{"list":"other","total":51,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"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":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"1805.12185","title":"Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks","created":"2018-05-30","cited_by_count":580},{"id":"1902.06531","title":"STRIP: A Defence Against Trojan Attacks on Deep Neural Networks","created":"2019-02-18","cited_by_count":459},{"id":"2012.03816","title":"Invisible Backdoor Attack with Sample-Specific Triggers","created":"2020-12-07","cited_by_count":353},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"1801.02613","title":"Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality","created":"2018-01-08","cited_by_count":282},{"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":"1905.12457","title":"A backdoor attack against LSTM-based text classification systems","created":"2019-05-29","cited_by_count":227},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222},{"id":"2006.01043","title":"BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements","created":"2020-06-01","cited_by_count":211},{"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":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153},{"id":"2402.11208","title":"Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents","created":"2024-02-17","cited_by_count":137},{"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":"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":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81},{"id":"2206.08514","title":"A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks","created":"2022-06-17","cited_by_count":74},{"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":"2101.03778","title":"Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection","created":"2021-01-11","cited_by_count":70},{"id":"2211.14719","title":"BadPrompt: Backdoor Attacks on Continuous Prompts","created":"2022-11-27","cited_by_count":63},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62},{"id":"2103.04264","title":"T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification","created":"2021-03-07","cited_by_count":60},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57},{"id":"2205.06900","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","created":"2022-05-13","cited_by_count":55},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53},{"id":"2011.14654","title":"Feature Space Singularity for Out-of-Distribution Detection","created":"2020-11-30","cited_by_count":49},{"id":"2205.08305","title":"A Study of the Attention Abnormality in Trojaned BERTs","created":"2022-05-13","cited_by_count":48},{"id":"2305.17826","title":"NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models","created":"2023-05-28","cited_by_count":37},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33},{"id":"2309.13256","title":"Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks","created":"2023-09-23","cited_by_count":33},{"id":"2303.02242","title":"TrojText: Test-time Invisible Textual Trojan Insertion","created":"2023-03-03","cited_by_count":28},{"id":"2205.03190","title":"Imperceptible Backdoor Attack: From Input Space to Feature Representation","created":"2022-05-06","cited_by_count":27},{"id":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27},{"id":"2401.17268","title":"Weaver: Foundation Models for Creative Writing","created":"2024-01-30","cited_by_count":27},{"id":"2305.02394","title":"Defending against Insertion-based Textual Backdoor Attacks via Attribution","created":"2023-05-03","cited_by_count":25},{"id":"2210.07907","title":"Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks","created":"2022-10-14","cited_by_count":19},{"id":"2305.16503","title":"IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks","created":"2023-05-25","cited_by_count":15},{"id":"2301.12715","title":"Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features","created":"2023-01-30","cited_by_count":12}],"next_cursor":null}