{"list":"other","total":89,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"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":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1511.04599","title":"DeepFool: a simple and accurate method to fool deep neural networks","created":"2015-11-14","cited_by_count":1318},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1511.07528","title":"The Limitations of Deep Learning in Adversarial Settings","created":"2015-11-24","cited_by_count":790},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"1711.00851","title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","created":"2017-11-02","cited_by_count":567},{"id":"1711.00117","title":"Countering Adversarial Images using Input Transformations","created":"2017-10-31","cited_by_count":520},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"1802.03471","title":"Certified Robustness to Adversarial Examples with Differential Privacy","created":"2018-02-09","cited_by_count":468},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"1812.05271","title":"TextBugger: Generating Adversarial Text Against Real-world Applications","created":"2018-12-13","cited_by_count":381},{"id":"2310.10501","title":"NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails","created":"2023-10-16","cited_by_count":365},{"id":"1805.06605","title":"Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models","created":"2018-05-17","cited_by_count":362},{"id":"2004.01970","title":"BAE: BERT-based Adversarial Examples for Text Classification","created":"2020-04-04","cited_by_count":316},{"id":"2110.01691","title":"AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts","created":"2021-10-04","cited_by_count":268},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"1703.00410","title":"Detecting Adversarial Samples from Artifacts","created":"2017-03-01","cited_by_count":245},{"id":"2212.09611","title":"Optimizing Prompts for Text-to-Image Generation","created":"2022-12-19","cited_by_count":207},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187},{"id":"1905.12843","title":"Fair Regression: Quantitative Definitions and Reduction-based Algorithms","created":"2019-05-30","cited_by_count":168},{"id":"1909.00986","title":"Certified Robustness to Adversarial Word Substitutions","created":"2019-09-03","cited_by_count":168},{"id":"1905.11268","title":"Combating Adversarial Misspellings with Robust Word Recognition","created":"2019-05-27","cited_by_count":163},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2010.06121","title":"To be Robust or to be Fair: Towards Fairness in Adversarial Training","created":"2020-10-13","cited_by_count":137},{"id":"2009.07502","title":"Contextualized Perturbation for Textual Adversarial Attack","created":"2020-09-16","cited_by_count":136},{"id":"2310.13345","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","created":"2023-10-20","cited_by_count":116},{"id":"1705.02498","title":"A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions","created":"2017-05-06","cited_by_count":108},{"id":"2302.03162","title":"Protecting Language Generation Models via Invisible Watermarking","created":"2023-02-06","cited_by_count":90},{"id":"2103.01592","title":"A Comprehensive Study on Face Recognition Biases Beyond Demographics","created":"2021-03-02","cited_by_count":86},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84},{"id":"1803.06975","title":"Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks","created":"2018-03-19","cited_by_count":81},{"id":"2109.00544","title":"Towards Improving Adversarial Training of NLP Models","created":"2021-09-01","cited_by_count":79},{"id":"2402.18649","title":"A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems","created":"2024-02-28","cited_by_count":77},{"id":"2209.08773","title":"CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks","created":"2022-09-19","cited_by_count":76},{"id":"2309.14459","title":"Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces","created":"2023-09-25","cited_by_count":72},{"id":"1708.09537","title":"DolphinAtack: Inaudible Voice Commands","created":"2017-08-31","cited_by_count":69},{"id":"1909.09552","title":"Defending Against Physically Realizable Attacks on Image Classification","created":"2019-09-20","cited_by_count":66},{"id":"2108.09135","title":"PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier","created":"2021-08-20","cited_by_count":65},{"id":"1802.09653","title":"On the Suitability of $L_p$-norms for Creating and Preventing Adversarial Examples","created":"2018-02-27","cited_by_count":58},{"id":"1511.05122","title":"Adversarial Manipulation of Deep Representations","created":"2015-11-16","cited_by_count":56},{"id":"2311.18140","title":"ROBBIE: Robust Bias Evaluation of Large Generative Language Models","created":"2023-11-29","cited_by_count":53},{"id":"2309.10254","title":"LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins","created":"2023-09-19","cited_by_count":51},{"id":"2002.12398","title":"TSS: Transformation-Specific Smoothing for Robustness Certification","created":"2020-02-27","cited_by_count":49},{"id":"2209.01390","title":"How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models","created":"2022-09-03","cited_by_count":44},{"id":"2404.00405","title":"A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration","created":"2024-03-30","cited_by_count":38},{"id":"2006.14042","title":"Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks","created":"2020-06-24","cited_by_count":37},{"id":"2111.09999","title":"TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems","created":"2021-11-19","cited_by_count":36},{"id":"2404.02319","title":"Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization","created":"2024-04-02","cited_by_count":30},{"id":"2102.02956","title":"DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks","created":"2021-02-05","cited_by_count":29},{"id":"2110.15317","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","created":"2021-10-28","cited_by_count":28},{"id":"2001.02479","title":"Dark Patterns after the GDPR: Scraping Consent Pop-ups and Demonstrating their Influence","created":"2020-01-08","cited_by_count":27},{"id":"2402.08030","title":"Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking","created":"2024-02-12","cited_by_count":26},{"id":"1909.02638","title":"(Un)informed Consent: Studying GDPR Consent Notices in the Field","created":"2019-09-05","cited_by_count":23},{"id":"1912.01799","title":"Addressing Marketing Bias in Product Recommendations","created":"2019-12-04","cited_by_count":23},{"id":"2212.10563","title":"BLIND: Bias Removal With No Demographics","created":"2022-12-20","cited_by_count":22},{"id":"2006.11946","title":"Light Commands: Laser-Based Audio Injection Attacks on Voice-Controllable Systems","created":"2020-06-22","cited_by_count":18},{"id":"1703.06857","title":"On the Limitation of Convolutional Neural Networks in Recognizing Negative Images","created":"2017-03-20","cited_by_count":17},{"id":"2208.08232","title":"HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models","created":"2022-08-17","cited_by_count":17},{"id":"2311.11225","title":"TextGuard: Provable Defense against Backdoor Attacks on Text Classification","created":"2023-11-19","cited_by_count":16},{"id":"2101.04843","title":"What Makes a Dark Pattern... Dark? Design Attributes, Normative Considerations, and Measurement Methods","created":"2021-01-13","cited_by_count":15},{"id":"1710.03135","title":"Stack Overflow Considered Harmful? The Impact of Copy&Paste on Android Application Security","created":"2017-10-09","cited_by_count":12},{"id":"1802.06806","title":"Divide, Denoise, and Defend against Adversarial Attacks","created":"2018-02-19","cited_by_count":12},{"id":"2305.14716","title":"GlobalBench: A Benchmark for Global Progress in Natural Language Processing","created":"2023-05-24","cited_by_count":9},{"id":"2308.13904","title":"LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors","created":"2023-08-26","cited_by_count":9},{"id":"1908.10048","title":"Multiple Purposes, Multiple Problems: A User Study of Consent Dialogs after GDPR","created":"2019-08-27","cited_by_count":6},{"id":"1706.10220","title":"6thSense: A Context-aware Sensor-based Attack Detector for Smart Devices","created":"2017-06-30","cited_by_count":5},{"id":"1810.10109","title":"Et Tu Alexa? When Commodity WiFi Devices Turn into Adversarial Motion Sensors","created":"2018-10-23","cited_by_count":4},{"id":"2112.14232","title":"Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks","created":"2021-12-28","cited_by_count":4},{"id":"2312.03577","title":"Improving Bias Mitigation through Bias Experts in Natural Language Understanding","created":"2023-12-06","cited_by_count":2},{"id":"2306.16614","title":"Group-based Robustness: A General Framework for Customized Robustness in the Real World","created":"2023-06-29","cited_by_count":1},{"id":"2405.08832","title":"Theorizing Deception: A Scoping Review of Theory in Research on Dark Patterns and Deceptive Design","created":"2024-05-14","cited_by_count":1}],"next_cursor":null}