{"type":"ScholarlyArticle","title":"Safety of Multimodal Large Language Models on Images and Text","authors":[{"name":"Xin Liu","slug":"xin-liu","given":"Xin","family":"Liu","affiliation":"East China Normal University; Shanghai AI Laboratory"},{"name":"Yichen Zhu","slug":"yichen-zhu","given":"Yichen","family":"Zhu","affiliation":"Midea Group"},{"name":"Yunshi Lan","slug":"yunshi-lan","given":"Yunshi","family":"Lan","affiliation":"East China Normal University"},{"name":"Chao Yang","slug":"chao-yang","given":"Chao","family":"Yang","affiliation":"Shanghai AI Laboratory"},{"name":"Yu Qiao","slug":"yu-qiao","given":"Yu","family":"Qiao","affiliation":"Shanghai AI Laboratory"}],"abstract":"Attracted by the impressive power of Multimodal Large Language Models (MLLMs), the public is increasingly utilizing them to improve the efficiency of daily work. Nonetheless, the vulnerabilities of MLLMs to unsafe instructions bring huge safety risks when these models are deployed in real-world scenarios. In this paper, we systematically survey current efforts on the evaluation, attack, and defense of MLLMs' safety on images and text. We begin with introducing the overview of MLLMs on images and text and understanding of safety, which helps researchers know the detailed scope of our survey. Then, we review the evaluation datasets and metrics for measuring the safety of MLLMs. Next, we comprehensively present attack and defense techniques related to MLLMs' safety. Finally, we analyze several unsolved issues and discuss promising research directions. The relevant papers are collected at \"https://github.com/isXinLiu/Awesome-MLLM-Safety\".","doi":"10.24963/ijcai.2024/901","url":"https://ijcai.org/proceedings/2024/901","pdf":"https://ijcai.org/proceedings/2024/0901.pdf","markdown":"https://ijcai.org/proceedings/2024/901.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/901","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Survey Track","track":"Survey Track","number":901,"pages":{"first":8151,"last":8159},"keywords":["AI Ethics, Trust, Fairness: ETF: Safety and robustness","AI Ethics, Trust, Fairness: General"],"videos":[],"references":[{"position":1,"raw":"[Askell et al., 2021] Amanda Askell, Yuntao Bai, et al. A general language assistant as a laboratory for alignment. arXiv preprint arXiv:2112.00861, 2021.","title":"A general language assistant as a laboratory for alignment","authors":"Amanda Askell, Yuntao Bai","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bagdasaryan et al., 2023] Eugene Bagdasaryan, Tsung-Yin Hsieh, Ben Nassi, and Vitaly Shmatikov. Abusing Im- ages and Sounds for Indirect Instruction Injection in Multi- Modal LLMs. arXiv preprint, page arXiv:2307.10490, 2023.","title":"Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs","authors":"Eugene Bagdasaryan, Tsung-Yin Hsieh, Ben Nassi, Vitaly Shmatikov","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bailey et al., 2023] Luke Bailey, Euan Ong, Stuart Russell, and Scott Emmons. Image Hijacks: Adversarial Im- ages can Control Generative Models at Runtime. arXiv preprint, page arXiv:2309.00236, 2023.","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","authors":"Bailey","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cai et al., 2019] Yitao Cai, Huiyu Cai, and Xiaojun Wan. Multi-modal sarcasm detection in Twitter with hierarchical fusion model. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2506-2515, 2019.","title":"Multi-modal sarcasm detection in Twitter with hierarchical fusion model","authors":"Cai","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Carlini et al., 2023] Nicholas Carlini, Milad Nasr, Christo- pher A. Choquette-Choo, Matthew Jagielski, Irena Gao, Pang Wei Koh, Daphne Ippolito, Florian Tramèr, and Lud- wig Schmidt. Are aligned neural networks adversarially aligned? In Thirty-seventh Conference on Neural Infor- mation Processing Systems, 2023.","title":"Are aligned neural networks adversarially aligned?","authors":"Nicholas Carlini, Milad Nasr, Christopher A Choquette-Choo, Matthew Jagielski, Irena Gao, Pang Wei Koh, Daphne Ippolito, Florian Tramèr, Ludwig Schmidt","year":"2023","venue":"Thirty-seventh Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2023a] Yang Chen, Hexiang Hu, Yi Luan, Haitian Sun, Soravit Changpinyo, Alan Ritter, and Ming- Wei Chang. Can pre-trained vision and language models answer visual information-seeking questions? In Proceed- ings of the 2023 Conference on Empirical Methods in Nat- ural Language Processing, pages 14948-14968, 2023.","title":"Can pre-trained vision and language models answer visual information-seeking questions?","authors":"Chen","year":"2023","venue":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2023b] Yang Chen, Ethan Mendes, Sauvik Das, Wei Xu, and Alan Ritter. Can language models be in- structed to protect personal information? arXiv preprint arXiv:2310.02224, 2023.","title":"Can language models be instructed to protect personal information","authors":"Chen","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2023c] Yangyi Chen, Karan Sikka, Michael Cogswell, Heng Ji, and Ajay Divakaran. Dress: Instruct- ing large vision-language models to align and interact with humans via natural language feedback. arXiv preprint arXiv:2311.10081, 2023.","title":"Dress: Instructing large vision-language models to align and interact with humans via natural language feedback","authors":"Chen","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dong et al., 2023] Yinpeng Dong, Huanran Chen, Jiawei Chen, Zhengwei Fang, Xiao Yang, Yichi Zhang, Yu Tian, Hang Su, and Jun Zhu. How robust is google's bard to ad- versarial image attacks? In R0-FoMo:Robustness of Few- shot and Zero-shot Learning in Large Foundation Models, 2023. [Fersini et al., 2022] Elisabetta Fersini, Francesca Gasparini, Giulia Rizzi, Aurora Saibene, Berta Chulvi, Paolo Rosso, Alyssa Lees, and Jeffrey Sorensen. SemEval-2022 task 5: Multimedia automatic misogyny identification. In Pro- ceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 533-549, 2022.","title":"How robust is google's bard to adversarial image attacks? In R0-FoMo:Robustness of Fewshot and Zero-shot Learning in Large Foundation Models","authors":"Dong","year":"2022","venue":"Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fu et al., 2023] Xiaohan Fu, Zihan Wang, Shuheng Li, Ra- jesh K. Gupta, Niloofar Mireshghallah, Taylor Berg- Kirkpatrick, and Earlence Fernandes. Misusing Tools in Large Language Models With Visual Adversarial Exam- ples. arXiv preprint, page arXiv:2310.03185, 2023.","title":"Misusing Tools in Large Language Models With Visual Adversarial Examples","authors":"Xiaohan Fu, Zihan Wang, Shuheng Li, Rajesh K Gupta, Niloofar Mireshghallah, Taylor Berg-Kirkpatrick, Earlence Fernandes","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gong et al., 2023] Yichen Gong, Delong Ran, Jinyuan Liu, Conglei Wang, Tianshuo Cong, Anyu Wang, Sisi Duan, and Xiaoyun Wang. Figstep: Jailbreaking large vision- language models via typographic visual prompts. arXiv preprint arXiv:2311.05608, 2023.","title":"Figstep: Jailbreaking large visionlanguage models via typographic visual prompts","authors":"Yichen Gong, Jinyuan Delong Ran, Conglei Liu, Tianshuo Wang, Anyu Cong, Sisi Wang, Xiaoyun Duan, Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ji et al., 2023a] Jiaming Ji, Mickel Liu, Juntao Dai, Xuehai Pan, Chi Zhang, Ce Bian, Boyuan Chen, Ruiyang Sun, Yizhou Wang, and Yaodong Yang. Beavertails: Towards improved safety alignment of llm via a human-preference dataset. In Thirty-seventh Conference on Neural Informa- tion Processing Systems Datasets and Benchmarks Track, 2023.","title":"Beavertails: Towards improved safety alignment of llm via a human-preference dataset","authors":"Ji","year":"2023","venue":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ji et al., 2023b] Yuanfeng Ji, Chongjian Ge, Weikai Kong, Enze Xie, Zhengying Liu, Zhengguo Li, and Ping Luo. Large Language Models as Automated Aligners for benchmarking Vision-Language Models. arXiv preprint arXiv:2311.14580, 2023.","title":"Large Language Models as Automated Aligners for benchmarking Vision-Language Models","authors":"Ji","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kiela et al., 2020] Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. The hateful memes challenge: Detecting hate speech in multimodal memes. In Advances in Neural Information Processing Systems, pages 2611-2624, 2020.","title":"The hateful memes challenge: Detecting hate speech in multimodal memes","authors":"Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, Davide Testuggine","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2024] Mukai Li, Lei Li, Yuwei Yin, Masood Ahmed, Zhenguang Liu, and Qi Liu. Red teaming visual language models. arXiv preprint arXiv:2401.12915, 2024.","title":"Red teaming visual language models","authors":"Mukai Li, Lei Li, Yuwei Yin, Masood Ahmed, Zhenguang Liu, Qi Liu","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lin et al., 2014] Tsung-Yi Lin, Michael Maire, Serge Be- longie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. Microsoft coco: Com- mon objects in context. In Computer Vision -ECCV 2014, pages 740-755, 2014.","title":"Microsoft coco: Common objects in context","authors":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, C Lawrence Zitnick","year":"2014","venue":"Computer Vision -ECCV 2014","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lin et al., 2024] Hongzhan Lin, Ziyang Luo, Bo Wang, Ruichao Yang, and Jing Ma. Goat-bench: Safety insights to large multimodal models through meme-based social abuse. arXiv preprint arXiv:2401.01523, 2024.","title":"Goat-bench: Safety insights to large multimodal models through meme-based social abuse","authors":"Lin","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2023] Xin Liu, Yichen Zhu, Yunshi Lan, Chao Yang, and Yu Qiao. Query-relevant images jailbreak large multi-modal models. arXiv preprint arXiv:2311.17600, 2023.","title":"Query-relevant images jailbreak large multi-modal models","authors":"Xin Liu, Yichen Zhu, Yunshi Lan, Chao Yang, Yu Qiao","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Luo et al., 2024] Haochen Luo, Jindong Gu, Fengyuan Liu, and Philip Torr. An image is worth 1000 lies: Trans- ferability of adversarial images across prompts on vision- language models. In The Twelfth International Conference on Learning Representations, 2024.","title":"An image is worth 1000 lies: Transferability of adversarial images across prompts on visionlanguage models","authors":"Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr","year":"2024","venue":"The Twelfth International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Madry et al., 2018] Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial attacks. In International Conference on Learning Representations, 2018.","title":"Towards deep learning models resistant to adversarial attacks","authors":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pi et al., 2024] Renjie Pi, Tianyang Han, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, and Tong Zhang. Mllm-protector: Ensuring mllm's safety without hurting performance. arXiv preprint arXiv:2401.02906, 2024.","title":"Mllm-protector: Ensuring mllm's safety without hurting performance","authors":"Renjie Pi, Tianyang Han, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pramanick et al., 2021a] Shraman Pramanick, Dimi- tar Dimitrov, Rituparna Mukherjee, Shivam Sharma, Md. Shad Akhtar, Preslav Nakov, and Tanmoy Chakraborty. Detecting harmful memes and their targets. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2783-2796, 2021.","title":"Detecting harmful memes and their targets","authors":"Pramanick","year":"2021","venue":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pramanick et al., 2021b] Shraman Pramanick, Shivam Sharma, Dimitar Dimitrov, Md. Shad Akhtar, Preslav Nakov, and Tanmoy Chakraborty. MOMENTA: A multi- modal framework for detecting harmful memes and their targets. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4439-4455, 2021.","title":"MOMENTA: A multimodal framework for detecting harmful memes and their targets","authors":"Pramanick","year":"2021","venue":"Findings of the Association for Computational Linguistics: EMNLP 2021","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Qi et al., 2023] Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Mengdi Wang, and Prateek Mittal. Visual adver- sarial examples jailbreak aligned large language models. In The Second Workshop on New Frontiers in Adversarial Machine Learning, 2023.","title":"Visual adversarial examples jailbreak aligned large language models","authors":"Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Mengdi Wang, Prateek Mittal","year":"2023","venue":"The Second Workshop on New Frontiers in Adversarial Machine Learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Qi et al., 2024] Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson. Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth Interna- tional Conference on Learning Representations, 2024.","title":"Fine-tuning aligned language models compromises safety, even when users do not intend to!","authors":"Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, Peter Henderson","year":"2024","venue":"The Twelfth International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Rafailov et al., 2023] Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D Manning, and Chelsea Finn. Direct preference optimization: Your lan- guage model is secretly a reward model. arXiv preprint arXiv:2305.18290, 2023.","title":"Direct preference optimization: Your language model is secretly a reward model","authors":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D Manning, Chelsea Finn","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Röttger et al., 2023] Paul Röttger, Hannah Rose Kirk, et al. Xstest: A test suite for identifying exaggerated safety behaviours in large language models. arXiv preprint arXiv:2308.01263, 2023.","title":"Xstest: A test suite for identifying exaggerated safety behaviours in large language models","authors":"Paul Röttger, Hannah Rose Kirk","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Schlarmann and Hein, 2023] Christian Schlarmann and Matthias Hein. On the adversarial robustness of multi-modal foundation models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, pages 3677-3685, 2023.","title":"Christian Schlarmann and Matthias Hein. On the adversarial robustness of multi-modal foundation models","authors":"Hein Schlarmann","year":"2023","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Shah et al., 2019] Sanket Shah, Anand Mishra, et al. Kvqa: Knowledge-aware visual question answering. In AAAI Conference on Artificial Intelligence, 2019.","title":"Kvqa: Knowledge-aware visual question answering","authors":"Sanket Shah, Anand Mishra","year":"2019","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Shayegani et al., 2023] Erfan Shayegani, Yue Dong, and Nael Abu-Ghazaleh. Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models. arXiv preprint arXiv:2307.14539, 2023.","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","authors":"Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Sun et al., 2023] Hao Sun, Zhexin Zhang, et al. Safety as- sessment of chinese large language models. arXiv preprint arXiv:2304.10436, 2023.","title":"Safety assessment of chinese large language models","authors":"Zhexin Hao Sun, Zhang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Sun et al., 2024] Lichao Sun, Yue Huang, et al. Trustllm: Trustworthiness in large language models. arXiv preprint arXiv:2401.05561, 2024.","title":"Trustllm: Trustworthiness in large language models","authors":"Sun","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Suryawanshi et al., 2020] Shardul Suryawanshi, Bharathi Raja Chakravarthi, et al. Multimodal meme dataset (MultiOFF) for identifying offensive content in image and text. In Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying, pages 32-41, 2020.","title":"Multimodal meme dataset (MultiOFF) for identifying offensive content in image and text","authors":"Shardul Suryawanshi, Bharathi Raja Chakravarthi","year":"2020","venue":"Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Tu et al., 2023] Haoqin Tu, Chenhang Cui, et al. How Many Unicorns Are in This Image? A Safety Evalua- tion Benchmark for Vision LLMs. arXiv preprint, page arXiv:2311.16101, 2023.","title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","authors":"Tu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Van and Wu, 2023] Minh-Hao Van and Xintao Wu. De- tecting and correcting hate speech in multimodal memes with large visual language model. arXiv preprint arXiv:2311.06737, 2023.","title":"Detecting and correcting hate speech in multimodal memes with large visual language model","authors":"Wu Van, Minh-Hao Van, Xintao Wu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Vatsa et al., 2023] Mayank Vatsa, Anubhooti Jain, and Richa Singh. Adventures of trustworthy vision-language models: A survey. arXiv preprint arXiv:2312.04231, 2023.","title":"Adventures of trustworthy vision-language models: A survey","authors":"Mayank Vatsa, Anubhooti Jain, Richa Singh","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wang et al., 2023] Xinpeng Wang, Xiaoyuan Yi, et al. Tovi- lag: Your visual-language generative model is also an evil- doer. In The 2023 Conference on Empirical Methods in Natural Language Processing, 2023.","title":"Tovilag: Your visual-language generative model is also an evildoer","authors":"Wang","year":"2023","venue":"The 2023 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Wang et al., 2024] Pengyu Wang, Dong Zhang, et al. Inferaligner: Inference-time alignment for harmless- ness through cross-model guidance. arXiv preprint arXiv:2401.11206, 2024.","title":"Inferaligner: Inference-time alignment for harmlessness through cross-model guidance","authors":"Pengyu Wang, Dong Zhang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Welbl et al., 2021] Johannes Welbl, Amelia Glaese, et al. Challenges in detoxifying language models. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2447-2469, 2021.","title":"Challenges in detoxifying language models","authors":"Welbl","year":"2021","venue":"Findings of the Association for Computational Linguistics: EMNLP 2021","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Won et al., 2017] Donghyeon Won, Zachary C. Steinert- Threlkeld, et al. Protest activity detection and perceived violence estimation from social media images. In Proceed- ings of the 25th ACM International Conference on Multi- media, page 786-794, 2017.","title":"Protest activity detection and perceived violence estimation from social media images","authors":"Won","year":"2017","venue":"Proceedings of the 25th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Wu et al., 2023] Yuanwei Wu, Xiang Li, et al. Jailbreaking gpt-4v via self-adversarial attacks with system prompts. arXiv preprint arXiv:2311.09127, 2023.","title":"Jailbreaking gpt-4v via self-adversarial attacks with system prompts","authors":"Wu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Yuan et al., 2023] Lifan Yuan, YiChi Zhang, et al. Bridge the gap between CV and NLP! a gradient-based textual ad- versarial attack framework. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7132- 7146, 2023.","title":"Bridge the gap between CV and NLP! a gradient-based textual adversarial attack framework","authors":"Lifan Yuan, Yichi Zhang","year":"2023","venue":"Findings of the Association for Computational Linguistics: ACL 2023","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Zhang et al., 2023] Zhexin Zhang, Leqi Lei, et al. Safe- tybench: Evaluating the safety of large language mod- els with multiple choice questions. arXiv preprint arXiv:2309.07045, 2023.","title":"Safetybench: Evaluating the safety of large language models with multiple choice questions","authors":"Zhang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Zhu et al., 2024] Yichen Zhu, Minjie Zhu, et al. Llava-ϕ: Efficient multi-modal assistant with small language model. arXiv preprint arXiv:2401.02330, 2024.","title":"Llava-ϕ: Efficient multi-modal assistant with small language model","authors":"Yichen Zhu, Minjie Zhu","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}