{"list":"other","total":52,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294},{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247},{"id":"1909.01838","title":"High Accuracy and High Fidelity Extraction of Neural Networks","created":"2019-09-03","cited_by_count":214},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116},{"id":"1909.05193","title":"TBT: Targeted Neural Network Attack with Bit Trojan","created":"2019-09-10","cited_by_count":113},{"id":"1903.12269","title":"Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search","created":"2019-03-28","cited_by_count":108},{"id":"2402.13494","title":"GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis","created":"2024-02-21","cited_by_count":96},{"id":"2310.05424","title":"Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding","created":"2023-10-09","cited_by_count":80},{"id":"2403.00867","title":"Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes","created":"2024-03-01","cited_by_count":74},{"id":"1805.12233","title":"How Important Is a Neuron?","created":"2018-05-30","cited_by_count":73},{"id":"2312.04916","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","created":"2023-12-08","cited_by_count":69},{"id":"1906.01017","title":"Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks","created":"2019-06-03","cited_by_count":57},{"id":"2003.13746","title":"DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips","created":"2020-03-30","cited_by_count":56},{"id":"2111.04625","title":"DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories","created":"2021-11-08","cited_by_count":42},{"id":"2208.13049","title":"TrojViT: Trojan Insertion in Vision Transformers","created":"2022-08-27","cited_by_count":31},{"id":"2402.15180","title":"Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement","created":"2024-02-23","cited_by_count":29},{"id":"2101.08254","title":"RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery","created":"2021-01-20","cited_by_count":18},{"id":"2302.13520","title":"Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks","created":"2023-02-27","cited_by_count":17},{"id":"2308.07934","title":"One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training","created":"2023-08-12","cited_by_count":14},{"id":"2207.12405","title":"Versatile Weight Attack via Flipping Limited Bits","created":"2022-07-25","cited_by_count":13},{"id":"1710.00551","title":"Another Flip in the Wall of Rowhammer Defenses","created":"2017-10-02","cited_by_count":12},{"id":"2004.01807","title":"TRRespass: Exploiting the Many Sides of Target Row Refresh","created":"2020-04-03","cited_by_count":11},{"id":"2103.13813","title":"RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy","created":"2021-03-22","cited_by_count":11},{"id":"1511.08756","title":"DRAMA: Exploiting DRAM Addressing for Cross-CPU Attacks","created":"2015-11-27","cited_by_count":10},{"id":"1507.06955","title":"Rowhammer.js: A Remote Software-Induced Fault Attack in JavaScript","created":"2015-07-24","cited_by_count":9},{"id":"2111.01932","title":"HASHTAG: Hash Signatures for Online Detection of Fault-Injection Attacks on Deep Neural Networks","created":"2021-11-02","cited_by_count":9},{"id":"2110.10603","title":"Uncovering In-DRAM RowHammer Protection Mechanisms: A New Methodology, Custom RowHammer Patterns, and Implications","created":"2021-10-20","cited_by_count":7},{"id":"2110.07683","title":"Don't Knock! Rowhammer at the Backdoor of DNN Models","created":"2021-10-14","cited_by_count":6},{"id":"2102.05981","title":"BlockHammer: Preventing RowHammer at Low Cost by Blacklisting Rapidly-Accessed DRAM Rows","created":"2021-02-11","cited_by_count":4},{"id":"2310.14665","title":"Read Disturbance in High Bandwidth Memory: A Detailed Experimental Study on HBM2 DRAM Chips","created":"2023-10-23","cited_by_count":3}],"next_cursor":null}