{"total":324,"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":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263,"area":null},{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235,"area":null},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166,"area":null},{"id":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153,"area":null},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"area":null},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127,"area":null},{"id":"2110.07831","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","created":"2021-10-15","cited_by_count":104,"area":"safety"},{"id":"2307.14692","title":"Backdoor Attacks for In-Context Learning with Language Models","created":"2023-07-27","cited_by_count":96,"area":"safety"},{"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":"2205.13383","title":"BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning","created":"2022-05-26","cited_by_count":86,"area":null},{"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":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80,"area":"lr"},{"id":"2108.07969","title":"Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better","created":"2021-08-18","cited_by_count":79,"area":"distill"},{"id":"2208.03111","title":"Data-free Backdoor Removal based on Channel Lipschitzness","created":"2022-08-05","cited_by_count":79,"area":null},{"id":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72,"area":"safety"},{"id":"2201.09538","title":"Backdoor Defense with Machine Unlearning","created":"2022-01-24","cited_by_count":65,"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":"2211.14719","title":"BadPrompt: Backdoor Attacks on Continuous Prompts","created":"2022-11-27","cited_by_count":63,"area":"safety"},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63,"area":"safety"},{"id":"2112.01148","title":"FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis","created":"2021-12-02","cited_by_count":61,"area":null},{"id":"2102.04716","title":"Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training","created":"2021-02-09","cited_by_count":59,"area":null},{"id":"2305.14876","title":"Reconstructive Neuron Pruning for Backdoor Defense","created":"2023-05-24","cited_by_count":59,"area":null},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58,"area":"safety"},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57,"area":"safety"},{"id":"2205.06900","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","created":"2022-05-13","cited_by_count":55,"area":null},{"id":"2303.15180","title":"Detecting Backdoors in Pre-trained Encoders","created":"2023-03-23","cited_by_count":55,"area":"safety"},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53,"area":"safety"},{"id":"2305.06360","title":"Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy","created":"2023-05-10","cited_by_count":51,"area":"safety"},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50,"area":"safety"},{"id":"2101.06969","title":"Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks","created":"2021-01-18","cited_by_count":49,"area":null},{"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":"2205.14497","title":"BadDet: Backdoor Attacks on Object Detection","created":"2022-05-28","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":"2111.08429","title":"An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences","created":"2021-11-16","cited_by_count":42,"area":null},{"id":"2205.13616","title":"Towards A Proactive ML Approach for Detecting Backdoor Poison Samples","created":"2022-05-26","cited_by_count":40,"area":null},{"id":"2210.15127","title":"Rethinking the Reverse-engineering of Trojan Triggers","created":"2022-10-27","cited_by_count":39,"area":"safety"},{"id":"2309.06055","title":"Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review","created":"2023-09-12","cited_by_count":39,"area":"safety"},{"id":"2312.15172","title":"Pre-trained Trojan Attacks for Visual Recognition","created":"2023-12-23","cited_by_count":39,"area":"safety"},{"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":"2212.09067","title":"Fine-Tuning Is All You Need to Mitigate Backdoor Attacks","created":"2022-12-18","cited_by_count":38,"area":null},{"id":"2303.06818","title":"Backdoor Defense via Deconfounded Representation Learning","created":"2023-03-13","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":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37,"area":null},{"id":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36,"area":"safety"},{"id":"2203.14533","title":"Robust Unlearnable Examples: Protecting Data Against Adversarial Learning","created":"2022-03-28","cited_by_count":35,"area":null},{"id":"2402.11473","title":"Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection","created":"2024-02-18","cited_by_count":35,"area":null},{"id":"2505.16916","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning","created":"2025-05-22","cited_by_count":35,"area":"mllm"},{"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":"2408.03400","title":"Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey","created":"2024-08-06","cited_by_count":32,"area":"diffusion"},{"id":"2306.06815","title":"TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models","created":"2023-06-12","cited_by_count":31,"area":null},{"id":"2312.00050","title":"Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift","created":"2023-11-27","cited_by_count":31,"area":"diffusion"},{"id":"2108.09187","title":"Quantization Backdoors to Deep Learning Commercial Frameworks","created":"2021-08-20","cited_by_count":29,"area":null},{"id":"2201.08474","title":"Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios","created":"2022-01-20","cited_by_count":29,"area":null},{"id":"2310.18933","title":"Label Poisoning is All You Need","created":"2023-10-29","cited_by_count":29,"area":"safety"},{"id":"2207.04497","title":"One-shot Neural Backdoor Erasing via Adversarial Weight Masking","created":"2022-07-10","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":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"area":"safety"},{"id":"2503.23751","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks","created":"2025-03-31","cited_by_count":28,"area":"safety"},{"id":"2205.03190","title":"Imperceptible Backdoor Attack: From Input Space to Feature Representation","created":"2022-05-06","cited_by_count":27,"area":null},{"id":"2301.08170","title":"On the Vulnerability of Backdoor Defenses for Federated Learning","created":"2023-01-19","cited_by_count":27,"area":null},{"id":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","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":"2303.04278","title":"CUDA: Convolution-based Unlearnable Datasets","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2401.17319","title":"Decentralized Federated Learning: A Survey on Security and Privacy","created":"2024-01-25","cited_by_count":25,"area":null},{"id":"2109.01300","title":"How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data","created":"2021-09-03","cited_by_count":24,"area":null},{"id":"2502.18508","title":"REFINE: Inversion-Free Backdoor Defense via Model Reprogramming","created":"2025-02-22","cited_by_count":22,"area":null},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21,"area":null},{"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":"2209.09841","title":"Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation","created":"2022-09-20","cited_by_count":19,"area":"distill"},{"id":"2210.07907","title":"Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks","created":"2022-10-14","cited_by_count":19,"area":"safety"},{"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":"2111.10991","title":"Backdoor Attack through Frequency Domain","created":"2021-11-22","cited_by_count":18,"area":null},{"id":"2204.09975","title":"Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation","created":"2022-04-21","cited_by_count":18,"area":null},{"id":"2211.10530","title":"Provable Defense against Backdoor Policies in Reinforcement Learning","created":"2022-11-18","cited_by_count":18,"area":null},{"id":"2302.06279","title":"Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data","created":"2023-02-13","cited_by_count":18,"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":"2405.12725","title":"Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks","created":"2024-05-21","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":"2411.09702","title":"On the Surprising Effectiveness of Attention Transfer for Vision Transformers","created":"2024-11-14","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":"2302.12758","title":"Defending Against Backdoor Attacks by Layer-wise Feature Analysis","created":"2023-02-24","cited_by_count":16,"area":null},{"id":"2111.05077","title":"Enhancing Backdoor Attacks with Multi-Level MMD Regularization","created":"2021-11-09","cited_by_count":15,"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":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2407.04600","title":"Understanding the Gains from Repeated Self-Distillation","created":"2024-07-05","cited_by_count":15,"area":"distill"},{"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":"2211.15929","title":"Backdoor Vulnerabilities in Normally Trained Deep Learning Models","created":"2022-11-29","cited_by_count":13,"area":null},{"id":"2307.10184","title":"A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives","created":"2023-07-03","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}],"next_cursor":"100"}