{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"1609.02943","title":"Stealing Machine Learning Models via Prediction APIs","created":"2016-09-09","cited_by_count":619},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285},{"id":"1705.09064","title":"MagNet: a Two-Pronged Defense against Adversarial Examples","created":"2017-05-25","cited_by_count":269},{"id":"1911.07135","title":"The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks","created":"2019-11-17","cited_by_count":246},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234},{"id":"2205.12628","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","created":"2022-05-25","cited_by_count":200},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158},{"id":"2403.04957","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","created":"2024-03-07","cited_by_count":119},{"id":"2108.13888","title":"Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning","created":"2021-08-31","cited_by_count":113},{"id":"2103.15543","title":"Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models","created":"2021-03-29","cited_by_count":105},{"id":"2110.07831","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","created":"2021-10-15","cited_by_count":104},{"id":"2403.05156","title":"On Protecting the Data Privacy of Large Language Models (LLMs): A Survey","created":"2024-03-08","cited_by_count":96},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95},{"id":"2305.01219","title":"Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models","created":"2023-05-02","cited_by_count":94},{"id":"2008.00312","title":"Trojaning Language Models for Fun and Profit","created":"2020-08-01","cited_by_count":90},{"id":"2105.00164","title":"Hidden Backdoors in Human-Centric Language Models","created":"2021-05-01","cited_by_count":90},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88},{"id":"2305.18354","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations","created":"2023-05-26","cited_by_count":82},{"id":"2402.18649","title":"A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems","created":"2024-02-28","cited_by_count":77},{"id":"2402.17840","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","created":"2024-02-27","cited_by_count":76},{"id":"2206.08451","title":"I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences","created":"2022-06-16","cited_by_count":75},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72},{"id":"2402.16459","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","created":"2024-02-26","cited_by_count":70},{"id":"2311.13647","title":"Language Model Inversion","created":"2023-11-22","cited_by_count":68},{"id":"2401.00287","title":"The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness","created":"2023-12-30","cited_by_count":67},{"id":"2306.01684","title":"Harnessing large-language models to generate private synthetic text","created":"2023-06-02","cited_by_count":65},{"id":"2103.06819","title":"TAG: Gradient Attack on Transformer-based Language Models","created":"2021-03-11","cited_by_count":63},{"id":"2211.14719","title":"BadPrompt: Backdoor Attacks on Continuous Prompts","created":"2022-11-27","cited_by_count":63},{"id":"2310.03016","title":"Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions","created":"2023-10-04","cited_by_count":63},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57},{"id":"2202.08827","title":"LAMP: Extracting Text from Gradients with Language Model Priors","created":"2022-02-17","cited_by_count":54},{"id":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54},{"id":"2401.07612","title":"Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications","created":"2024-01-15","cited_by_count":54},{"id":"2310.19737","title":"Adversarial Attacks and Defenses in Large Language Models: Old and New Threats","created":"2023-10-30","cited_by_count":49},{"id":"2308.14367","title":"A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networks","created":"2023-08-28","cited_by_count":42},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37},{"id":"2405.07932","title":"PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition","created":"2024-05-13","cited_by_count":35},{"id":"2403.04801","title":"Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs","created":"2024-03-05","cited_by_count":33},{"id":"2209.10505","title":"Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers","created":"2022-09-21","cited_by_count":31},{"id":"2310.01424","title":"Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey","created":"2023-09-27","cited_by_count":30},{"id":"2401.12192","title":"Text Embedding Inversion Security for Multilingual Language Models","created":"2024-01-22","cited_by_count":26},{"id":"2309.10544","title":"Model Leeching: An Extraction Attack Targeting LLMs","created":"2023-09-19","cited_by_count":22},{"id":"2404.07242","title":"Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs","created":"2024-04-09","cited_by_count":20},{"id":"2311.07621","title":"To Transformers and Beyond: Large Language Models for the Genome","created":"2023-11-13","cited_by_count":15},{"id":"2406.00240","title":"Exploring Vulnerabilities and Protections in Large Language Models: A Survey","created":"2024-06-01","cited_by_count":11},{"id":"2302.07735","title":"Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge","created":"2023-02-13","cited_by_count":8},{"id":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8}],"next_cursor":null}