the extraction of unbiased steering representations. Additionally, it includes an explainable component that provides insights into the alignment between the generated output and the desired direction. Experiments demonstrate LLMGuardaril's effectiveness in steering LLMs towards desired attributes while mitigating biases. Our work contributes to the development of safe and reliable LLMs that align with desired attributes. We discuss the limitations and future research directions, highlighting the need for ongoing research to address the ethical implications of large language models.
Deep learning-based malware classifiers face significant challenges due to concept drift. The rapid evolution of malware, especially with new families, can depress classification accuracy to near-random levels. Previous research has primarily focused on detecting drift samples, relying on expert-led analysis and labeling for model retraining. However, these methods often lack a comprehensive understanding of malware concepts and provide limited guidance for effective drift adaptation, leading to unstable detection performance and high human labeling costs. To address these limitations, we introduce DREAM, a novel system designed to surpass the capabilities of existing drift detectors and to establish an explanatory drift adaptation process. DREAM enhances drift detection through model sensitivity and data autonomy. The detector, trained in a semi-supervised approach, proactively captures malware behavior concepts through classifier feedback. During testing, it utilizes samples generated by the detector itself, eliminating reliance on extensive training data. For drift adaptation, DREAM enlarges human intervention, enabling revisions of malware labels and concept explanations embedded within the detector's latent space. To ensure a comprehensive response to concept drift, it facilitates a coordinated update process for both the classifier and the detector. Our evaluation shows that DREAM can effectively improve the drift detection accuracy and reduce the expert analysis effort in adaptation across different malware datasets and classifiers.
Federated learning (FL) enables collaborative model training among multiple clients without raw data exposure. However, recent studies have shown that clients' private training data can be reconstructed from the gradients they share in FL, known as gradient inversion attacks (GIAs). While GIAs have demonstrated effectiveness under \emph{ideal settings and auxiliary assumptions}, their actual efficacy against \emph{practical FL systems} remains under-explored. To address this gap, we conduct a comprehensive study on GIAs in this work. We start with a survey of GIAs that establishes a milestone to trace their evolution and develops a systematization to uncover their inherent threats. Specifically, we categorize the auxiliary assumptions used by existing GIAs based on their practical accessibility to potential adversaries. To facilitate deeper analysis, we highlight the challenges that GIAs face in practical FL systems from three perspectives: \textit{local training}, \textit{model}, and \textit{post-processing}. We then perform extensive theoretical and empirical evaluations of state-of-the-art GIAs across diverse settings, utilizing eight datasets and thirteen models. Our findings indicate that GIAs have inherent limitations when reconstructing data under practical local training settings. Furthermore, their efficacy is sensitive to the trained model, and even simple post-processing measures applied to gradients can be effective defenses. Overall, our work provides crucial insights into the limited effectiveness of GIAs in practical FL systems. By rectifying prior misconceptions, we hope to inspire more accurate and realistic investigations on this topic.
Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing is believing. One aspect that has been overlooked so far is that current deepfake detection approaches may easily fall into the trap of overfitting, focusing only on forgery clues within one or a few local regions. Moreover, existing works heavily rely on neural networks to extract forgery features, lacking theoretical constraints guaranteeing that sufficient forgery clues are extracted and superfluous features are eliminated. These deficiencies culminate in unsatisfactory accuracy and limited generalizability in real-life scenarios. In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature. (2) Based on the information bottleneck theory, we derive Local Information Loss to guarantee the orthogonality of local representations while preserving comprehensive task-relevant information. (3) Further, to fuse the local representations and remove task-irrelevant information, we arrive at a Global Information Loss through the theoretical analysis of mutual information. Empirically, our method achieves state-of-the-art performance on five benchmark datasets.Our code is available at \url{https://github.com/QingyuLiu/Exposing-the-Deception}, hoping to inspire researchers.
Guided image synthesis methods, like SDEdit based on the diffusion model, excel at creating realistic images from user inputs such as stroke paintings. However, existing efforts mainly focus on image quality, often overlooking a key point: the diffusion model represents a data distribution, not individual images. This introduces a low but critical chance of generating images that contradict user intentions, raising ethical concerns. For example, a user inputting a stroke painting with female characteristics might, with some probability, get male faces from SDEdit. To expose this potential vulnerability, we aim to build an adversarial attack forcing SDEdit to generate a specific data distribution aligned with a specified attribute (e.g., female), without changing the input's attribute characteristics. We propose the Targeted Attribute Generative Attack (TAGA), using an attribute-aware objective function and optimizing the adversarial noise added to the input stroke painting. Empirical studies reveal that traditional adversarial noise struggles with TAGA, while natural perturbations like exposure and motion blur easily alter generated images' attributes. To execute effective attacks, we introduce FoolSDEdit: We design a joint adversarial exposure and blur attack, adding exposure and motion blur to the stroke painting and optimizing them together. We optimize the execution strategy of various perturbations, framing it as a network architecture search problem. We create the SuperPert, a graph representing diverse execution strategies for different perturbations. After training, we obtain the optimized execution strategy for effective TAGA against SDEdit. Comprehensive experiments on two datasets show our method compelling SDEdit to generate a targeted attribute-aware data distribution, significantly outperforming baselines.