{"list":"other","total":198,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"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":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1804.06872","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","created":"2018-04-18","cited_by_count":1059},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2110.14795","title":"MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification","created":"2021-10-27","cited_by_count":690},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1712.05055","title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","created":"2017-12-14","cited_by_count":653},{"id":"1609.02943","title":"Stealing Machine Learning Models via Prediction APIs","created":"2016-09-09","cited_by_count":619},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","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":"1902.06531","title":"STRIP: A Defence Against Trojan Attacks on Deep Neural Networks","created":"2019-02-18","cited_by_count":459},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"2309.07875","title":"Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions","created":"2023-09-14","cited_by_count":387},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"1802.04633","title":"Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring","created":"2018-02-13","cited_by_count":357},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"1702.07464","title":"Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning","created":"2017-02-24","cited_by_count":334},{"id":"2101.05930","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","created":"2021-01-15","cited_by_count":324},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321},{"id":"1812.02766","title":"Knockoff Nets: Stealing Functionality of Black-Box Models","created":"2018-12-06","cited_by_count":292},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263},{"id":"1801.02610","title":"Generating Adversarial Examples with Adversarial Networks","created":"2018-01-08","cited_by_count":258},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"id":"1909.08072","title":"Adversarial Attacks and Defenses in Images, Graphs and Text: A Review","created":"2019-09-17","cited_by_count":237},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230},{"id":"1909.01838","title":"High Accuracy and High Fidelity Extraction of Neural Networks","created":"2019-09-03","cited_by_count":214},{"id":"2010.14925","title":"MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis","created":"2020-10-28","cited_by_count":206},{"id":"1711.10098","title":"Attentive Generative Adversarial Network for Raindrop Removal from a Single Image","created":"2017-11-28","cited_by_count":204},{"id":"1801.02612","title":"Spatially Transformed Adversarial Examples","created":"2018-01-08","cited_by_count":195},{"id":"1807.05852","title":"Machine Learning with Membership Privacy using Adversarial Regularization","created":"2018-07-16","cited_by_count":186},{"id":"2309.11751","title":"How Robust is Google's Bard to Adversarial Image Attacks?","created":"2023-09-21","cited_by_count":183},{"id":"1506.02753","title":"Inverting Visual Representations with Convolutional Networks","created":"2015-06-09","cited_by_count":170},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167},{"id":"1805.02628","title":"PRADA: Protecting against DNN Model Stealing Attacks","created":"2018-05-07","cited_by_count":165},{"id":"2009.02276","title":"Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching","created":"2020-09-04","cited_by_count":163},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"1909.01285","title":"Robust Invisible Video Watermarking with Attention","created":"2019-09-03","cited_by_count":149},{"id":"2002.12200","title":"Entangled Watermarks as a Defense against Model Extraction","created":"2020-02-27","cited_by_count":149},{"id":"1910.12366","title":"Thieves on Sesame Street! Model Extraction of BERT-based APIs","created":"2019-10-27","cited_by_count":139},{"id":"1811.00741","title":"Stronger Data Poisoning Attacks Break Data Sanitization Defenses","created":"2018-11-02","cited_by_count":135},{"id":"2306.01953","title":"Invisible Image Watermarks Are Provably Removable Using Generative AI","created":"2023-06-02","cited_by_count":134},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134},{"id":"1905.05897","title":"Transferable Clean-Label Poisoning Attacks on Deep Neural Nets","created":"2019-05-15","cited_by_count":131},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125},{"id":"2011.14779","title":"Data-Free Model Extraction","created":"2020-11-30","cited_by_count":124},{"id":"2404.01099","title":"What is in Your Safe Data? Identifying Benign Data that Breaks Safety","created":"2024-04-01","cited_by_count":118},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115},{"id":"2312.07913","title":"A Survey of Text Watermarking in the Era of Large Language Models","created":"2023-12-13","cited_by_count":112},{"id":"2406.06443","title":"LLM Dataset Inference: Did you train on my dataset?","created":"2024-06-10","cited_by_count":110},{"id":"2312.03262","title":"Low-Cost High-Power Membership Inference Attacks","created":"2023-12-06","cited_by_count":107},{"id":"1911.08718","title":"Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN","created":"2019-11-20","cited_by_count":103},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103},{"id":"1906.00830","title":"DAWN: Dynamic Adversarial Watermarking of Neural Networks","created":"2019-06-03","cited_by_count":100},{"id":"2005.03161","title":"MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation","created":"2020-05-06","cited_by_count":99},{"id":"2308.13320","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","created":"2023-08-25","cited_by_count":96},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96},{"id":"2407.21720","title":"Detecting, Explaining, and Mitigating Memorization in Diffusion Models","created":"2024-07-31","cited_by_count":95},{"id":"2402.09154","title":"Attacking Large Language Models with Projected Gradient Descent","created":"2024-02-14","cited_by_count":94},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93},{"id":"2405.18641","title":"Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-05-28","cited_by_count":92},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90},{"id":"2011.09527","title":"Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff","created":"2020-11-18","cited_by_count":89},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84},{"id":"2201.08135","title":"Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges","created":"2022-01-20","cited_by_count":84},{"id":"2407.07403","title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","created":"2024-07-10","cited_by_count":84},{"id":"1910.00744","title":"Reverse-Engineering Deep ReLU Networks","created":"2019-10-02","cited_by_count":83},{"id":"1906.10908","title":"Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks","created":"2019-06-26","cited_by_count":81},{"id":"2406.20053","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","created":"2024-06-28","cited_by_count":80},{"id":"2201.10787","title":"Variational Model Inversion Attacks","created":"2022-01-26","cited_by_count":75},{"id":"2206.08451","title":"I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences","created":"2022-06-16","cited_by_count":75},{"id":"2408.09600","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","created":"2024-08-18","cited_by_count":72},{"id":"2312.00273","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","created":"2023-12-01","cited_by_count":71},{"id":"1806.05476","title":"Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data","created":"2018-06-14","cited_by_count":70},{"id":"2108.04974","title":"SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)","created":"2021-08-11","cited_by_count":69},{"id":"2003.04884","title":"Cryptanalytic Extraction of Neural Network Models","created":"2020-03-10","cited_by_count":68},{"id":"2010.04092","title":"Knowledge-Enriched Distributional Model Inversion Attacks","created":"2020-10-08","cited_by_count":67},{"id":"2110.08324","title":"Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture","created":"2021-10-15","cited_by_count":67},{"id":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64},{"id":"2509.26354","title":"Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents","created":"2025-09-30","cited_by_count":62},{"id":"2204.11022","title":"Towards Data-Free Model Stealing in a Hard Label Setting","created":"2022-04-23","cited_by_count":58},{"id":"1911.07100","title":"Defending Against Model Stealing Attacks with Adaptive Misinformation","created":"2019-11-16","cited_by_count":57}],"next_cursor":"100"}