As Large Language Models quickly become ubiquitous, their security vulnerabilities are critical to understand. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from the rich body of work on adversarial machine learning, we approach these attacks with three questions: What threat models are practically useful in this domain? How do baseline defense techniques perform in this new domain? How does LLM security differ from computer vision? We evaluate several baseline defense strategies against leading adversarial attacks on LLMs, discussing the various settings in which each is feasible and effective. Particularly, we look at three types of defenses: detection (perplexity based), input preprocessing (paraphrase and retokenization), and adversarial training. We discuss white-box and gray-box settings and discuss the robustness-performance trade-off for each of the defenses considered. Surprisingly, we find much more success with filtering and preprocessing than we would expect from other domains, such as vision, providing a first indication that the relative strengths of these defenses may be weighed differently in these domains.
相關內容
It is critical that compilers are correct! Finding bugs is one aspect of testing the correctness of compilers in wide use today. A compiler is correct if every compiled program behaves as allowed by the semantics of its source code - else there is a bug. Memory consistency models define the semantics of concurrent programs. We focus on how to detect concurrency bugs introduced by compilers, as identified using memory models. We seek a testing technique that automatically covers concurrency bugs up to fixed bounds on program sizes and that scales to find bugs in compiled programs with many lines of code. Otherwise, a testing technique can miss bugs. Unfortunately, the state-of-the-art techniques are yet to satisfy all of these properties. We present the T\'el\'echat compiler testing tool for concurrent programs. T\'el\'echat finds a concurrency bug when the behaviour of a compiled program, as allowed by its architecture memory model, is not a behaviour of the source program under its source model. We make three claims: T\'el\'echat improves the state-of-the-art at finding bugs in code generation for multi-threaded execution, it is the first public description of a compiler testing tool for concurrency that is deployed in industry, and it is the first tool that takes a significant step towards the desired properties. We provide experimental evidence suggesting T\'el\'echat finds bugs missed by other state-of-the-art techniques, case studies indicating that T\'el\'echat satisfies the properties, and reports of our experience deploying T\'el\'echat in industry.
We consider the fair division of indivisible items using the maximin shares measure. Recent work on the topic has focused on extending results beyond the class of additive valuation functions. In this spirit, we study the case where the items form an hereditary set system. We present a simple algorithm that allocates each agent a bundle of items whose value is at least $0.3636$ times the maximin share of the agent. This improves upon the current best known guarantee of $0.2$ due to Ghodsi et al. The analysis of the algorithm is almost tight; we present an instance where the algorithm provides a guarantee of at most $0.3738$. We also show that the algorithm can be implemented in polynomial time given a valuation oracle for each agent.
Synthesizing inductive loop invariants is fundamental to automating program verification. In this work, we observe that Large Language Models (such as gpt-3.5 or gpt-4) are capable of synthesizing loop invariants for a class of programs in a 0-shot setting, yet require several samples to generate the correct invariants. This can lead to a large number of calls to a program verifier to establish an invariant. To address this issue, we propose a {\it re-ranking} approach for the generated results of LLMs. We have designed a ranker that can distinguish between correct inductive invariants and incorrect attempts based on the problem definition. The ranker is optimized as a contrastive ranker. Experimental results demonstrate that this re-ranking mechanism significantly improves the ranking of correct invariants among the generated candidates, leading to a notable reduction in the number of calls to a verifier.
In this study, we aimed to determine if fine-tuned large language models (LLMs) can generate accurate, personalized impressions for whole-body PET reports. Twelve language models were trained on a corpus of PET reports using the teacher-forcing algorithm, with the report findings as input and the clinical impressions as reference. An extra input token encodes the reading physician's identity, allowing models to learn physician-specific reporting styles. Our corpus comprised 37,370 retrospective PET reports collected from our institution between 2010 and 2022. To identify the best LLM, 30 evaluation metrics were benchmarked against quality scores from two nuclear medicine (NM) physicians, with the most aligned metrics selecting the model for expert evaluation. In a subset of data, model-generated impressions and original clinical impressions were assessed by three NM physicians according to 6 quality dimensions (3-point scale) and an overall utility score (5-point scale). Each physician reviewed 12 of their own reports and 12 reports from other physicians. Bootstrap resampling was used for statistical analysis. Of all evaluation metrics, domain-adapted BARTScore and PEGASUSScore showed the highest Spearman's rank correlations (0.568 and 0.563) with physician preferences. Based on these metrics, the fine-tuned PEGASUS model was selected as the top LLM. When physicians reviewed PEGASUS-generated impressions in their own style, 89% were considered clinically acceptable, with a mean utility score of 4.08 out of 5. Physicians rated these personalized impressions as comparable in overall utility to the impressions dictated by other physicians (4.03, P=0.41). In conclusion, personalized impressions generated by PEGASUS were clinically useful, highlighting its potential to expedite PET reporting.
Multimodal Large Language Model (MLLM) recently has been a new rising research hotspot, which uses powerful Large Language Models (LLMs) as a brain to perform multimodal tasks. The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional methods, suggesting a potential path to artificial general intelligence. In this paper, we aim to trace and summarize the recent progress of MLLM. First of all, we present the formulation of MLLM and delineate its related concepts. Then, we discuss the key techniques and applications, including Multimodal Instruction Tuning (M-IT), Multimodal In-Context Learning (M-ICL), Multimodal Chain of Thought (M-CoT), and LLM-Aided Visual Reasoning (LAVR). Finally, we discuss existing challenges and point out promising research directions. In light of the fact that the era of MLLM has only just begun, we will keep updating this survey and hope it can inspire more research. An associated GitHub link collecting the latest papers is available at //github.com/BradyFU/Awesome-Multimodal-Large-Language-Models.
This work aims to provide an engagement decision support tool for Beyond Visual Range (BVR) air combat in the context of Defensive Counter Air (DCA) missions. In BVR air combat, engagement decision refers to the choice of the moment the pilot engages a target by assuming an offensive stance and executing corresponding maneuvers. To model this decision, we use the Brazilian Air Force's Aerospace Simulation Environment (\textit{Ambiente de Simula\c{c}\~ao Aeroespacial - ASA} in Portuguese), which generated 3,729 constructive simulations lasting 12 minutes each and a total of 10,316 engagements. We analyzed all samples by an operational metric called the DCA index, which represents, based on the experience of subject matter experts, the degree of success in this type of mission. This metric considers the distances of the aircraft of the same team and the opposite team, the point of Combat Air Patrol, and the number of missiles used. By defining the engagement status right before it starts and the average of the DCA index throughout the engagement, we create a supervised learning model to determine the quality of a new engagement. An algorithm based on decision trees, working with the XGBoost library, provides a regression model to predict the DCA index with a coefficient of determination close to 0.8 and a Root Mean Square Error of 0.05 that can furnish parameters to the BVR pilot to decide whether or not to engage. Thus, using data obtained through simulations, this work contributes by building a decision support system based on machine learning for BVR air combat.
Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further improve graph representation. However, there is an inherent gap between self-supervised tasks and downstream tasks in terms of optimization objective and training data. Conventional pre-training methods may be not effective enough on knowledge transfer since they do not make any adaptation for downstream tasks. To solve such problems, we propose a new transfer learning paradigm on GNNs which could effectively leverage self-supervised tasks as auxiliary tasks to help the target task. Our methods would adaptively select and combine different auxiliary tasks with the target task in the fine-tuning stage. We design an adaptive auxiliary loss weighting model to learn the weights of auxiliary tasks by quantifying the consistency between auxiliary tasks and the target task. In addition, we learn the weighting model through meta-learning. Our methods can be applied to various transfer learning approaches, it performs well not only in multi-task learning but also in pre-training and fine-tuning. Comprehensive experiments on multiple downstream tasks demonstrate that the proposed methods can effectively combine auxiliary tasks with the target task and significantly improve the performance compared to state-of-the-art methods.
Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This motivates us to propose a novel computer vision problem called: `Open World Object Detection', where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received. We formulate the problem, introduce a strong evaluation protocol and provide a novel solution, which we call ORE: Open World Object Detector, based on contrastive clustering and energy based unknown identification. Our experimental evaluation and ablation studies analyze the efficacy of ORE in achieving Open World objectives. As an interesting by-product, we find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting, where we achieve state-of-the-art performance, with no extra methodological effort. We hope that our work will attract further research into this newly identified, yet crucial research direction.
Emotion plays an important role in detecting fake news online. When leveraging emotional signals, the existing methods focus on exploiting the emotions of news contents that conveyed by the publishers (i.e., publisher emotion). However, fake news is always fabricated to evoke high-arousal or activating emotions of people to spread like a virus, so the emotions of news comments that aroused by the crowd (i.e., social emotion) can not be ignored. Furthermore, it needs to be explored whether there exists a relationship between publisher emotion and social emotion (i.e., dual emotion), and how the dual emotion appears in fake news. In the paper, we propose Dual Emotion Features to mine dual emotion and the relationship between them for fake news detection. And we design a universal paradigm to plug it into any existing detectors as an enhancement. Experimental results on three real-world datasets indicate the effectiveness of the proposed features.
Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems. Despite the plethora of different models for deep learning on graphs, few approaches have been proposed thus far for dealing with graphs that present some sort of dynamic nature (e.g. evolving features or connectivity over time). In this paper, we present Temporal Graph Networks (TGNs), a generic, efficient framework for deep learning on dynamic graphs represented as sequences of timed events. Thanks to a novel combination of memory modules and graph-based operators, TGNs are able to significantly outperform previous approaches being at the same time more computationally efficient. We furthermore show that several previous models for learning on dynamic graphs can be cast as specific instances of our framework. We perform a detailed ablation study of different components of our framework and devise the best configuration that achieves state-of-the-art performance on several transductive and inductive prediction tasks for dynamic graphs.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191