{"total":32,"rows":[{"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,"area":null},{"id":"2310.17626","title":"A Survey on Transferability of Adversarial Examples across Deep Neural Networks","created":"2023-10-26","cited_by_count":44,"area":null},{"id":"2406.10280","title":"Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries","created":"2024-06-12","cited_by_count":25,"area":null},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2303.04729","title":"Stealing the Decoding Algorithms of Language Models","created":"2023-03-08","cited_by_count":19,"area":null},{"id":"2506.22521","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","created":"2025-06-26","cited_by_count":19,"area":null},{"id":"2108.13873","title":"Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs","created":"2021-08-29","cited_by_count":18,"area":null},{"id":"2203.10378","title":"On Robust Prefix-Tuning for Text Classification","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2205.01094","title":"A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictions","created":"2022-05-01","cited_by_count":15,"area":null},{"id":"2201.07406","title":"Fooling MOSS Detection with Pretrained Language Models","created":"2022-01-19","cited_by_count":12,"area":null},{"id":"2403.01472","title":"WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection","created":"2024-03-03","cited_by_count":12,"area":null},{"id":"2411.07536","title":"Model Stealing for Any Low-Rank Language Model","created":"2024-11-12","cited_by_count":9,"area":null},{"id":"2105.10909","title":"Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs","created":"2021-05-23","cited_by_count":8,"area":null},{"id":"2302.02023","title":"TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification","created":"2023-02-03","cited_by_count":8,"area":null},{"id":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2410.11182","title":"A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2304.11300","title":"MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion","created":"2023-04-22","cited_by_count":7,"area":null},{"id":"2409.04459","title":"WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks","created":"2024-08-29","cited_by_count":7,"area":null},{"id":"2311.04588","title":"Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection","created":"2023-11-08","cited_by_count":6,"area":null},{"id":"2109.05793","title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","created":"2021-09-13","cited_by_count":5,"area":null},{"id":"2211.04205","title":"Preserving Semantics in Textual Adversarial Attacks","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2306.05083","title":"Revealing the Blind Spot of Sentence Encoder Evaluation by HEROS","created":"2023-06-08","cited_by_count":5,"area":null},{"id":"2602.20419","title":"CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2203.11849","title":"A Girl Has A Name, And It's ... Adversarial Authorship Attribution for Deobfuscation","created":"2022-03-22","cited_by_count":3,"area":null},{"id":"2206.07164","title":"Edge Security: Challenges and Issues","created":"2022-06-14","cited_by_count":3,"area":null},{"id":"2409.15868","title":"Privacy Evaluation Benchmarks for NLP Models","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2403.05365","title":"The Impact of Quantization on the Robustness of Transformer-based Text Classifiers","created":"2024-03-08","cited_by_count":2,"area":null},{"id":"2507.21750","title":"Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2408.02140","title":"VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2211.16044","title":"Model Extraction Attack against Self-supervised Speech Models","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2311.17722","title":"SenTest: Evaluating Robustness of Sentence Encoders","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2608.26982","title":"JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}