{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"1805.12185","title":"Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks","created":"2018-05-30","cited_by_count":580},{"id":"1811.00636","title":"Spectral Signatures in Backdoor Attacks","created":"2018-11-01","cited_by_count":484},{"id":"1811.03728","title":"Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering","created":"2018-11-09","cited_by_count":456},{"id":"1910.00033","title":"Hidden Trigger Backdoor Attacks","created":"2019-09-30","cited_by_count":371},{"id":"2012.03816","title":"Invisible Backdoor Attack with Sample-Specific Triggers","created":"2020-12-07","cited_by_count":353},{"id":"2007.02343","title":"Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks","created":"2020-07-05","cited_by_count":349},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"1706.03691","title":"Certified Defenses for Data Poisoning Attacks","created":"2017-06-09","cited_by_count":303},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263},{"id":"1902.11237","title":"A new Backdoor Attack in CNNs by training set corruption without label poisoning","created":"2019-02-12","cited_by_count":242},{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235},{"id":"1804.00308","title":"Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning","created":"2018-04-01","cited_by_count":225},{"id":"1910.03137","title":"Detecting AI Trojans Using Meta Neural Analysis","created":"2019-10-08","cited_by_count":199},{"id":"1708.08689","title":"Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization","created":"2017-08-29","cited_by_count":197},{"id":"2003.03030","title":"Clean-Label Backdoor Attacks on Video Recognition Models","created":"2020-03-06","cited_by_count":169},{"id":"2009.02276","title":"Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching","created":"2020-09-04","cited_by_count":163},{"id":"2307.16888","title":"Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection","created":"2023-07-31","cited_by_count":157},{"id":"1710.00942","title":"Neural Trojans","created":"2017-10-03","cited_by_count":153},{"id":"1812.00292","title":"SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems","created":"2018-12-02","cited_by_count":152},{"id":"2003.03675","title":"Dynamic Backdoor Attacks Against Machine Learning Models","created":"2020-03-07","cited_by_count":151},{"id":"2106.09667","title":"Poisoning and Backdooring Contrastive Learning","created":"2021-06-17","cited_by_count":151},{"id":"1901.04407","title":"Self-Driving Cars: A Survey","created":"2019-01-14","cited_by_count":148},{"id":"1906.10842","title":"Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs","created":"2019-06-26","cited_by_count":146},{"id":"1808.10307","title":"Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation","created":"2018-08-30","cited_by_count":134},{"id":"2005.00060","title":"Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness","created":"2020-04-30","cited_by_count":132},{"id":"1908.00686","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","created":"2019-08-02","cited_by_count":124},{"id":"1908.01763","title":"TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems","created":"2019-08-02","cited_by_count":122},{"id":"2004.00225","title":"MetaPoison: Practical General-purpose Clean-label Data Poisoning","created":"2020-04-01","cited_by_count":120},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116},{"id":"2002.03018","title":"Certified Robustness to Label-Flipping Attacks via Randomized Smoothing","created":"2020-02-07","cited_by_count":108},{"id":"2102.05123","title":"Backdoor Scanning for Deep Neural Networks through K-Arm Optimization","created":"2021-02-09","cited_by_count":98},{"id":"1911.07116","title":"Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy","created":"2019-11-16","cited_by_count":95},{"id":"2007.15802","title":"Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases","created":"2020-07-31","cited_by_count":95},{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","cited_by_count":94},{"id":"2303.05762","title":"TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets","created":"2023-03-10","cited_by_count":88},{"id":"1910.04749","title":"Defending Neural Backdoors via Generative Distribution Modeling","created":"2019-10-10","cited_by_count":84},{"id":"1608.08182","title":"Data Poisoning Attacks on Factorization-Based Collaborative Filtering","created":"2016-08-29","cited_by_count":83},{"id":"2002.11497","title":"On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping","created":"2020-02-26","cited_by_count":83},{"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":"2012.07006","title":"DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation","created":"2020-12-13","cited_by_count":77},{"id":"2304.12298","title":"BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT","created":"2023-02-21","cited_by_count":76},{"id":"1803.00992","title":"Label Sanitization against Label Flipping Poisoning Attacks","created":"2018-03-02","cited_by_count":73},{"id":"2002.08025","title":"Influence Function based Data Poisoning Attacks to Top-N Recommender Systems","created":"2020-02-19","cited_by_count":63},{"id":"1809.04127","title":"Poisoning Attacks to Graph-Based Recommender Systems","created":"2018-09-11","cited_by_count":56},{"id":"1709.06692","title":"A Voting-Based System for Ethical Decision Making","created":"2017-09-20","cited_by_count":55},{"id":"1703.01340","title":"Generative Poisoning Attack Method Against Neural Networks","created":"2017-03-03","cited_by_count":52},{"id":"1908.02203","title":"Model Agnostic Defence against Backdoor Attacks in Machine Learning","created":"2019-08-06","cited_by_count":52},{"id":"2106.03408","title":"Antipodes of Label Differential Privacy: PATE and ALIBI","created":"2021-06-07","cited_by_count":52},{"id":"1911.07399","title":"NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations","created":"2019-11-18","cited_by_count":50},{"id":"2105.01622","title":"Poisoning the Unlabeled Dataset of Semi-Supervised Learning","created":"2021-05-04","cited_by_count":44},{"id":"2202.06382","title":"Training with More Confidence: Mitigating Injected and Natural Backdoors During Training","created":"2022-02-13","cited_by_count":38},{"id":"2106.06469","title":"Topological Detection of Trojaned Neural Networks","created":"2021-06-11","cited_by_count":34},{"id":"1306.6294","title":"Learning Trajectory Preferences for Manipulators via Iterative Improvement","created":"2013-06-26","cited_by_count":31},{"id":"2201.02873","title":"LoMar: A Local Defense Against Poisoning Attack on Federated Learning","created":"2022-01-08","cited_by_count":31},{"id":"2004.03728","title":"Practical Data Poisoning Attack against Next-Item Recommendation","created":"2020-04-07","cited_by_count":29},{"id":"2310.18933","title":"Label Poisoning is All You Need","created":"2023-10-29","cited_by_count":29},{"id":"2003.08633","title":"Backdooring and Poisoning Neural Networks with Image-Scaling Attacks","created":"2020-03-19","cited_by_count":28},{"id":"2007.00711","title":"ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks","created":"2020-07-01","cited_by_count":28},{"id":"2009.02326","title":"CLEANN: Accelerated Trojan Shield for Embedded Neural Networks","created":"2020-09-04","cited_by_count":22},{"id":"2012.01557","title":"Value Alignment Verification","created":"2020-12-02","cited_by_count":20},{"id":"1708.08327","title":"Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features","created":"2017-08-28","cited_by_count":18},{"id":"2202.07183","title":"A Survey of Neural Trojan Attacks and Defenses in Deep Learning","created":"2022-02-15","cited_by_count":17},{"id":"1904.04098","title":"A Survey of Distributed Consensus Protocols for Blockchain Networks","created":"2019-04-08","cited_by_count":16},{"id":"2207.01982","title":"Defending against the Label-flipping Attack in Federated Learning","created":"2022-07-05","cited_by_count":16},{"id":"2103.10274","title":"TOP: Backdoor Detection in Neural Networks via Transferability of Perturbation","created":"2021-03-18","cited_by_count":13},{"id":"1906.08805","title":"Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning","created":"2019-06-20","cited_by_count":12},{"id":"1603.07292","title":"Debugging Machine Learning Tasks","created":"2016-03-23","cited_by_count":10},{"id":"2303.14601","title":"PORE: Provably Robust Recommender Systems against Data Poisoning Attacks","created":"2023-03-26","cited_by_count":10},{"id":"2011.02526","title":"Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection","created":"2020-11-04","cited_by_count":9},{"id":"2008.00047","title":"Towards Class-Oriented Poisoning Attacks Against Neural Networks","created":"2020-07-31","cited_by_count":8},{"id":"1908.10498","title":"Detection of Backdoors in Trained Classifiers Without Access to the Training Set","created":"2019-08-27","cited_by_count":7},{"id":"2202.12154","title":"Towards Effective and Robust Neural Trojan Defenses via Input Filtering","created":"2022-02-24","cited_by_count":7},{"id":"2209.01721","title":"An Adaptive Black-box Defense against Trojan Attacks (TrojDef)","created":"2022-09-05","cited_by_count":5},{"id":"2209.03540","title":"Reward Delay Attacks on Deep Reinforcement Learning","created":"2022-09-08","cited_by_count":5},{"id":"2112.05612","title":"Decentralized Spectrum Access System: Vision, Challenges, and a Blockchain Solution","created":"2021-12-10","cited_by_count":4},{"id":"2307.01073","title":"What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?","created":"2023-07-03","cited_by_count":3},{"id":"2002.08912","title":"Modeling the Impact of Network Connectivity on Consensus Security of Proof-of-Work Blockchain","created":"2020-02-20","cited_by_count":2},{"id":"2105.13347","title":"Security and Privacy in the Emerging Cyber-Physical World: A Survey","created":"2021-05-27","cited_by_count":2},{"id":"2110.11411","title":"PROVES: Establishing Image Provenance using Semantic Signatures","created":"2021-10-21","cited_by_count":2},{"id":"1904.07275","title":"PrivacyGuard: Enforcing Private Data Usage Control with Blockchain and Attested Off-chain Contract Execution","created":"2019-04-15","cited_by_count":1}],"next_cursor":null}