Fetching the paper…
Reading the bibliography…
Adversarial prompts are capable of jailbreaking frontier large language models (LLMs) and inducing undesirable behaviours, posing a significant obstacle to their safe deployment.
Calculus: an intuitive and physical approach
Morris Kline · 1998
Earlier work this paper cites.
Lof: identifying density-based local outliers
Markus M Breunig, Hans-Peter Kriegel, Raymond T Ng, and Jörg Sander · 2000
Earlier work this paper cites.
Maximum likelihood estimation of intrinsic dimension
Elizaveta Levina and Peter Bickel · 2004
Earlier work this paper cites.
Elementary differential geometry
Barrett O’Neill · 2006
Earlier work this paper cites.
Isolation forest
Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou · 2008
Earlier work this paper cites.
Principal component analysis
Hervé Abdi and Lynne J Williams · 2010
Earlier work this paper cites.
Efficient estimation of word representations in vector space
Tomas Mikolov · 2013
Earlier work this paper cites.
Intriguing properties of neural networks
C Szegedy · 2013
Earlier work this paper cites.
Estimating local intrinsic dimensionality
Laurent Amsaleg, Oussama Chelly, Teddy Furon, Stéphane Girard, Michael E Houle, Ken-ichi Kawarabayashi, and Michael Nett · 2015
Earlier work this paper cites.
Improving distributional similarity with lessons learned from word embeddings
Omer Levy, Yoav Goldberg, and Ido Dagan · 2015
Earlier work this paper cites.
Measuring word significance using distributed representations of words
Adriaan MJ Schakel and Benjamin J Wilson · 2015
Earlier work this paper cites.
Differential geometry: a first course in curves and surfaces
Theodore Shifrin · 2015
Earlier work this paper cites.
Estimating the intrinsic dimension of datasets by a minimal neighborhood information
Elena Facco, Maria d’Errico, Alex Rodriguez, and Alessandro Laio · 2017
Earlier work this paper cites.
Local intrinsic dimensionality i: an extreme-value-theoretic foundation for similarity applications
Michael E Houle · 2017
Earlier work this paper cites.
Bert: Pre-training of deep bidirectional transformers for language understanding
Jacob Devlin · 2018
Earlier work this paper cites.
Characterizing adversarial subspaces using local intrinsic dimensionality
Xingjun Ma, Bo Li, Yisen Wang, Sarah M Erfani, Sudanthi Wijewickrema, Grant Schoenebeck, Dawn Song, Michael E Houle, and James Bailey · 2018
Earlier work this paper cites.
Intrinsic dimension of data representations in deep neural networks
Alessio Ansuini, Alessandro Laio, Jakob H Macke, and Davide Zoccolan · 2019
Earlier work this paper cites.
On the intrinsic dimensionality of image representations
Sixue Gong, Vishnu Naresh Boddeti, and Anil K Jain · 2019
Earlier work this paper cites.
Adversarial examples are not bugs, they are features
Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, and Aleksander Madry · 2019
Earlier work this paper cites.
Language models are unsupervised multitask learners
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al · 2019
Earlier work this paper cites.
Visualizing and measuring the geometry of bert
Emily Reif, Ann Yuan, Martin Wattenberg, Fernanda B Viegas, Andy Coenen, Adam Pearce, and Been Kim · 2019
Earlier work this paper cites.
Generating natural language adversarial examples through probability weighted word saliency
Shuhuai Ren, Yihe Deng, Kun He, and Wanxiang Che · 2019
Earlier work this paper cites.
Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter
V Sanh · 2019
Earlier work this paper cites.
Universal adversarial triggers for attacking and analyzing nlp
Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, and Sameer Singh · 2019
Earlier work this paper cites.
Xlnet: Generalized autoregressive pretraining for language understanding
Zhilin Yang · 2019
Earlier work this paper cites.
Language models are few-shot learners
Tom B Brown · 2020
Earlier work this paper cites.
Measuring massive multitask language understanding
Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt · 2020
Earlier work this paper cites.
Truthfulqa: Measuring how models mimic human falsehoods
Stephanie Lin, Jacob Hilton, and Owain Evans · 2021
Earlier work this paper cites.
Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned
Deep Ganguli, Liane Lovitt, Jackson Kernion, Amanda Askell, Yuntao Bai, Saurav Kadavath, Ben Mann, Ethan Perez, Nicholas Schiefer, Kamal Ndousse, et al · 2022
Earlier work this paper cites.
Lidl: Local intrinsic dimension estimation using approximate likelihood
Piotr Tempczyk, Rafał Michaluk, Lukasz Garncarek, Przemysław Spurek, Jacek Tabor, and Adam Golinski · 2022
Earlier work this paper cites.
Glm-130b: An open bilingual pre-trained model
Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, et al · 2022
Earlier work this paper cites.
Adversarial training for high-stakes reliability
Daniel Ziegler, Seraphina Nix, Lawrence Chan, Tim Bauman, Peter Schmidt-Nielsen, Tao Lin, Adam Scherlis, Noa Nabeshima, Benjamin Weinstein-Raun, Daniel de Haas, et al · 2022
Cited alongside, same era.
Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al · 2023
Cited alongside, same era.
Detecting language model attacks with perplexity
Gabriel Alon and Michael Kamfonas · 2023
Cited alongside, same era.
Paul M Alsing and Carlo Cafaro · 2023
Cited alongside, same era.
Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher
Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Pinjia He, Shuming Shi, and Zhaopeng Tu · 2023
Later among the works it cites.
Universal and transferable adversarial attacks on aligned language models
Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J Zico Kolter, and Matt Fredrikson · 2023
Later among the works it cites.
Llama 3 model card
AI@Meta · 2024
Later among the works it cites.
Jailbreaking leading safety-aligned llms with simple adaptive attacks
Maksym Andriushchenko, Francesco Croce, and Nicolas Flammarion · 2024
Later among the works it cites.
Many-shot jailbreaking
Cem Anil, Esin Durmus, Mrinank Sharma, Joe Benton, Sandipan Kundu, Joshua Batson, Nina Rimsky, Meg Tong, Jesse Mu, Daniel Ford, et al · 2024
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Rohan Anil, Andrew M Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, et al · 2023
Cited alongside, same era.
Defending against alignment-breaking attacks via robustly aligned llm
Bochuan Cao, Yuanpu Cao, Lu Lin, and Jinghui Chen · 2023
Cited alongside, same era.
Jailbreaking black box large language models in twenty queries
Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J Pappas, and Eric Wong · 2023
Cited alongside, same era.
Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality
Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al · 2023
Cited alongside, same era.
How robust is google’s bard to adversarial image attacks?
Yinpeng Dong, Huanran Chen, Jiawei Chen, Zhengwei Fang, Xiao Yang, Yichi Zhang, Yu Tian, Hang Su, and Jun Zhu · 2023
Cited alongside, same era.
Haizelabs/llama3-jailbreak: A trivial programmatic llama 3 jailbreak. sorry zuck!, 2023
Haizelabs · 2023
Cited alongside, same era.
Token-level adversarial prompt detection based on perplexity measures and contextual information
Zhengmian Hu, Gang Wu, Saayan Mitra, Ruiyi Zhang, Tong Sun, Heng Huang, and Vishy Swaminathan · 2023
Cited alongside, same era.
Trajectory planning in frenet frame via multi-objective optimization
Jianyu Huang, Zuguang He, Yutaka Arakawa, and Billy Dawton · 2023
Cited alongside, same era.
Deepseek llm: Scaling open-source language models with longtermism
Xiao Bi, Deli Chen, Guanting Chen, Shanhuang Chen, Damai Dai, Chengqi Deng, Honghui Ding, Kai Dong, Qiushi Du, Zhe Fu, et al · 2024
Later among the works it cites.
Play guessing game with llm: Indirect jailbreak attack with implicit clues
Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, and Yang Liu · 2024
Later among the works it cites.
Humans or llms as the judge? a study on judgement biases
Guiming Hardy Chen, Shunian Chen, Ziche Liu, Feng Jiang, and Benyou Wang · 2024
Later among the works it cites.
Comprehensive assessment of jailbreak attacks against llms
Junjie Chu, Yugeng Liu, Ziqing Yang, Xinyue Shen, Michael Backes, and Yang Zhang · 2024
Later among the works it cites.
Or-bench: An over-refusal benchmark for large language models
Justin Cui, Wei-Lin Chiang, Ion Stoica, and Cho-Jui Hsieh · 2024
Later among the works it cites.
Stay on track: A frenet wrapper to overcome off-road trajectories in vehicle motion prediction
Marcel Hallgarten, Ismail Kisa, Martin Stoll, and Andreas Zell · 2024
Later among the works it cites.
Xiaomeng Hu, Pin-Yu Chen, and Tsung-Yi Ho · 2024
Later among the works it cites.
Ldreg: Local dimensionality regularized self-supervised learning
Hanxun Huang, Ricardo JGB Campello, Sarah Monazam Erfani, Xingjun Ma, Michael E Houle, and James Bailey · 2024
Later among the works it cites.
Drattack: Prompt decomposition and reconstruction makes powerful llm jailbreakers
Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, and Cho-Jui Hsieh · 2024
Later among the works it cites.
Zeyi Liao and Huan Sun · 2024
Later among the works it cites.
Harmbench: A standardized evaluation framework for automated red teaming and robust refusal
Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, et al · 2024
Later among the works it cites.
Is llm-as-a-judge robust? investigating universal adversarial attacks on zero-shot llm assessment
Vyas Raina, Adian Liusie, and Mark Gales · 2024
Later among the works it cites.
Targeted latent adversarial training improves robustness to persistent harmful behaviors in llms
Abhay Sheshadri, Aidan Ewart, Phillip Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, et al · 2024
Later among the works it cites.
Gemma 2: Improving open language models at a practical size
Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, et al · 2024
Later among the works it cites.
Intrinsic dimension estimation for robust detection of ai-generated texts
Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Sergey Nikolenko, Evgeny Burnaev, Serguei Barannikov, and Irina Piontkovskaya · 2024
Later among the works it cites.
Selfdefend: Llms can defend themselves against jailbreaking in a practical manner
Xunguang Wang, Daoyuan Wu, Zhenlan Ji, Zongjie Li, Pingchuan Ma, Shuai Wang, Yingjiu Li, Yang Liu, Ning Liu, and Juergen Rahmel · 2024
Later among the works it cites.
Jailbroken: How does llm safety training fail?
Alexander Wei, Nika Haghtalab, and Jacob Steinhardt · 2024
Later among the works it cites.
A survey on large language model (llm) security and privacy: The good, the bad, and the ugly
Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, and Yue Zhang · 2024
Later among the works it cites.
Characterizing truthfulness in large language model generations with local intrinsic dimension
Fan Yin, Jayanth Srinivasa, and Kai-Wei Chang · 2024
Later among the works it cites.
Round trip translation defence against large language model jailbreaking attacks
Canaan Yung, Hadi Mohaghegh Dolatabadi, Sarah Erfani, and Christopher Leckie · 2024
Later among the works it cites.
Yi Zeng, Hongpeng Lin, Jingwen Zhang, Diyi Yang, Ruoxi Jia, and Weiyan Shi · 2024
Later among the works it cites.
Improving alignment and robustness with circuit breakers
Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, J Zico Kolter, Matt Fredrikson, and Dan Hendrycks · 2024
Later among the works it cites.
Detecting backdoor samples in contrastive language image pretraining
Hanxun Huang, Sarah Monazam Erfani, Yige Li, Xingjun Ma, and James Bailey · 2025
Closest in time.
Safety alignment should be made more than just a few tokens deep
Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, and Peter Henderson · 2025
Closest in time.
Mrinank Sharma, Meg Tong, Jesse Mu, Jerry Wei, Jorrit Kruthoff, Scott Goodfriend, Euan Ong, Alwin Peng, Raj Agarwal, Cem Anil, et al · 2025
Closest in time.