{"total":122,"rows":[{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166,"area":null},{"id":"2104.03413","title":"Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective","created":"2021-04-07","cited_by_count":161,"area":"safety"},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2108.00352","title":"BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning","created":"2021-08-01","cited_by_count":123,"area":"safety"},{"id":"2204.05255","title":"Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information","created":"2022-04-11","cited_by_count":103,"area":null},{"id":"2102.05123","title":"Backdoor Scanning for Deep Neural Networks through K-Arm Optimization","created":"2021-02-09","cited_by_count":98,"area":null},{"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":"2105.00164","title":"Hidden Backdoors in Human-Centric Language Models","created":"2021-05-01","cited_by_count":90,"area":"safety"},{"id":"2103.13127","title":"Black-box Detection of Backdoor Attacks with Limited Information and Data","created":"2021-03-24","cited_by_count":73,"area":null},{"id":"2105.00579","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","created":"2021-05-02","cited_by_count":68,"area":null},{"id":"2103.04264","title":"T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification","created":"2021-03-07","cited_by_count":60,"area":"safety"},{"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":"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":"2110.14880","title":"AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis","created":"2021-10-28","cited_by_count":53,"area":null},{"id":"2108.02488","title":"Poison Ink: Robust and Invisible Backdoor Attack","created":"2021-08-05","cited_by_count":50,"area":null},{"id":"2304.02786","title":"UNICORN: A Unified Backdoor Trigger Inversion Framework","created":"2023-04-05","cited_by_count":46,"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":"2110.08335","title":"Trigger Hunting with a Topological Prior for Trojan Detection","created":"2021-10-15","cited_by_count":39,"area":"safety"},{"id":"2210.15127","title":"Rethinking the Reverse-engineering of Trojan Triggers","created":"2022-10-27","cited_by_count":39,"area":"safety"},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","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":"2303.11470","title":"Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking","created":"2023-03-20","cited_by_count":37,"area":null},{"id":"2106.06469","title":"Topological Detection of Trojaned Neural Networks","created":"2021-06-11","cited_by_count":34,"area":null},{"id":"2111.12965","title":"Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks","created":"2021-11-25","cited_by_count":34,"area":null},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33,"area":"safety"},{"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":"2407.04215","title":"T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models","created":"2024-07-05","cited_by_count":29,"area":"diffusion"},{"id":"2207.04497","title":"One-shot Neural Backdoor Erasing via Adversarial Weight Masking","created":"2022-07-10","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":"2302.10894","title":"Red Teaming Deep Neural Networks with Feature Synthesis Tools","created":"2023-02-08","cited_by_count":21,"area":"safety"},{"id":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2202.03609","title":"PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning","created":"2022-02-08","cited_by_count":19,"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":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2111.10991","title":"Backdoor Attack through Frequency Domain","created":"2021-11-22","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":"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":"2210.06516","title":"How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?","created":"2022-10-12","cited_by_count":17,"area":"safety"},{"id":"2301.10412","title":"BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing","created":"2023-01-25","cited_by_count":16,"area":"safety"},{"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":"2402.01920","title":"Preference Poisoning Attacks on Reward Model Learning","created":"2024-02-02","cited_by_count":14,"area":"alignment"},{"id":"2103.10274","title":"TOP: Backdoor Detection in Neural Networks via Transferability of Perturbation","created":"2021-03-18","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":"2403.10717","title":"Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"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":"2308.03906","title":"TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models","created":"2023-08-07","cited_by_count":12,"area":"safety"},{"id":"2212.04687","title":"Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models","created":"2022-12-09","cited_by_count":11,"area":null},{"id":"2110.10354","title":"Detecting Backdoor Attacks Against Point Cloud Classifiers","created":"2021-10-20","cited_by_count":10,"area":null},{"id":"2112.03350","title":"Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2303.00215","title":"Single Image Backdoor Inversion via Robust Smoothed Classifiers","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2102.01815","title":"TAD: Trigger Approximation based Black-box Trojan Detection for AI","created":"2021-02-03","cited_by_count":9,"area":null},{"id":"2109.05507","title":"Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain","created":"2021-09-12","cited_by_count":9,"area":null},{"id":"2303.13211","title":"Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs","created":"2023-03-23","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","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":"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":"2210.06704","title":"COLLIDER: A Robust Training Framework for Backdoor Data","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2211.10024","title":"Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2307.05422","title":"Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2403.18136","title":"Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics","created":"2024-03-26","cited_by_count":6,"area":null},{"id":"2103.08820","title":"EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2207.04209","title":"Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain","created":"2022-07-09","cited_by_count":5,"area":null},{"id":"2306.08009","title":"DHBE: Data-free Holistic Backdoor Erasing in Deep Neural Networks via Restricted Adversarial Distillation","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2405.14781","title":"Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2406.05826","title":"PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection","created":"2024-06-09","cited_by_count":5,"area":null},{"id":"2411.12220","title":"DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning","created":"2024-11-19","cited_by_count":5,"area":null},{"id":"2103.15918","title":"MISA: Online Defense of Trojaned Models using Misattributions","created":"2021-03-29","cited_by_count":4,"area":null},{"id":"2201.12211","title":"Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire","created":"2022-01-28","cited_by_count":4,"area":"safety"},{"id":"2301.12318","title":"Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering","created":"2023-01-29","cited_by_count":4,"area":null},{"id":"2310.12665","title":"SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models","created":"2023-10-19","cited_by_count":4,"area":"safety"},{"id":"2111.11157","title":"NTD: Non-Transferability Enabled Backdoor Detection","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2205.09167","title":"Backdoor Attacks on Bayesian Neural Networks using Reverse Distribution","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2205.15944","title":"Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systems","created":"2022-05-31","cited_by_count":3,"area":null},{"id":"2210.10272","title":"Training set cleansing of backdoor poisoning by self-supervised representation learning","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2307.11565","title":"Adversarial Feature Map Pruning for Backdoor","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2308.04617","title":"Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection","created":"2023-08-08","cited_by_count":3,"area":"safety"},{"id":"2308.11070","title":"Temporal-Distributed Backdoor Attack Against Video Based Action Recognition","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2403.08208","title":"Advancing Security in AI Systems: A Novel Approach to Detecting Backdoors in Deep Neural Networks","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2411.11006","title":"BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation","created":"2024-11-17","cited_by_count":3,"area":"safety"},{"id":"2501.17151","title":"Scanning Trojaned Models Using Out-of-Distribution Samples","created":"2025-01-28","cited_by_count":3,"area":"safety"},{"id":"2605.04209","title":"Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions","created":"2026-05-05","cited_by_count":3,"area":null},{"id":"2201.09774","title":"Hiding Behind Backdoors: Self-Obfuscation Against Generative Models","created":"2022-01-24","cited_by_count":2,"area":"safety"},{"id":"2203.09289","title":"PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2205.03894","title":"VPN: Verification of Poisoning in Neural Networks","created":"2022-05-08","cited_by_count":2,"area":"safety"},{"id":"2407.11372","title":"UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2112.13064","title":"CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing","created":"2021-12-24","cited_by_count":1,"area":null},{"id":"2204.04329","title":"An Adaptive Black-box Backdoor Detection Method for Deep Neural Networks","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2206.07018","title":"Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2210.06509","title":"Understanding Impacts of Task Similarity on Backdoor Attack and Detection","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2305.09671","title":"Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks","created":"2023-05-07","cited_by_count":1,"area":"safety"},{"id":"2308.09850","title":"Backdoor Mitigation by Correcting the Distribution of Neural Activations","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2402.02034","title":"CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors","created":"2024-02-03","cited_by_count":1,"area":null}],"next_cursor":"100"}