{"list":"other","total":100,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"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":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573},{"id":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2205.07460","title":"Diffusion Models for Adversarial Purification","created":"2022-05-16","cited_by_count":476},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2205.14987","title":"A Continuous Time Framework for Discrete Denoising Models","created":"2022-05-30","cited_by_count":451},{"id":"1902.06705","title":"On Evaluating Adversarial Robustness","created":"2019-02-18","cited_by_count":447},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"1906.04584","title":"Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers","created":"2019-06-09","cited_by_count":330},{"id":"1712.02976","title":"Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser","created":"2017-12-08","cited_by_count":329},{"id":"1810.12715","title":"On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models","created":"2018-10-30","cited_by_count":328},{"id":"1705.06640","title":"DeepXplore: Automated Whitebox Testing of Deep Learning Systems","created":"2017-05-18","cited_by_count":311},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"1804.09699","title":"Towards Fast Computation of Certified Robustness for ReLU Networks","created":"2018-04-25","cited_by_count":255},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211},{"id":"1801.02612","title":"Spatially Transformed Adversarial Examples","created":"2018-01-08","cited_by_count":195},{"id":"1705.08475","title":"Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation","created":"2017-05-23","cited_by_count":185},{"id":"2309.11751","title":"How Robust is Google's Bard to Adversarial Image Attacks?","created":"2023-09-21","cited_by_count":183},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172},{"id":"1909.00986","title":"Certified Robustness to Adversarial Word Substitutions","created":"2019-09-03","cited_by_count":168},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156},{"id":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156},{"id":"2211.00802","title":"Concrete Score Matching: Generalized Score Matching for Discrete Data","created":"2022-11-02","cited_by_count":148},{"id":"2206.10550","title":"(Certified!!) Adversarial Robustness for Free!","created":"2022-06-21","cited_by_count":132},{"id":"2405.21018","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","created":"2024-05-31","cited_by_count":110},{"id":"2205.14969","title":"Guided Diffusion Model for Adversarial Purification","created":"2022-05-30","cited_by_count":92},{"id":"2303.09105","title":"Rethinking Model Ensemble in Transfer-based Adversarial Attacks","created":"2023-03-16","cited_by_count":89},{"id":"1806.09030","title":"On Adversarial Examples for Character-Level Neural Machine Translation","created":"2018-06-23","cited_by_count":85},{"id":"2005.14424","title":"SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions","created":"2020-05-29","cited_by_count":73},{"id":"2406.01288","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","created":"2024-06-03","cited_by_count":70},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67},{"id":"1906.04948","title":"Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers","created":"2019-06-12","cited_by_count":65},{"id":"2303.09051","title":"Robust Evaluation of Diffusion-Based Adversarial Purification","created":"2023-03-16","cited_by_count":65},{"id":"1911.09272","title":"Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation","created":"2019-11-21","cited_by_count":60},{"id":"2403.12171","title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","created":"2024-03-18","cited_by_count":60},{"id":"2105.03743","title":"Certified Robustness to Text Adversarial Attacks by Randomized [MASK]","created":"2021-05-08","cited_by_count":57},{"id":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52},{"id":"1906.03805","title":"Improving Neural Language Modeling via Adversarial Training","created":"2019-06-10","cited_by_count":49},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44},{"id":"1804.03286","title":"On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses","created":"2018-04-10","cited_by_count":40},{"id":"2405.01229","title":"Boosting Jailbreak Attack with Momentum","created":"2024-05-02","cited_by_count":40},{"id":"2103.10834","title":"Improved, Deterministic Smoothing for L_1 Certified Robustness","created":"2021-03-17","cited_by_count":39},{"id":"2309.05950","title":"Language Models as Black-Box Optimizers for Vision-Language Models","created":"2023-09-12","cited_by_count":36},{"id":"2311.16124","title":"DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification","created":"2023-10-27","cited_by_count":36},{"id":"2402.02316","title":"Your Diffusion Model is Secretly a Certifiably Robust Classifier","created":"2024-02-04","cited_by_count":24},{"id":"2408.00315","title":"ADBM: Adversarial diffusion bridge model for reliable adversarial purification","created":"2024-08-01","cited_by_count":24},{"id":"1909.05822","title":"On the Hardness of Robust Classification","created":"2019-09-12","cited_by_count":23},{"id":"2206.09491","title":"On the Limitations of Stochastic Pre-processing Defenses","created":"2022-06-19","cited_by_count":21},{"id":"2003.10388","title":"Generating Natural Language Adversarial Examples on a Large Scale with Generative Models","created":"2020-03-10","cited_by_count":15},{"id":"2007.15220","title":"The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise","created":"2020-07-30","cited_by_count":15},{"id":"2405.18822","title":"Toxicity Detection for Free","created":"2024-05-29","cited_by_count":15},{"id":"2412.08615","title":"Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models","created":"2024-12-11","cited_by_count":15},{"id":"2402.05467","title":"Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia","created":"2024-02-08","cited_by_count":14},{"id":"2404.13752","title":"Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models","created":"2024-04-21","cited_by_count":12},{"id":"2411.14133","title":"GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs","created":"2024-11-21","cited_by_count":12},{"id":"2305.06522","title":"Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications","created":"2023-05-11","cited_by_count":11},{"id":"2410.22143","title":"AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts","created":"2024-10-29","cited_by_count":10},{"id":"2412.01547","title":"Improved Large Language Model Jailbreak Detection via Pretrained Embeddings","created":"2024-12-02","cited_by_count":10},{"id":"2309.16883","title":"The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing","created":"2023-09-28","cited_by_count":8},{"id":"2411.16782","title":"Scaling Laws for Black box Adversarial Attacks","created":"2024-11-25","cited_by_count":8},{"id":"2306.15164","title":"DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization","created":"2023-06-27","cited_by_count":7},{"id":"2405.04346","title":"Revisiting Character-level Adversarial Attacks for Language Models","created":"2024-05-07","cited_by_count":4}],"next_cursor":null}