{"total":235,"rows":[{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"area":null},{"id":"2212.05400","title":"How to Backdoor Diffusion Models?","created":"2022-12-11","cited_by_count":104,"area":"diffusion"},{"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,"area":"safety"},{"id":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86,"area":null},{"id":"2208.03111","title":"Data-free Backdoor Removal based on Channel Lipschitzness","created":"2022-08-05","cited_by_count":79,"area":null},{"id":"2304.11823","title":"Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization","created":"2023-04-24","cited_by_count":64,"area":null},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63,"area":"safety"},{"id":"2305.14876","title":"Reconstructive Neuron Pruning for Backdoor Defense","created":"2023-05-24","cited_by_count":59,"area":null},{"id":"2310.14942","title":"Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand","created":"2023-10-09","cited_by_count":57,"area":null},{"id":"2303.15180","title":"Detecting Backdoors in Pre-trained Encoders","created":"2023-03-23","cited_by_count":55,"area":"safety"},{"id":"2202.05749","title":"Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense","created":"2022-02-11","cited_by_count":47,"area":"safety"},{"id":"2304.02786","title":"UNICORN: A Unified Backdoor Trigger Inversion Framework","created":"2023-04-05","cited_by_count":46,"area":null},{"id":"2303.12175","title":"Black-box Backdoor Defense via Zero-shot Image Purification","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2303.12993","title":"Backdoor Defense via Adaptively Splitting Poisoned Dataset","created":"2023-03-23","cited_by_count":43,"area":null},{"id":"2307.10562","title":"Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples","created":"2023-07-20","cited_by_count":43,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2202.06382","title":"Training with More Confidence: Mitigating Injected and Natural Backdoors During Training","created":"2022-02-13","cited_by_count":38,"area":null},{"id":"2306.16697","title":"Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features","created":"2023-06-29","cited_by_count":37,"area":null},{"id":"2201.13178","title":"Few-Shot Backdoor Attacks on Visual Object Tracking","created":"2022-01-31","cited_by_count":35,"area":null},{"id":"2408.07362","title":"BadMerging: Backdoor Attacks Against Model Merging","created":"2024-08-14","cited_by_count":34,"area":null},{"id":"2210.09194","title":"Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class","created":"2022-10-17","cited_by_count":33,"area":null},{"id":"2411.12768","title":"CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization","created":"2024-11-18","cited_by_count":33,"area":"safety"},{"id":"2310.01875","title":"Towards Stable Backdoor Purification through Feature Shift Tuning","created":"2023-10-03","cited_by_count":32,"area":null},{"id":"2207.04497","title":"One-shot Neural Backdoor Erasing via Adversarial Weight Masking","created":"2022-07-10","cited_by_count":28,"area":null},{"id":"2211.05638","title":"Untargeted Backdoor Attack against Object Detection","created":"2022-11-02","cited_by_count":28,"area":null},{"id":"2405.16134","title":"Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack","created":"2024-05-25","cited_by_count":28,"area":null},{"id":"2202.05189","title":"Understanding Rare Spurious Correlations in Neural Networks","created":"2022-02-10","cited_by_count":27,"area":null},{"id":"2205.03190","title":"Imperceptible Backdoor Attack: From Input Space to Feature Representation","created":"2022-05-06","cited_by_count":27,"area":null},{"id":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2302.01762","title":"BackdoorBox: A Python Toolbox for Backdoor Learning","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2409.05294","title":"TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors","created":"2024-09-09","cited_by_count":25,"area":"diffusion"},{"id":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24,"area":"safety"},{"id":"2302.12461","title":"Analyzing And Editing Inner Mechanisms Of Backdoored Language Models","created":"2023-02-24","cited_by_count":23,"area":"safety"},{"id":"2204.01186","title":"Revisiting a kNN-based Image Classification System with High-capacity Storage","created":"2022-04-03","cited_by_count":22,"area":null},{"id":"2405.16534","title":"Pruning for Robust Concept Erasing in Diffusion Models","created":"2024-05-26","cited_by_count":22,"area":"diffusion"},{"id":"2207.10825","title":"Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation","created":"2022-07-22","cited_by_count":20,"area":null},{"id":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2306.06209","title":"Backdoor Attack with Sparse and Invisible Trigger","created":"2023-05-11","cited_by_count":20,"area":null},{"id":"2401.15295","title":"Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks","created":"2024-01-27","cited_by_count":19,"area":null},{"id":"2407.19845","title":"BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning","created":"2024-07-29","cited_by_count":19,"area":null},{"id":"2305.18651","title":"UMD: Unsupervised Model Detection for X2X Backdoor Attacks","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2308.04466","title":"Backdoor Federated Learning by Poisoning Backdoor-Critical Layers","created":"2023-08-08","cited_by_count":18,"area":null},{"id":"2202.07183","title":"A Survey of Neural Trojan Attacks and Defenses in Deep Learning","created":"2022-02-15","cited_by_count":17,"area":null},{"id":"2211.12044","title":"Backdoor Cleansing with Unlabeled Data","created":"2022-11-22","cited_by_count":17,"area":null},{"id":"2202.10627","title":"On the Effectiveness of Adversarial Training against Backdoor Attacks","created":"2022-02-22","cited_by_count":16,"area":null},{"id":"2302.01677","title":"Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2205.11819","title":"Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2301.06241","title":"BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense","created":"2023-01-16","cited_by_count":15,"area":null},{"id":"2202.05470","title":"Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers","created":"2022-02-11","cited_by_count":14,"area":null},{"id":"2312.08890","title":"Defenses in Adversarial Machine Learning: A Survey","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2402.01920","title":"Preference Poisoning Attacks on Reward Model Learning","created":"2024-02-02","cited_by_count":14,"area":"alignment"},{"id":"2410.13910","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2206.08477","title":"Backdoor Attacks on Vision Transformers","created":"2022-06-16","cited_by_count":13,"area":"safety"},{"id":"2211.15929","title":"Backdoor Vulnerabilities in Normally Trained Deep Learning Models","created":"2022-11-29","cited_by_count":13,"area":null},{"id":"2310.17498","title":"CBD: A Certified Backdoor Detector Based on Local Dominant Probability","created":"2023-10-26","cited_by_count":13,"area":null},{"id":"2403.17188","title":"LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning","created":"2024-03-25","cited_by_count":13,"area":null},{"id":"2407.21316","title":"Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models","created":"2024-07-31","cited_by_count":13,"area":"diffusion"},{"id":"2201.13329","title":"Can Adversarial Training Be Manipulated By Non-Robust Features?","created":"2022-01-31","cited_by_count":12,"area":null},{"id":"2210.06428","title":"Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork","created":"2022-10-12","cited_by_count":12,"area":null},{"id":"2412.07277","title":"Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger","created":"2024-12-10","cited_by_count":12,"area":null},{"id":"2412.20392","title":"Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning","created":"2024-12-29","cited_by_count":12,"area":"safety"},{"id":"2202.06312","title":"Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks","created":"2022-02-13","cited_by_count":11,"area":null},{"id":"2307.15539","title":"Beating Backdoor Attack at Its Own Game","created":"2023-07-28","cited_by_count":11,"area":null},{"id":"2308.12439","title":"BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection","created":"2023-08-23","cited_by_count":11,"area":null},{"id":"2405.16112","title":"Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor","created":"2024-05-25","cited_by_count":11,"area":null},{"id":"2412.01646","title":"Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2207.05641","title":"Backdoor Attacks on Crowd Counting","created":"2022-07-12","cited_by_count":10,"area":null},{"id":"2211.07915","title":"Backdoor Attacks on Time Series: A Generative Approach","created":"2022-11-15","cited_by_count":10,"area":"safety"},{"id":"2309.04777","title":"Towards Robust Model Watermark via Reducing Parametric Vulnerability","created":"2023-09-09","cited_by_count":10,"area":"safety"},{"id":"2405.17929","title":"Towards Unified Robustness Against Both Backdoor and Adversarial Attacks","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2409.15968","title":"Adversarial Backdoor Defense in CLIP","created":"2024-09-24","cited_by_count":10,"area":"safety"},{"id":"2507.05113","title":"CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation","created":"2025-07-07","cited_by_count":10,"area":"safety"},{"id":"2206.02976","title":"Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2306.00816","title":"Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers","created":"2023-06-01","cited_by_count":9,"area":null},{"id":"2312.11057","title":"DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models","created":"2023-12-18","cited_by_count":9,"area":"diffusion"},{"id":"2406.00816","title":"Invisible Backdoor Attacks on Diffusion Models","created":"2024-06-02","cited_by_count":9,"area":"diffusion"},{"id":"2409.14119","title":"Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm","created":"2024-09-21","cited_by_count":9,"area":null},{"id":"2412.11441","title":"UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models","created":"2024-12-16","cited_by_count":9,"area":"diffusion"},{"id":"2401.01085","title":"Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control","created":"2024-01-02","cited_by_count":8,"area":"safety"},{"id":"2405.19928","title":"BAN: Detecting Backdoors Activated by Adversarial Neuron Noise","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2406.03508","title":"Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders","created":"2024-06-05","cited_by_count":8,"area":"safety"},{"id":"2502.11798","title":"BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model","created":"2025-02-17","cited_by_count":8,"area":"diffusion"},{"id":"2503.06453","title":"Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation","created":"2025-03-09","cited_by_count":8,"area":"diffusion"},{"id":"2202.12154","title":"Towards Effective and Robust Neural Trojan Defenses via Input Filtering","created":"2022-02-24","cited_by_count":7,"area":null},{"id":"2301.00986","title":"Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition","created":"2023-01-03","cited_by_count":7,"area":null},{"id":"2302.14500","title":"FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases","created":"2023-02-28","cited_by_count":7,"area":"safety"},{"id":"2410.09838","title":"Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2411.15673","title":"Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment","created":"2024-11-23","cited_by_count":7,"area":"mllm"},{"id":"2411.19479","title":"FLARE: Toward Universal Dataset Purification against Backdoor Attacks","created":"2024-11-29","cited_by_count":7,"area":null},{"id":"2412.06219","title":"Data Free Backdoor Attacks","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2501.05928","title":"Towards Backdoor Stealthiness in Model Parameter Space","created":"2025-01-10","cited_by_count":7,"area":null},{"id":"2510.07985","title":"Fewer Weights, More Problems: A Practical Attack on LLM Pruning","created":"2025-10-09","cited_by_count":7,"area":null},{"id":"2603.13461","title":"Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference","created":"2026-03-13","cited_by_count":7,"area":"safety"},{"id":"2307.15017","title":"Samplable Anonymous Aggregation for Private Federated Data Analysis","created":"2023-07-27","cited_by_count":6,"area":null},{"id":"2308.04406","title":"XGBD: Explanation-Guided Graph Backdoor Detection","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2403.03846","title":"Can Distillation Mitigate Backdoor Attacks in Pre-trained Encoders?","created":"2024-03-06","cited_by_count":6,"area":"safety"},{"id":"2405.20291","title":"Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness","created":"2024-05-30","cited_by_count":6,"area":null}],"next_cursor":"100"}