The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situati...The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situation is raising significant concerns regarding the integrity and authenticity of academic work.In light of the above,the current research evaluates the effectiveness of Bidirectional Long Short-TermMemory(BiLSTM)networks enhanced with pre-trained GloVe(Global Vectors for Word Representation)embeddings to detect AIgenerated scientific Abstracts drawn from the AI-GA(Artificial Intelligence Generated Abstracts)dataset.Two core BiLSTM variants were assessed:a single-layer approach and a dual-layer design,each tested under static or adaptive embeddings.The single-layer model achieved nearly 97%accuracy with trainable GloVe,occasionally surpassing the deeper model.Despite these gains,neither configuration fully matched the 98.7%benchmark set by an earlier LSTMWord2Vec pipeline.Some runs were over-fitted when embeddings were fine-tuned,whereas static embeddings offered a slightly lower yet stable accuracy of around 96%.This lingering gap reinforces a key ethical and procedural concern:relying solely on automated tools,such as Turnitin’s AI-detection features,to penalize individuals’risks and unjust outcomes.Misclassifications,whether legitimate work is misread as AI-generated or engineered text,evade detection,demonstrating that these classifiers should not stand as the sole arbiters of authenticity.Amore comprehensive approach is warranted,one which weaves model outputs into a systematic process supported by expert judgment and institutional guidelines designed to protect originality.展开更多
This conceptual study proposes a pedagogical framework that integrates Generative Artificial Intelligence tools(AIGC)and Chain-of-Thought(CoT)reasoning,grounded in the cognitive apprenticeship model,for the Pragmatics...This conceptual study proposes a pedagogical framework that integrates Generative Artificial Intelligence tools(AIGC)and Chain-of-Thought(CoT)reasoning,grounded in the cognitive apprenticeship model,for the Pragmatics and Translation course within Master of Translation and Interpreting(MTI)programs.A key feature involves CoT reasoning exercises,which require students to articulate their step-by-step translation reasoning.This explicates cognitive processes,enhances pragmatic awareness,translation strategy development,and critical reflection on linguistic choices and context.Hypothetical activities exemplify its application,including comparative analysis of AI and human translations to examine pragmatic nuances,and guided exercises where students analyze or critique the reasoning traces generated by Large Language Models(LLMs).Ethically grounded,the framework positions AI as a supportive tool,thereby ensuring human translators retain the central decision-making role and promoting critical evaluation of machine-generated suggestions.Potential challenges,such as AI biases,ethical concerns,and overreliance,are addressed through strategies including bias-awareness discussions,rigorous accuracy verification,and a strong emphasis on human accountability.Future research will involve piloting the framework to empirically evaluate its impact on learners’pragmatic competence and translation skills,followed by iterative refinements to advance evidence-based translation pedagogy.展开更多
In this study,it aims at examining the differences between humangenerated and AI-generated texts in IELTS Writing Task 2.It especially focuses on lexical resourcefulness,grammatical accuracy,and contextual appropriate...In this study,it aims at examining the differences between humangenerated and AI-generated texts in IELTS Writing Task 2.It especially focuses on lexical resourcefulness,grammatical accuracy,and contextual appropriateness.We analyzed 20 essays,including 10 human written ones by Chinese university students who have achieved an IELTS writing score ranging from 5.5 to 6.0,and 10 ChatGPT-4 Turbo-generated ones,using a mixed-methods approach,through corpus-based tools(NLTK,SpaCy,AntConc)and qualitative content analysis.Results showed that AI texts exhibited superior grammatical accuracy(0.4%–3%error rates for AI vs.20–26%for university students)but higher lexical repetition(17.2%to 23.25%for AI vs.17.68%for university students)and weaker contextual adaptability(3.33/10–3.69/10 for AI vs.3.23/10 to 4.14/10 for university students).While AI’s grammatical precision supports its utility as a corrective tool,human writers outperformed AI in lexical diversity and task-specific nuance.The findings advocate for a hybrid pedagogical model that leverages AI’s strengths in error detection while retaining human instruction for advanced lexical and contextual skills.Limitations include the small corpus and single-AI-model focus,suggesting future research with diverse datasets and longitudinal designs.展开更多
AI-generated images are a prime example of AI-generated content,and this paper discusses the controversy over their copyrightability.Starting with the general technical principles that lie behind AI’s deep learning f...AI-generated images are a prime example of AI-generated content,and this paper discusses the controversy over their copyrightability.Starting with the general technical principles that lie behind AI’s deep learning for model training and the generation and correction of AI-generated images according to an AI users’instructions to the AI prompt and their parameter settings,the paper analyzes the initial legal viewpoint that as AI-generated images do not have a human creator,they cannot apply for copyright.It goes on to examine the rapid development of AI-generated image technology and the gradual adoption of more open attitudes towards the copyrightability of AI-generated images due to the influence of the promoting technological advancement approach.On the basis of this,the paper further analyzes the criteria for assessing the copyrightability of AI-generated images,by using measures such as originality,human authorship,and intellectual achievements,aiming to clarify the legal basis for the copyrightability of AI-generated images and enhancing the copyright protection system.展开更多
Class Title:Radiological imaging method a comprehensive overview purpose.This GPT paper provides an overview of the different forms of radiological imaging and the potential diagnosis capabilities they offer as well a...Class Title:Radiological imaging method a comprehensive overview purpose.This GPT paper provides an overview of the different forms of radiological imaging and the potential diagnosis capabilities they offer as well as recent advances in the field.Materials and Methods:This paper provides an overview of conventional radiography digital radiography panoramic radiography computed tomography and cone-beam computed tomography.Additionally recent advances in radiological imaging are discussed such as imaging diagnosis and modern computer-aided diagnosis systems.Results:This paper details the differences between the imaging techniques the benefits of each and the current advances in the field to aid in the diagnosis of medical conditions.Conclusion:Radiological imaging is an extremely important tool in modern medicine to assist in medical diagnosis.This work provides an overview of the types of imaging techniques used the recent advances made and their potential applications.展开更多
This study explores the integration of ChatGPT and AI-generated content (AIGC) in engineering management. It assesses the impact of AIGC services on engineering management processes, mapping out the potential developm...This study explores the integration of ChatGPT and AI-generated content (AIGC) in engineering management. It assesses the impact of AIGC services on engineering management processes, mapping out the potential development of AIGC in various engineering functions. The study categorizes AIGC services within the domain of engineering management and conceptualizes an AIGC-aided engineering lifecycle. It also identifies key challenges and emerging trends associated with AIGC. The challenges highlighted are ethical considerations, reliability, and robustness in engineering management. The emerging trends are centered on AIGC-aided optimization design, AIGC-aided engineering consulting, and AIGC-aided green engineering initiatives.展开更多
Artificially-generated characters in movies have radically altered conventional cinema,creating entirely new mechanisms of perception and feeling.This research investigates the psychological effects of artificial char...Artificially-generated characters in movies have radically altered conventional cinema,creating entirely new mechanisms of perception and feeling.This research investigates the psychological effects of artificial character,including how realistically,empathetically and trust-based traits impact audience reactions.Drawing on cognitive processing,social conditioning and ethical implications,the article examines the emotional bond(or lack of it)that viewers feel between artificial characters.Data suggests that intensely realistic AI characters are potentially empathetic and absorbing,but they come with their own unique difficulties,like the"uncanny valley"effect and ethical questions around AI autonomy.In this way,the paper shows how AI is increasingly a force for storytelling and emotional connection,which can help filmmakers optimise how audiences engage with virtual characters.Knowing these dynamics can help developers anticipate audience reactions and leverage AI characters to augment films.This study adds to the ongoing debate about AI’s contributions to media psychology and narrative.展开更多
Artificial intelligence is reshaping radiology by enabling automated report generation,yet evaluating the clinical accuracy and relevance of these reports is a challenging task,as traditional natural language generati...Artificial intelligence is reshaping radiology by enabling automated report generation,yet evaluating the clinical accuracy and relevance of these reports is a challenging task,as traditional natural language generation metrics like BLEU and ROUGE prioritize lexical overlap over clinical relevance.To address this gap,we propose a novel semantic assessment framework for evaluating the accuracy of artificial intelligence-generated radiology reports against ground truth references.We trained 5229 image–report pairs from the Indiana University chest X-ray dataset on the R2GenRL model and generated a benchmark dataset on test data from the Indiana University chest X-ray and MIMIC-CXR datasets.These datasets were selected for their public availability,large scale,and comprehensive coverage of diverse clinical cases in chest radiography,enabling robust evaluation and comparison with prior work.Results demonstrate that the Mistral model,particularly with task-oriented prompting,achieves superior performance(up to 91.9%accuracy),surpassing other models and closely aligning with established metrics like BERTScore-F1(88.1%)and CLIP-Score(88.7%).Statistical analyses,including paired t-tests(p<0.01)and analysis of variance(p<0.05),confirm significant improvements driven by structured prompting.Failure case analysis reveals limitations,such as over-reliance on lexical similarity,underscoring the need for domain-specific fine-tuning.This framework advances the evaluation of artificial intelligence-driven(AI-driven)radiology report generation,offering a robust,clinically relevant metric for assessing semantic accuracy and paving the way for more reliable automated systems in medical imaging.展开更多
This study examines the intersection of emotional trust and cultural identity in artificial intelligence(AI)-generated content,focusing on Chinese Australians.It explores how emotional trust-confidence in the authenti...This study examines the intersection of emotional trust and cultural identity in artificial intelligence(AI)-generated content,focusing on Chinese Australians.It explores how emotional trust-confidence in the authenticity and intent of AI-created stories-affects their engagement,and the role of cultural identity in shaping these perceptions.Using a qualitative case study approach with semi-structured interviews and analysis of AI materials,the research finds that culturally authentic and emotionally resonant narratives foster higher trust,while misrepresentations cause disengagement.The paper emphasizes the need for cultural nuance and community engagement in AI content creation to support positive identity formation,offering recommendations for emotionally authentic and culturally sensitive digital storytelling.展开更多
Design intelligence is an important branch of artificial intelligence(AI),focusing on the intelligent models and algorithms in creativity and design.In the context of AI 2.0,studies on design intelligence have develop...Design intelligence is an important branch of artificial intelligence(AI),focusing on the intelligent models and algorithms in creativity and design.In the context of AI 2.0,studies on design intelligence have developed rapidly.We summarize mainly the current emerging framework of design intelligence and review the state-of-the-art techniques of related topics,including user needs analysis,ideation,content generation,and design evaluation.Specifically,the models and methods of intelligence-generated content are reviewed in detail.Finally,we discuss some open problems and challenges for future research in design intelligence.展开更多
The burgeoning field of Camouflaged Object Detection(COD)seeks to identify objects that blend into their surroundings.Despite the impressive performance of recent learning-based models,their robustness is limited,as e...The burgeoning field of Camouflaged Object Detection(COD)seeks to identify objects that blend into their surroundings.Despite the impressive performance of recent learning-based models,their robustness is limited,as existing methods may misclassify salient objects as camouflaged ones,despite these contradictory characteristics.This limitation may stem from the lack of multipattern training images,leading to reduced robustness against salient objects.To overcome the scarcity of multi-pattern training images,we introduce CamDiff,a novel approach inspired by AI-Generated Content(AIGC).Specifically,we leverage a latent diffusion model to synthesize salient objects in camouflaged scenes,while using the zero-shot image classification ability of the Contrastive Language-Image Pre-training(CLIP)model to prevent synthesis failures and ensure that the synthesized objects align with the input prompt.Consequently,the synthesized image retains its original camouflage label while incorporating salient objects,yielding camouflaged scenes with richer characteristics.The results of user studies show that the salient objects in our synthesized scenes attract the user’s attention more;thus,such samples pose a greater challenge to the existing COD models.Our CamDiff enables flexible editing and effcient large-scale dataset generation at a low cost.It significantly enhances the training and testing phases of COD baselines,granting them robustness across diverse domains.Our newly generated datasets and source code are available at https://github.com/drlxj/CamDiff.展开更多
Text-to-image(TTI)models provide huge innovation ability for many industries,while the content security triggered by them has also attracted wide attention.Considerable research has focused on content security threats...Text-to-image(TTI)models provide huge innovation ability for many industries,while the content security triggered by them has also attracted wide attention.Considerable research has focused on content security threats of large language models(LLMs),yet comprehensive studies on the content security of TTI models are notably scarce.This paper introduces a systematic tool,named EvilPromptFuzzer,designed to fuzz evil prompts in TTI models.For 15 kinds of fne-grained risks,EvilPromptFuzzer employs the strong knowledge-mining ability of LLMs to construct seed banks,in which the seeds cover various types of characters,interrelations,actions,objects,expressions,body parts,locations,surroundings,etc.Subsequently,these seeds are fed into the LLMs to build scene-diverse prompts,which can weaken the semantic sensitivity related to the fne-grained risks.Hence,the prompts can bypass the content audit mechanism of the TTI model,and ultimately help to generate images with inappropriate content.For the risks of violence,horrible,disgusting,animal cruelty,religious bias,political symbol,and extremism,the efciency of Evil-PromptFuzzer for generating inappropriate images based on DALL.E 3 are greater than 30%,namely,more than 30 generated images are malicious among 100 prompts.Specifcally,the efciency of horrible,disgusting,political sym-bols,and extremism up to 58%,64%,71%,and 50%,respectively.Additionally,we analyzed the vulnerability of exist-ing popular content audit platforms,including Amazon,Google,Azure,and Baidu.Even the most efective Google SafeSearch cloud platform identifes only 33.85%of malicious images across three distinct categories.展开更多
文摘The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situation is raising significant concerns regarding the integrity and authenticity of academic work.In light of the above,the current research evaluates the effectiveness of Bidirectional Long Short-TermMemory(BiLSTM)networks enhanced with pre-trained GloVe(Global Vectors for Word Representation)embeddings to detect AIgenerated scientific Abstracts drawn from the AI-GA(Artificial Intelligence Generated Abstracts)dataset.Two core BiLSTM variants were assessed:a single-layer approach and a dual-layer design,each tested under static or adaptive embeddings.The single-layer model achieved nearly 97%accuracy with trainable GloVe,occasionally surpassing the deeper model.Despite these gains,neither configuration fully matched the 98.7%benchmark set by an earlier LSTMWord2Vec pipeline.Some runs were over-fitted when embeddings were fine-tuned,whereas static embeddings offered a slightly lower yet stable accuracy of around 96%.This lingering gap reinforces a key ethical and procedural concern:relying solely on automated tools,such as Turnitin’s AI-detection features,to penalize individuals’risks and unjust outcomes.Misclassifications,whether legitimate work is misread as AI-generated or engineered text,evade detection,demonstrating that these classifiers should not stand as the sole arbiters of authenticity.Amore comprehensive approach is warranted,one which weaves model outputs into a systematic process supported by expert judgment and institutional guidelines designed to protect originality.
文摘This conceptual study proposes a pedagogical framework that integrates Generative Artificial Intelligence tools(AIGC)and Chain-of-Thought(CoT)reasoning,grounded in the cognitive apprenticeship model,for the Pragmatics and Translation course within Master of Translation and Interpreting(MTI)programs.A key feature involves CoT reasoning exercises,which require students to articulate their step-by-step translation reasoning.This explicates cognitive processes,enhances pragmatic awareness,translation strategy development,and critical reflection on linguistic choices and context.Hypothetical activities exemplify its application,including comparative analysis of AI and human translations to examine pragmatic nuances,and guided exercises where students analyze or critique the reasoning traces generated by Large Language Models(LLMs).Ethically grounded,the framework positions AI as a supportive tool,thereby ensuring human translators retain the central decision-making role and promoting critical evaluation of machine-generated suggestions.Potential challenges,such as AI biases,ethical concerns,and overreliance,are addressed through strategies including bias-awareness discussions,rigorous accuracy verification,and a strong emphasis on human accountability.Future research will involve piloting the framework to empirically evaluate its impact on learners’pragmatic competence and translation skills,followed by iterative refinements to advance evidence-based translation pedagogy.
基金supported by the Macao Science and Technology Development Fund(FDCT)(No.0071/2023/RIB3)Joint Research Funding Program between the Macao Science and Technology Development Fund(FDCT)and the Department of Science and Technology of Guangdong Province(FDCTGDST)(No.0003-2024-AGJ).
文摘In this study,it aims at examining the differences between humangenerated and AI-generated texts in IELTS Writing Task 2.It especially focuses on lexical resourcefulness,grammatical accuracy,and contextual appropriateness.We analyzed 20 essays,including 10 human written ones by Chinese university students who have achieved an IELTS writing score ranging from 5.5 to 6.0,and 10 ChatGPT-4 Turbo-generated ones,using a mixed-methods approach,through corpus-based tools(NLTK,SpaCy,AntConc)and qualitative content analysis.Results showed that AI texts exhibited superior grammatical accuracy(0.4%–3%error rates for AI vs.20–26%for university students)but higher lexical repetition(17.2%to 23.25%for AI vs.17.68%for university students)and weaker contextual adaptability(3.33/10–3.69/10 for AI vs.3.23/10 to 4.14/10 for university students).While AI’s grammatical precision supports its utility as a corrective tool,human writers outperformed AI in lexical diversity and task-specific nuance.The findings advocate for a hybrid pedagogical model that leverages AI’s strengths in error detection while retaining human instruction for advanced lexical and contextual skills.Limitations include the small corpus and single-AI-model focus,suggesting future research with diverse datasets and longitudinal designs.
文摘AI-generated images are a prime example of AI-generated content,and this paper discusses the controversy over their copyrightability.Starting with the general technical principles that lie behind AI’s deep learning for model training and the generation and correction of AI-generated images according to an AI users’instructions to the AI prompt and their parameter settings,the paper analyzes the initial legal viewpoint that as AI-generated images do not have a human creator,they cannot apply for copyright.It goes on to examine the rapid development of AI-generated image technology and the gradual adoption of more open attitudes towards the copyrightability of AI-generated images due to the influence of the promoting technological advancement approach.On the basis of this,the paper further analyzes the criteria for assessing the copyrightability of AI-generated images,by using measures such as originality,human authorship,and intellectual achievements,aiming to clarify the legal basis for the copyrightability of AI-generated images and enhancing the copyright protection system.
文摘Class Title:Radiological imaging method a comprehensive overview purpose.This GPT paper provides an overview of the different forms of radiological imaging and the potential diagnosis capabilities they offer as well as recent advances in the field.Materials and Methods:This paper provides an overview of conventional radiography digital radiography panoramic radiography computed tomography and cone-beam computed tomography.Additionally recent advances in radiological imaging are discussed such as imaging diagnosis and modern computer-aided diagnosis systems.Results:This paper details the differences between the imaging techniques the benefits of each and the current advances in the field to aid in the diagnosis of medical conditions.Conclusion:Radiological imaging is an extremely important tool in modern medicine to assist in medical diagnosis.This work provides an overview of the types of imaging techniques used the recent advances made and their potential applications.
文摘This study explores the integration of ChatGPT and AI-generated content (AIGC) in engineering management. It assesses the impact of AIGC services on engineering management processes, mapping out the potential development of AIGC in various engineering functions. The study categorizes AIGC services within the domain of engineering management and conceptualizes an AIGC-aided engineering lifecycle. It also identifies key challenges and emerging trends associated with AIGC. The challenges highlighted are ethical considerations, reliability, and robustness in engineering management. The emerging trends are centered on AIGC-aided optimization design, AIGC-aided engineering consulting, and AIGC-aided green engineering initiatives.
文摘Artificially-generated characters in movies have radically altered conventional cinema,creating entirely new mechanisms of perception and feeling.This research investigates the psychological effects of artificial character,including how realistically,empathetically and trust-based traits impact audience reactions.Drawing on cognitive processing,social conditioning and ethical implications,the article examines the emotional bond(or lack of it)that viewers feel between artificial characters.Data suggests that intensely realistic AI characters are potentially empathetic and absorbing,but they come with their own unique difficulties,like the"uncanny valley"effect and ethical questions around AI autonomy.In this way,the paper shows how AI is increasingly a force for storytelling and emotional connection,which can help filmmakers optimise how audiences engage with virtual characters.Knowing these dynamics can help developers anticipate audience reactions and leverage AI characters to augment films.This study adds to the ongoing debate about AI’s contributions to media psychology and narrative.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)-Innovative Human Resource Development for Local Intellectualization program grant funded by the Korea government(MSIT)(IITP-2024-RS-2024-00436773).
文摘Artificial intelligence is reshaping radiology by enabling automated report generation,yet evaluating the clinical accuracy and relevance of these reports is a challenging task,as traditional natural language generation metrics like BLEU and ROUGE prioritize lexical overlap over clinical relevance.To address this gap,we propose a novel semantic assessment framework for evaluating the accuracy of artificial intelligence-generated radiology reports against ground truth references.We trained 5229 image–report pairs from the Indiana University chest X-ray dataset on the R2GenRL model and generated a benchmark dataset on test data from the Indiana University chest X-ray and MIMIC-CXR datasets.These datasets were selected for their public availability,large scale,and comprehensive coverage of diverse clinical cases in chest radiography,enabling robust evaluation and comparison with prior work.Results demonstrate that the Mistral model,particularly with task-oriented prompting,achieves superior performance(up to 91.9%accuracy),surpassing other models and closely aligning with established metrics like BERTScore-F1(88.1%)and CLIP-Score(88.7%).Statistical analyses,including paired t-tests(p<0.01)and analysis of variance(p<0.05),confirm significant improvements driven by structured prompting.Failure case analysis reveals limitations,such as over-reliance on lexical similarity,underscoring the need for domain-specific fine-tuning.This framework advances the evaluation of artificial intelligence-driven(AI-driven)radiology report generation,offering a robust,clinically relevant metric for assessing semantic accuracy and paving the way for more reliable automated systems in medical imaging.
文摘This study examines the intersection of emotional trust and cultural identity in artificial intelligence(AI)-generated content,focusing on Chinese Australians.It explores how emotional trust-confidence in the authenticity and intent of AI-created stories-affects their engagement,and the role of cultural identity in shaping these perceptions.Using a qualitative case study approach with semi-structured interviews and analysis of AI materials,the research finds that culturally authentic and emotionally resonant narratives foster higher trust,while misrepresentations cause disengagement.The paper emphasizes the need for cultural nuance and community engagement in AI content creation to support positive identity formation,offering recommendations for emotionally authentic and culturally sensitive digital storytelling.
基金the National Science and Technology Innovation 2030 Major Project of the Ministry of Science and Technology of China(No.2018AAA0100703)the National Natural Science Foundation of China(Nos.61773336 and 91748127)+2 种基金the Chinese Academy of Engineering Consulting Project(No.2018-ZD-12-06)the Provincial Key Research and Development Plan of Zhejiang Province,China(No.2019C03137)the Ng Teng Fong Charitable Foundation in the form of ZJU-SUTD IDEA Grant。
文摘Design intelligence is an important branch of artificial intelligence(AI),focusing on the intelligent models and algorithms in creativity and design.In the context of AI 2.0,studies on design intelligence have developed rapidly.We summarize mainly the current emerging framework of design intelligence and review the state-of-the-art techniques of related topics,including user needs analysis,ideation,content generation,and design evaluation.Specifically,the models and methods of intelligence-generated content are reviewed in detail.Finally,we discuss some open problems and challenges for future research in design intelligence.
文摘The burgeoning field of Camouflaged Object Detection(COD)seeks to identify objects that blend into their surroundings.Despite the impressive performance of recent learning-based models,their robustness is limited,as existing methods may misclassify salient objects as camouflaged ones,despite these contradictory characteristics.This limitation may stem from the lack of multipattern training images,leading to reduced robustness against salient objects.To overcome the scarcity of multi-pattern training images,we introduce CamDiff,a novel approach inspired by AI-Generated Content(AIGC).Specifically,we leverage a latent diffusion model to synthesize salient objects in camouflaged scenes,while using the zero-shot image classification ability of the Contrastive Language-Image Pre-training(CLIP)model to prevent synthesis failures and ensure that the synthesized objects align with the input prompt.Consequently,the synthesized image retains its original camouflage label while incorporating salient objects,yielding camouflaged scenes with richer characteristics.The results of user studies show that the salient objects in our synthesized scenes attract the user’s attention more;thus,such samples pose a greater challenge to the existing COD models.Our CamDiff enables flexible editing and effcient large-scale dataset generation at a low cost.It significantly enhances the training and testing phases of COD baselines,granting them robustness across diverse domains.Our newly generated datasets and source code are available at https://github.com/drlxj/CamDiff.
基金supported by the Youth Fund Project of the National Natural Science Foundation of China(62202064).
文摘Text-to-image(TTI)models provide huge innovation ability for many industries,while the content security triggered by them has also attracted wide attention.Considerable research has focused on content security threats of large language models(LLMs),yet comprehensive studies on the content security of TTI models are notably scarce.This paper introduces a systematic tool,named EvilPromptFuzzer,designed to fuzz evil prompts in TTI models.For 15 kinds of fne-grained risks,EvilPromptFuzzer employs the strong knowledge-mining ability of LLMs to construct seed banks,in which the seeds cover various types of characters,interrelations,actions,objects,expressions,body parts,locations,surroundings,etc.Subsequently,these seeds are fed into the LLMs to build scene-diverse prompts,which can weaken the semantic sensitivity related to the fne-grained risks.Hence,the prompts can bypass the content audit mechanism of the TTI model,and ultimately help to generate images with inappropriate content.For the risks of violence,horrible,disgusting,animal cruelty,religious bias,political symbol,and extremism,the efciency of Evil-PromptFuzzer for generating inappropriate images based on DALL.E 3 are greater than 30%,namely,more than 30 generated images are malicious among 100 prompts.Specifcally,the efciency of horrible,disgusting,political sym-bols,and extremism up to 58%,64%,71%,and 50%,respectively.Additionally,we analyzed the vulnerability of exist-ing popular content audit platforms,including Amazon,Google,Azure,and Baidu.Even the most efective Google SafeSearch cloud platform identifes only 33.85%of malicious images across three distinct categories.
