{"total":63,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2308.04265","title":"FLIRT: Feedback Loop In-context Red Teaming","created":"2023-08-08","cited_by_count":83,"area":"safety"},{"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":"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":"2204.06974","title":"Planting Undetectable Backdoors in Machine Learning Models","created":"2022-04-14","cited_by_count":59,"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":"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":"2110.06904","title":"Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks","created":"2021-10-13","cited_by_count":40,"area":"safety"},{"id":"2302.04116","title":"Training-free Lexical Backdoor Attacks on Language Models","created":"2023-02-08","cited_by_count":31,"area":"safety"},{"id":"2404.01231","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2310.18933","title":"Label Poisoning is All You Need","created":"2023-10-29","cited_by_count":29,"area":"safety"},{"id":"2206.07840","title":"Architectural Backdoors in Neural Networks","created":"2022-06-15","cited_by_count":25,"area":null},{"id":"2302.09457","title":"Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective","created":"2023-02-19","cited_by_count":20,"area":null},{"id":"2312.08667","title":"Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey","created":"2023-12-14","cited_by_count":18,"area":null},{"id":"2311.09994","title":"Towards more Practical Threat Models in Artificial Intelligence Security","created":"2023-11-16","cited_by_count":17,"area":null},{"id":"2503.16023","title":"BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models","created":"2025-03-20","cited_by_count":17,"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":"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":"2210.00108","title":"ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks","created":"2022-09-30","cited_by_count":9,"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":"2312.00157","title":"Universal Backdoor Attacks","created":"2023-11-30","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":"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":"2405.16783","title":"TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models","created":"2024-05-27","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":"2301.03118","title":"Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons","created":"2023-01-08","cited_by_count":4,"area":"safety"},{"id":"2406.02619","title":"Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits","created":"2024-06-03","cited_by_count":4,"area":"safety"},{"id":"2406.10573","title":"Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions","created":"2024-06-15","cited_by_count":4,"area":null},{"id":"2601.11207","title":"LoRA as Oracle","created":"2026-01-16","cited_by_count":4,"area":"safety"},{"id":"2402.06357","title":"The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks","created":"2024-02-09","cited_by_count":3,"area":null},{"id":"2406.05660","title":"Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models","created":"2024-06-09","cited_by_count":3,"area":"safety"},{"id":"2410.18267","title":"Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2506.12815","title":"TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models","created":"2025-06-15","cited_by_count":3,"area":"offlinerl"},{"id":"2404.19420","title":"Let's Focus: Focused Backdoor Attack against Federated Transfer Learning","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2409.03077","title":"Backdoor defense, learnability and obfuscation","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2409.04142","title":"Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers","created":"2024-09-06","cited_by_count":2,"area":"safety"},{"id":"2503.08829","title":"Seal Your Backdoor with Variational Defense","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2503.23748","title":"THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models","created":"2025-03-31","cited_by_count":2,"area":"safety"},{"id":"2505.15175","title":"A Linear Approach to Data Poisoning","created":"2025-05-21","cited_by_count":2,"area":"safety"},{"id":"2509.20714","title":"Cryptographic Backdoor for Neural Networks: Boon and Bane","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2108.11299","title":"Certifiers Make Neural Networks Vulnerable to Availability Attacks","created":"2021-08-25","cited_by_count":1,"area":null},{"id":"2302.04977","title":"Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelines","created":"2023-02-09","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":"2310.08259","title":"Invisible Threats: Backdoor Attack in OCR Systems","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2408.00255","title":"Revocable Backdoor for Deep Model Trading","created":"2024-08-01","cited_by_count":1,"area":null},{"id":"2503.17578","title":"Large Language Models Can Verbatim Reproduce Long Malicious Sequences","created":"2025-03-21","cited_by_count":1,"area":"safety"},{"id":"2505.17092","title":"Covert Attacks on Machine Learning Training in Passively Secure MPC","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.01825","title":"Backdoors in Code Summarizers: How Bad Is It?","created":"2025-06-02","cited_by_count":1,"area":"safety"},{"id":"2508.21004","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","created":"2025-08-28","cited_by_count":1,"area":"safety"},{"id":"2302.13056","title":"SATBA: An Invisible Backdoor Attack Based On Spatial Attention","created":"2023-02-25","cited_by_count":0,"area":null},{"id":"2401.09740","title":"Hijacking Attacks against Neural Networks by Analyzing Training Data","created":"2024-01-18","cited_by_count":0,"area":"safety"},{"id":"2407.11031","title":"Purification Of Contaminated Convolutional Neural Networks Via Robust Recovery: An Approach with Theoretical Guarantee in One-Hidden-Layer Case","created":"2024-07-04","cited_by_count":0,"area":"safety"},{"id":"2409.19442","title":"Trigger-Based Fragile Model Watermarking for Image Transformation Networks","created":"2024-09-28","cited_by_count":0,"area":"safety"},{"id":"2412.16905","title":"Backdoor Attack with Invisible Triggers Based on Model Architecture Modification","created":"2024-12-22","cited_by_count":0,"area":null},{"id":"2502.18592","title":"DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networks","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2507.19905","title":"ConSeg: Contextual Backdoor Attack Against Semantic Segmentation","created":"2025-07-26","cited_by_count":0,"area":"safety"},{"id":"2510.19145","title":"HAMLOCK: HArdware-Model LOgically Combined attacK","created":"2025-10-22","cited_by_count":0,"area":"safety"},{"id":"2511.06072","title":"CatBack: Universal Backdoor Attacks on Tabular Data via Categorical Encoding","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2605.13214","title":"Backdoor Channels Hidden in Latent Space: Extending Cryptographic Undetectability to Modern Neural Networks","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.21045","title":"OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2610.05453","title":"The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models","created":"2026-10-04","cited_by_count":0,"area":"safety"},{"id":"2610.13928","title":"AI Models Can Provably Hide Arbitrary Capabilities","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}