{"total":182,"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":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166,"area":null},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"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":"2204.00032","title":"Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets","created":"2022-03-31","cited_by_count":101,"area":null},{"id":"2105.00164","title":"Hidden Backdoors in Human-Centric Language Models","created":"2021-05-01","cited_by_count":90,"area":"safety"},{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75,"area":"safety"},{"id":"2206.08514","title":"A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks","created":"2022-06-17","cited_by_count":74,"area":"safety"},{"id":"2112.05224","title":"Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures","created":"2021-12-09","cited_by_count":73,"area":"safety"},{"id":"2209.15179","title":"Physical Adversarial Attack meets Computer Vision: A Decade Survey","created":"2022-09-30","cited_by_count":67,"area":null},{"id":"2106.04690","title":"Handcrafted Backdoors in Deep Neural Networks","created":"2021-06-08","cited_by_count":63,"area":null},{"id":"2310.20448","title":"A Survey on Federated Unlearning: Challenges, Methods, and Future Directions","created":"2023-10-31","cited_by_count":63,"area":"safety"},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"area":null},{"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":"2301.02496","title":"Stealthy Backdoor Attack for Code Models","created":"2023-01-06","cited_by_count":49,"area":"safety"},{"id":"2112.03476","title":"Defending against Model Stealing via Verifying Embedded External Features","created":"2021-12-07","cited_by_count":46,"area":null},{"id":"2107.14569","title":"Can You Hear It? Backdoor Attacks via Ultrasonic Triggers","created":"2021-07-30","cited_by_count":44,"area":null},{"id":"2110.06904","title":"Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks","created":"2021-10-13","cited_by_count":40,"area":"safety"},{"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":"2106.15764","title":"The Threat of Offensive AI to Organizations","created":"2021-06-30","cited_by_count":38,"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":"2109.13236","title":"FedIPR: Ownership Verification for Federated Deep Neural Network Models","created":"2021-09-27","cited_by_count":36,"area":"safety"},{"id":"2111.09999","title":"TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems","created":"2021-11-19","cited_by_count":36,"area":null},{"id":"2103.16074","title":"PointBA: Towards Backdoor Attacks in 3D Point Cloud","created":"2021-03-30","cited_by_count":35,"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":"2203.00858","title":"Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving","created":"2022-03-02","cited_by_count":31,"area":null},{"id":"2302.11408","title":"ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms","created":"2023-02-22","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":"2504.21668","title":"Traceback of Poisoning Attacks to Retrieval-Augmented Generation","created":"2025-04-30","cited_by_count":28,"area":"rag"},{"id":"2302.01762","title":"BackdoorBox: A Python Toolbox for Backdoor Learning","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2206.07840","title":"Architectural Backdoors in Neural Networks","created":"2022-06-15","cited_by_count":25,"area":null},{"id":"2201.08619","title":"Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World","created":"2022-01-21","cited_by_count":22,"area":null},{"id":"2402.10196","title":"A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents","created":"2024-02-15","cited_by_count":22,"area":"agents"},{"id":"2104.07395","title":"Robust Backdoor Attacks against Deep Neural Networks in Real Physical World","created":"2021-04-15","cited_by_count":20,"area":null},{"id":"2106.07798","title":"Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers","created":"2021-06-14","cited_by_count":20,"area":"safety"},{"id":"2206.12381","title":"Defending Backdoor Attacks on Vision Transformer via Patch Processing","created":"2022-06-24","cited_by_count":20,"area":"safety"},{"id":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2501.18617","title":"DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs","created":"2025-01-24","cited_by_count":20,"area":"lr"},{"id":"2305.17506","title":"Backdooring Neural Code Search","created":"2023-05-27","cited_by_count":19,"area":"safety"},{"id":"2407.19845","title":"BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning","created":"2024-07-29","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":"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":"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":"2401.15239","title":"MEA-Defender: A Robust Watermark against Model Extraction Attack","created":"2024-01-26","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":"2108.03980","title":"Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness","created":"2021-07-30","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":"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":"2403.17188","title":"LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning","created":"2024-03-25","cited_by_count":13,"area":null},{"id":"2409.01193","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","created":"2024-09-02","cited_by_count":13,"area":"safety"},{"id":"2303.09079","title":"SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning","created":"2023-03-16","cited_by_count":11,"area":"safety"},{"id":"2308.12439","title":"BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection","created":"2023-08-23","cited_by_count":11,"area":null},{"id":"2402.06957","title":"Architectural Neural Backdoors from First Principles","created":"2024-02-10","cited_by_count":11,"area":null},{"id":"2406.00588","title":"Generalization Bound and New Algorithm for Clean-Label Backdoor Attack","created":"2024-06-02","cited_by_count":11,"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":"2303.00215","title":"Single Image Backdoor Inversion via Robust Smoothed Classifiers","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2310.10780","title":"Demystifying Poisoning Backdoor Attacks from a Statistical Perspective","created":"2023-10-16","cited_by_count":10,"area":null},{"id":"2312.09665","title":"FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2405.17929","title":"Towards Unified Robustness Against Both Backdoor and Adversarial Attacks","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2203.11633","title":"Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis","created":"2022-03-22","cited_by_count":9,"area":null},{"id":"2209.03563","title":"SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning","created":"2022-09-08","cited_by_count":9,"area":null},{"id":"2210.00108","title":"ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2211.10908","title":"ESTAS: Effective and Stable Trojan Attacks in Self-supervised Encoders with One Target Unlabelled Sample","created":"2022-11-20","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":"2302.14353","title":"A semantic backdoor attack against Graph Convolutional Networks","created":"2023-02-28","cited_by_count":8,"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":"2310.13424","title":"FLTracer: Accurate Poisoning Attack Provenance in Federated Learning","created":"2023-10-20","cited_by_count":8,"area":null},{"id":"2405.19928","title":"BAN: Detecting Backdoors Activated by Adversarial Neuron Noise","created":"2024-05-30","cited_by_count":8,"area":null},{"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":"2210.09305","title":"Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning","created":"2022-10-17","cited_by_count":7,"area":"safety"},{"id":"2210.13660","title":"Multi-SpacePhish: Extending the Evasion-space of Adversarial Attacks against Phishing Website Detectors using Machine Learning","created":"2022-10-24","cited_by_count":7,"area":null},{"id":"2210.15614","title":"Private and Reliable Neural Network Inference","created":"2022-10-27","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":"2306.08386","title":"Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2401.08216","title":"Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning","created":"2024-01-16","cited_by_count":7,"area":null},{"id":"2407.01919","title":"A Method to Facilitate Membership Inference Attacks in Deep Learning Models","created":"2024-07-02","cited_by_count":7,"area":"safety"},{"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":"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":"2110.07683","title":"Don't Knock! Rowhammer at the Backdoor of DNN Models","created":"2021-10-14","cited_by_count":6,"area":null},{"id":"2302.01740","title":"SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification","created":"2023-02-03","cited_by_count":6,"area":null},{"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},{"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":"2107.10443","title":"Spinning Sequence-to-Sequence Models with Meta-Backdoors","created":"2021-07-22","cited_by_count":5,"area":null},{"id":"2203.02079","title":"Dynamic Backdoors with Global Average Pooling","created":"2022-03-04","cited_by_count":5,"area":null},{"id":"2206.13498","title":"Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior","created":"2022-06-27","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":"2306.08313","title":"A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2405.10612","title":"Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers","created":"2024-05-17","cited_by_count":5,"area":"safety"},{"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":"2406.10932","title":"Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition","created":"2024-06-16","cited_by_count":5,"area":"safety"},{"id":"2409.03741","title":"Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?","created":"2024-09-05","cited_by_count":5,"area":"safety"},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","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":"2312.04584","title":"Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger","created":"2023-12-03","cited_by_count":4,"area":null},{"id":"2402.02886","title":"Time-Distributed Backdoor Attacks on Federated Spiking Learning","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2503.09712","title":"Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain","created":"2025-03-12","cited_by_count":4,"area":null}],"next_cursor":"100"}