{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"2305.13860","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","created":"2023-05-23","cited_by_count":498},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2310.12815","title":"Formalizing and Benchmarking Prompt Injection Attacks and Defenses","created":"2023-10-19","cited_by_count":364},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278},{"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":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"2307.08715","title":"MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots","created":"2023-07-16","cited_by_count":183},{"id":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2403.17710","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","created":"2024-03-26","cited_by_count":143},{"id":"1910.12366","title":"Thieves on Sesame Street! Model Extraction of BERT-based APIs","created":"2019-10-27","cited_by_count":139},{"id":"2402.13494","title":"GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis","created":"2024-02-21","cited_by_count":96},{"id":"2411.00348","title":"Attention Tracker: Detecting Prompt Injection Attacks in LLMs","created":"2024-11-01","cited_by_count":95},{"id":"2302.03162","title":"Protecting Language Generation Models via Invisible Watermarking","created":"2023-02-06","cited_by_count":90},{"id":"2302.09462","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","created":"2023-02-19","cited_by_count":89},{"id":"2303.13379","title":"Practical and Ethical Challenges of Large Language Models in Education: A Systematic Scoping Review","created":"2023-03-17","cited_by_count":83},{"id":"2004.15015","title":"Imitation Attacks and Defenses for Black-box Machine Translation Systems","created":"2020-04-30","cited_by_count":81},{"id":"2209.08773","title":"CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks","created":"2022-09-19","cited_by_count":76},{"id":"2310.12505","title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models","created":"2023-10-19","cited_by_count":76},{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75},{"id":"2405.03003","title":"Parameter-Efficient Fine-Tuning with Discrete Fourier Transform","created":"2024-05-05","cited_by_count":71},{"id":"2209.02128","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","created":"2022-09-05","cited_by_count":69},{"id":"2305.10036","title":"Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark","created":"2023-05-17","cited_by_count":67},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66},{"id":"2311.09127","title":"Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts","created":"2023-11-15","cited_by_count":65},{"id":"2305.14950","title":"Adversarial Demonstration Attacks on Large Language Models","created":"2023-05-24","cited_by_count":63},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63},{"id":"2311.11538","title":"Assessing Prompt Injection Risks in 200+ Custom GPTs","created":"2023-11-20","cited_by_count":55},{"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":"2203.01584","title":"Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models","created":"2022-03-03","cited_by_count":47},{"id":"2403.08424","title":"Distract Large Language Models for Automatic Jailbreak Attack","created":"2024-03-13","cited_by_count":45},{"id":"2403.14473","title":"The Ethics of ChatGPT in Medicine and Healthcare: A Systematic Review on Large Language Models (LLMs)","created":"2024-03-21","cited_by_count":45},{"id":"2308.06013","title":"Large Language Models for Telecom: Forthcoming Impact on the Industry","created":"2023-08-11","cited_by_count":44},{"id":"2310.12439","title":"PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models","created":"2023-10-19","cited_by_count":42},{"id":"2401.16765","title":"A Cross-Language Investigation into Jailbreak Attacks in Large Language Models","created":"2024-01-30","cited_by_count":41},{"id":"2402.11755","title":"SPML: A DSL for Defending Language Models Against Prompt Attacks","created":"2024-02-19","cited_by_count":34},{"id":"2402.00898","title":"An Early Categorization of Prompt Injection Attacks on Large Language Models","created":"2024-01-31","cited_by_count":30},{"id":"2309.10544","title":"Model Leeching: An Extraction Attack Targeting LLMs","created":"2023-09-19","cited_by_count":22},{"id":"1703.01220","title":"Denoising Adversarial Autoencoders","created":"2017-03-03","cited_by_count":20},{"id":"2312.10982","title":"A Comprehensive Survey of Attack Techniques, Implementation, and Mitigation Strategies in Large Language Models","created":"2023-12-18","cited_by_count":14},{"id":"2404.02637","title":"Vocabulary Attack to Hijack Large Language Model Applications","created":"2024-04-03","cited_by_count":12},{"id":"2311.01283","title":"Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition","created":"2023-11-02","cited_by_count":3},{"id":"2408.07364","title":"Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation","created":"2024-08-14","cited_by_count":1}],"next_cursor":null}