{"list":"other","total":68,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1805.12185","title":"Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks","created":"2018-05-30","cited_by_count":580},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"1804.00792","title":"Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks","created":"2018-04-03","cited_by_count":519},{"id":"1811.00636","title":"Spectral Signatures in Backdoor Attacks","created":"2018-11-01","cited_by_count":484},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"2010.08138","title":"Input-Aware Dynamic Backdoor Attack","created":"2020-10-16","cited_by_count":313},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"2011.10369","title":"ONION: A Simple and Effective Defense Against Textual Backdoor Attacks","created":"2020-11-20","cited_by_count":263},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222},{"id":"2307.16888","title":"Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection","created":"2023-07-31","cited_by_count":157},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2007.02220","title":"You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion","created":"2020-07-05","cited_by_count":131},{"id":"2311.14455","title":"Universal Jailbreak Backdoors from Poisoned Human Feedback","created":"2023-11-24","cited_by_count":128},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116},{"id":"2406.03007","title":"BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents","created":"2024-06-05","cited_by_count":115},{"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":"1901.05415","title":"Learning from Dialogue after Deployment: Feed Yourself, Chatbot!","created":"2019-01-16","cited_by_count":102},{"id":"2403.13355","title":"BadEdit: Backdooring large language models by model editing","created":"2024-03-20","cited_by_count":96},{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","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":"2007.12070","title":"Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identification","created":"2020-07-11","cited_by_count":86},{"id":"2111.00197","title":"Backdoor Pre-trained Models Can Transfer to All","created":"2021-10-30","cited_by_count":86},{"id":"2110.02467","title":"BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models","created":"2021-10-06","cited_by_count":85},{"id":"2112.05224","title":"Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures","created":"2021-12-09","cited_by_count":73},{"id":"1911.10312","title":"Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks","created":"2019-11-23","cited_by_count":71},{"id":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66},{"id":"2301.02344","title":"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models","created":"2023-01-06","cited_by_count":60},{"id":"2204.05239","title":"Exploring the Universal Vulnerability of Prompt-based Learning Paradigm","created":"2022-04-11","cited_by_count":57},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53},{"id":"2101.06969","title":"Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks","created":"2021-01-18","cited_by_count":49},{"id":"2006.06841","title":"Backdoors in Neural Models of Source Code","created":"2020-06-11","cited_by_count":41},{"id":"2307.16489","title":"BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models","created":"2023-07-31","cited_by_count":37},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35},{"id":"2308.04451","title":"Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks","created":"2023-08-04","cited_by_count":33},{"id":"2401.04136","title":"The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline","created":"2024-01-07","cited_by_count":33},{"id":"2302.04116","title":"Training-free Lexical Backdoor Attacks on Language Models","created":"2023-02-08","cited_by_count":31},{"id":"2304.14475","title":"ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger","created":"2023-04-27","cited_by_count":31},{"id":"2303.02242","title":"TrojText: Test-time Invisible Textual Trojan Insertion","created":"2023-03-03","cited_by_count":28},{"id":"2402.11725","title":"How Susceptible are Large Language Models to Ideological Manipulation?","created":"2024-02-18","cited_by_count":26},{"id":"2206.01832","title":"Kallima: A Clean-label Framework for Textual Backdoor Attacks","created":"2022-06-03","cited_by_count":24},{"id":"1604.06045","title":"Dialog-based Language Learning","created":"2016-04-20","cited_by_count":21},{"id":"1909.02742","title":"Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization","created":"2019-09-06","cited_by_count":18},{"id":"2407.04108","title":"Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs","created":"2024-07-04","cited_by_count":15},{"id":"2010.12563","title":"Concealed Data Poisoning Attacks on NLP Models","created":"2020-10-23","cited_by_count":14},{"id":"2310.18603","title":"Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers","created":"2023-10-28","cited_by_count":14},{"id":"2210.17029","title":"Poison Attack and Defense on Deep Source Code Processing Models","created":"2022-10-31","cited_by_count":11},{"id":"2312.10467","title":"TrojFSP: Trojan Insertion in Few-shot Prompt Tuning","created":"2023-12-16","cited_by_count":9},{"id":"2407.12281","title":"Turning Generative Models Degenerate: The Power of Data Poisoning Attacks","created":"2024-07-17","cited_by_count":9},{"id":"2405.15662","title":"Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning","created":"2024-05-24","cited_by_count":6},{"id":"2405.11466","title":"Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code","created":"2024-05-19","cited_by_count":4},{"id":"2311.17429","title":"TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4","created":"2023-11-29","cited_by_count":3},{"id":"2408.11587","title":"Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks","created":"2024-08-21","cited_by_count":2}],"next_cursor":null}