Text-to-image (T2I) diffusion models (DMs) have shown promise in generating high-quality images from textual descriptions. The real-world applications of these models require particular attention to their safety and fidelity, but this has not been sufficiently explored. One fundamental question is whether existing T2I DMs are robust against variations over input texts. To answer it, this work provides the first robustness evaluation of T2I DMs against real-world attacks. Unlike prior studies that focus on malicious attacks involving apocryphal alterations to the input texts, we consider an attack space spanned by realistic errors (e.g., typo, glyph, phonetic) that humans can make, to ensure semantic consistency. Given the inherent randomness of the generation process, we develop novel distribution-based attack objectives to mislead T2I DMs. We perform attacks in a black-box manner without any knowledge of the model. Extensive experiments demonstrate the effectiveness of our method for attacking popular T2I DMs and simultaneously reveal their non-trivial robustness issues. Moreover, we provide an in-depth analysis of our method to show that it is not designed to attack the text encoder in T2I DMs solely.

Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks

Adversarial attacks have been extensively studied in the domain of deep image classification, but their impacts on other domains such as Machine and Deep Learning-based Network Intrusion Detection Systems (NIDSs) have received limited attention. While adversarial attacks on images are generally more straightforward due to fewer constraints in the input domain, generating adversarial examples in the network domain poses greater challenges due to the diverse types of network traffic and the need to maintain its validity. Prior research has introduced constraints to generate adversarial examples against NIDSs, but their effectiveness across different attack settings, including transferability, targetability, defenses, and the overall attack success have not been thoroughly examined. In this paper, we proposed a novel set of domain constraints for network traffic that preserve the statistical and semantic relationships between traffic features while ensuring the validity of the perturbed adversarial traffic. Our constraints are categorized into four types: feature mutability constraints, feature value constraints, feature dependency constraints and distribution preserving constraints. We evaluated the impacts of these constraints on white box and black box attacks using two intrusion detection datasets. Our results demonstrated that the introduced constraints have a significant impact on the success of white box attacks. Our research revealed that transferability of adversarial examples depends on the similarity between the targeted models and the models to which the examples are transferred, regardless of the attack type or the presence of constraints. We also observed that adversarial training enhanced the robustness of the majority of machine learning and deep learning-based NIDSs against unconstrained attacks, while providing some resilience against constrained attacks. In practice, this suggests the potential use of pre-existing signatures of constrained attacks to combat new variations or zero-day adversarial attacks in real-world NIDSs. 

Constraining Adversarial Attacks On Network Intrusion Detection Systems: Transferability and Defense Analysis

Textual adversarial attacks expose the vulnerabilities of text classifiers and can be used to improve their robustness. Previous context-aware attack models suffer from several limitations. They generally rely on out-of-date substitutes, solely consider the gold label probability, and use the greedy search when generating adversarial examples, often limiting the attack efficiency. To tackle these issues, we propose MC-PDBS, a More Context-aware textual adversarial attack model using Probability Difference-guided Beam Search. MC-PDBS generates substitutes using the newest perturbed text sequences in each attack iteration, enabling the generation of more context-aware adversarial examples. The probability difference is an overall consideration of the probabilities of all class labels, which is more effective than the gold label probability in guiding the selection of attack paths. In addition, the beam search enables MC-PDBS to search attack paths from multiple search channels, thereby avoiding the limited search space problem. Extensive experiments and human evaluation demonstrate that MC-PDBS outperforms previous best models in a series of evaluation metrics, particularly bringing up to a +19.5% attack success rate. Extensive analyses further confirm the effectiveness of MC-PDBS.

A More Context-aware Approach for Textual Adversarial Attacks using Probability Difference-guided Beam Search

The widespread adoption of DNNs in NLP software has highlighted the need for robustness. Researchers proposed various automatic testing techniques for adversarial test cases. However, existing methods suffer from two limitations: weak error-discovering capabilities, with success rates ranging from 0% to 24.6% for BERT-based NLP software, and time inefficiency, taking 177.8s to 205.28s per test case, making them challenging for time-constrained scenarios. To address these issues, this paper proposes LEAP, an automated test method that uses LEvy flight-based Adaptive Particle swarm optimization integrated with textual features to generate adversarial test cases. Specifically, we adopt Levy flight for population initialization to increase the diversity of generated test cases. We also design an inertial weight adaptive update operator to improve the efficiency of LEAP's global optimization of high-dimensional text examples and a mutation operator based on the greedy strategy to reduce the search time. We conducted a series of experiments to validate LEAP's ability to test NLP software and found that the average success rate of LEAP in generating adversarial test cases is 79.1%, which is 6.1% higher than the next best approach (PSOattack). While ensuring high success rates, LEAP significantly reduces time overhead by up to 147.6s compared to other heuristic-based methods. Additionally, the experimental results demonstrate that LEAP can generate more transferable test cases and significantly enhance the robustness of DNN-based systems.

pdf/leap-efficient-and-automated-test-method-for-nlp-software-1lps3ez7pi.pdf

LEAP: Efficient and Automated Test Method for NLP Software

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means to provide evidence (i.e., citations). However, current attribution methods usually focus on the retrieval stage and automatic evaluation that neglect mirroring the citation mechanisms in human scholarly writing to bolster credibility. In this paper, we address these challenges by modelling the attribution task as preference learning and introducing an Automatic Preference Optimization (APO) framework. First, we create a curated collection for post-training with 6,330 examples by collecting and filtering from existing datasets. Second, considering the high cost of labelling preference data, we further propose an automatic method to synthesize attribution preference data resulting in 95,263 pairs. Moreover, inspired by the human citation process, we further propose a progressive preference optimization method by leveraging fine-grained information. Extensive experiments on three datasets (i.e., ASQA, StrategyQA, and ELI5) demonstrate that APO achieves state-of-the-art citation F1 with higher answer quality.

Improving Attributed Text Generation of Large Language Models via Preference Learning

오늘날 게임 산업이 성장하면서 수많은 게임이 출시되고 있다. 이에 게임사들은 유저를 확보하기 위해 가격 프로모션을 적극적으로 활용하고 있지만, 그 효과가 반드시 장기적으로 이어지는 것은 아니다. 한편, 유저들의 게임플레이 행동은 온라인 게임 커뮤니티 및 게임 스트리밍 시청과 같은 게임 관련 제반 활동과 긴밀하게 연관되어 있기 때문에 가격 프로모션이 이러한 제반 활동에 영향을 미칠 가능성이 있다. 본 연구는 게임 플레이 및 게임 제반 활동에 가격 프로모션이 미치는 장기 효과를 살펴보고자 한다. 구체적으로, 토빗(Tobit) 모형이 패널 벡터자기회귀모형(Panel Vector Autoregressive)에 결합된 모형을 통해 가격 프로모션이 게임 플레이 및 게임 제반 활동에 미치는 장단기 효과를 분석하고자 한다. 이를 위해 게임 유통 플랫폼 스팀(Steam)에서 수집한 데이터를 분석한 결과, 가격 프로모션의 효과는 게임 플레이 및 제반 활동과 동태적 상호작용을 가진 것으로 드러났다. 이러한 결과를 바탕으로 본 연구는 게임 실무자들에게 효과적인 마케팅 전략 수립을 위한 시사점을 제안하고자 한다. 

The Long-Term Impact of Price Promotion on the Game Market: Focusing on Tobit-Augmented Panel VAR Model

Surface state change of ammunition generated during the storage period increases the surface roughness and this affects the flight of ammunition, but there are no research results quantitatively indicating this. In this study, the drag force for each Mach number of howitzer shells was calculated through CFD to which the surface data of the howitzer shell was applied, and analysis of trajectory was performed using drag force values as an input of the 4th Runge-Kutta method, and the degree of decrease of the maximum range caused by the surface roughness of the howitzer shell was estimated. As a result, it was confirmed that the maximum range of howitzer shell with high surface roughness was 1.12 % shorter than that of howitzer shell without roughness. It was confirmed that the effect of surface roughness on the trajectory is not negligible.

The Effect of Surface Roughness on the Trajectory of Howitzer Shell

We focus on the problem of adversarial attacks against models on discrete sequential data in the black-box setting where the attacker aims to craft adversarial examples with limited query access to the victim model. Existing black-box attacks, mostly based on greedy algorithms, ﬁnd adversarial examples using pre-computed key positions to perturb, which severely limits the search space and might result in suboptimal solutions. To this end, we propose a query-efﬁcient black-box attack using Bayesian optimization, which dynamically computes important positions using an automatic relevance determination (ARD) categorical kernel. We introduce block decomposition and history subsampling techniques to improve the scalability of Bayesian optimization when an input sequence becomes long. Moreover, we develop a post-optimization algorithm that ﬁnds adversarial examples with smaller perturbation size. Experiments on natural language and protein classiﬁcation tasks demonstrate that our method consistently achieves higher attack success rate with signiﬁcant reduction in query count and modiﬁcation rate compared to the previous state-of-the-art methods.

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization

Ofﬂine reinforcement learning has developed rapidly over the recent years, but estimating the actual performance of ofﬂine policies still remains a challenge. We propose a scoring metric for ofﬂine policies that highly correlates with actual policy performance and can be directly used for ofﬂine policy optimization in a supervised manner. To achieve this, we leverage the contrastive learning framework to design a scoring metric that gives high scores to policies that imitate the actions yielding relatively high returns while avoiding those yielding relatively low returns. Our experiments show that 1) our scoring metric is able to more accurately rank ofﬂine policies and 2) the policies optimized using our metric show high performance on various ofﬂine reinforcement learning benchmarks. Notably, our algorithm has a much lower network capacity requirement for the policy network compared to other supervised learning-based methods and also does not need any additional networks such as a Q-network.

pdf/designing-an-offline-reinforcement-learning-objective-from-3uyea77j.pdf

Designing an offline reinforcement learning objective from scratch

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Junhyeok Lee

Author Tools

Chat about Author

Papers

The Long-Term Impact of Price Promotion on the Game Market: Focusing on Tobit-Augmented Panel VAR Model

The Effect of Surface Roughness on the Trajectory of Howitzer Shell

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization

Designing an offline reinforcement learning objective from scratch