{"list":"other","total":86,"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"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":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"1511.07528","title":"The Limitations of Deep Learning in Adversarial Settings","created":"2015-11-24","cited_by_count":790},{"id":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"1611.02770","title":"Delving into Transferable Adversarial Examples and Black-box Attacks","created":"2016-11-08","cited_by_count":536},{"id":"1804.00792","title":"Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks","created":"2018-04-03","cited_by_count":519},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2404.01833","title":"Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack","created":"2024-04-02","cited_by_count":390},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387},{"id":"1910.00033","title":"Hidden Trigger Backdoor Attacks","created":"2019-09-30","cited_by_count":371},{"id":"2310.12815","title":"Formalizing and Benchmarking Prompt Injection Attacks and Defenses","created":"2023-10-19","cited_by_count":364},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2004.01970","title":"BAE: BERT-based Adversarial Examples for Text Classification","created":"2020-04-04","cited_by_count":316},{"id":"1806.02371","title":"Adversarial Attack on Graph Structured Data","created":"2018-06-06","cited_by_count":301},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284},{"id":"2007.08432","title":"Data Poisoning Attacks Against Federated Learning Systems","created":"2020-07-16","cited_by_count":275},{"id":"1801.01944","title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text","created":"2018-01-05","cited_by_count":274},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"1905.11268","title":"Combating Adversarial Misspellings with Robust Word Recognition","created":"2019-05-27","cited_by_count":163},{"id":"2009.02276","title":"Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching","created":"2020-09-04","cited_by_count":163},{"id":"2307.16888","title":"Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection","created":"2023-07-31","cited_by_count":157},{"id":"2307.01881","title":"ProPILE: Probing Privacy Leakage in Large Language Models","created":"2023-07-04","cited_by_count":129},{"id":"2307.10490","title":"Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs","created":"2023-07-19","cited_by_count":124},{"id":"2406.12814","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","created":"2024-06-18","cited_by_count":120},{"id":"2403.04957","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","created":"2024-03-07","cited_by_count":119},{"id":"2006.03463","title":"Sponge Examples: Energy-Latency Attacks on Neural Networks","created":"2020-06-05","cited_by_count":111},{"id":"2402.13457","title":"A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models","created":"2024-02-21","cited_by_count":106},{"id":"1903.11508","title":"Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems","created":"2019-03-27","cited_by_count":101},{"id":"2402.16914","title":"DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers","created":"2024-02-25","cited_by_count":101},{"id":"2311.06062","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","created":"2023-11-10","cited_by_count":98},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95},{"id":"2104.02361","title":"Backdoor Attack in the Physical World","created":"2021-04-06","cited_by_count":84},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74},{"id":"2302.04460","title":"Bag of Tricks for Training Data Extraction from Language Models","created":"2023-02-09","cited_by_count":70},{"id":"2404.12038","title":"Uncovering Safety Risks of Large Language Models through Concept Activation Vector","created":"2024-04-18","cited_by_count":67},{"id":"2402.12329","title":"Query-Based Adversarial Prompt Generation","created":"2024-02-19","cited_by_count":62},{"id":"1911.07140","title":"Black-Box Adversarial Attack with Transferable Model-based Embedding","created":"2019-11-17","cited_by_count":57},{"id":"2112.08331","title":"Model Stealing Attacks Against Inductive Graph Neural Networks","created":"2021-12-15","cited_by_count":50},{"id":"2402.09674","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","created":"2024-02-15","cited_by_count":50},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50},{"id":"2101.08030","title":"Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data","created":"2021-01-20","cited_by_count":45},{"id":"2403.08424","title":"Distract Large Language Models for Automatic Jailbreak Attack","created":"2024-03-13","cited_by_count":45},{"id":"2405.15012","title":"Extracting Prompts by Inverting LLM Outputs","created":"2024-05-23","cited_by_count":41},{"id":"2406.06822","title":"An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection","created":"2024-06-10","cited_by_count":40},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37},{"id":"2307.04401","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","created":"2023-07-10","cited_by_count":36},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34},{"id":"2403.04801","title":"Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs","created":"2024-03-05","cited_by_count":33},{"id":"2404.17196","title":"Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications","created":"2024-04-26","cited_by_count":33},{"id":"2103.11576","title":"Grey-box Adversarial Attack And Defence For Sentiment Classification","created":"2021-03-22","cited_by_count":28},{"id":"1808.08994","title":"Data Poisoning Attacks against Online Learning","created":"2018-08-27","cited_by_count":27},{"id":"1905.12032","title":"Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks","created":"2019-05-28","cited_by_count":26},{"id":"2108.09513","title":"A Hard Label Black-box Adversarial Attack Against Graph Neural Networks","created":"2021-08-21","cited_by_count":26},{"id":"2009.09560","title":"ES Attack: Model Stealing against Deep Neural Networks without Data Hurdles","created":"2020-09-21","cited_by_count":25},{"id":"2407.02943","title":"PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding","created":"2024-07-03","cited_by_count":24},{"id":"2312.04127","title":"Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak","created":"2023-12-07","cited_by_count":23},{"id":"2107.07240","title":"Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting","created":"2021-07-15","cited_by_count":21},{"id":"2302.09457","title":"Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective","created":"2023-02-19","cited_by_count":20},{"id":"2409.03363","title":"Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding","created":"2024-09-05","cited_by_count":20},{"id":"2406.00240","title":"Exploring Vulnerabilities and Protections in Large Language Models: A Survey","created":"2024-06-01","cited_by_count":11},{"id":"2412.04756","title":"ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models","created":"2024-12-06","cited_by_count":11},{"id":"2009.00163","title":"Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs","created":"2020-09-01","cited_by_count":6},{"id":"2405.20015","title":"Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak","created":"2024-05-30","cited_by_count":4},{"id":"2408.13985","title":"TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models","created":"2024-08-26","cited_by_count":2},{"id":"2010.10712","title":"Boosting Gradient for White-Box Adversarial Attacks","created":"2020-10-21","cited_by_count":1}],"next_cursor":null}