{"total":166,"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":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153,"area":null},{"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":"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":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80,"area":"lr"},{"id":"2305.00054","title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms","created":"2023-04-28","cited_by_count":69,"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":"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":"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":"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":"2405.09786","title":"IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency","created":"2024-05-16","cited_by_count":39,"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":"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":"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":"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":"2302.01762","title":"BackdoorBox: A Python Toolbox for Backdoor Learning","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2210.04688","title":"BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets","created":"2022-10-07","cited_by_count":25,"area":"offlinerl"},{"id":"2502.18508","title":"REFINE: Inversion-Free Backdoor Defense via Model Reprogramming","created":"2025-02-22","cited_by_count":22,"area":null},{"id":"2305.02424","title":"Backdoor Learning on Sequence to Sequence Models","created":"2023-05-03","cited_by_count":21,"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":"2202.03609","title":"PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning","created":"2022-02-08","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":"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":"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":"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":"2302.12758","title":"Defending Against Backdoor Attacks by Layer-wise Feature Analysis","created":"2023-02-24","cited_by_count":16,"area":null},{"id":"2402.08922","title":"The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes","created":"2024-02-14","cited_by_count":16,"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":"2409.19993","title":"Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges","created":"2024-09-30","cited_by_count":15,"area":"safety"},{"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":"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":"2409.13864","title":"Persistent Backdoor Attacks in Continual Learning","created":"2024-09-20","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":"2210.10886","title":"Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis","created":"2022-10-19","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":"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":"2406.00588","title":"Generalization Bound and New Algorithm for Clean-Label Backdoor Attack","created":"2024-06-02","cited_by_count":11,"area":null},{"id":"2302.03684","title":"Temporal Robustness against Data Poisoning","created":"2023-02-07","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":"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":"2306.02368","title":"Revisiting Data-Free Knowledge Distillation with Poisoned Teachers","created":"2023-06-04","cited_by_count":9,"area":"safety"},{"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":"2401.01085","title":"Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control","created":"2024-01-02","cited_by_count":8,"area":"safety"},{"id":"2406.03508","title":"Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders","created":"2024-06-05","cited_by_count":8,"area":"safety"},{"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":"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":"2212.01314","title":"On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds","created":"2022-12-02","cited_by_count":6,"area":null},{"id":"2212.11751","title":"Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing","created":"2022-12-22","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":"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":"2503.05445","title":"Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks","created":"2025-03-07","cited_by_count":6,"area":"safety"},{"id":"2205.11736","title":"Towards a Defense Against Federated Backdoor Attacks Under Continuous Training","created":"2022-05-24","cited_by_count":5,"area":null},{"id":"2209.15139","title":"Augmentation Backdoors","created":"2022-09-29","cited_by_count":5,"area":null},{"id":"2303.12054","title":"Influencer Backdoor Attack on Semantic Segmentation","created":"2023-03-21","cited_by_count":5,"area":null},{"id":"2307.07328","title":"Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy","created":"2023-07-14","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":"2405.16783","title":"TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models","created":"2024-05-27","cited_by_count":5,"area":"safety"},{"id":"2410.11205","title":"Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2410.11283","title":"AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment","created":"2024-10-15","cited_by_count":5,"area":"alignment"},{"id":"2505.15656","title":"Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2509.23871","title":"Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack","created":"2025-09-28","cited_by_count":5,"area":"distill"},{"id":"2208.06537","title":"Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons","created":"2022-08-13","cited_by_count":4,"area":null},{"id":"2211.10933","title":"Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification","created":"2022-11-20","cited_by_count":4,"area":null},{"id":"2301.08751","title":"Towards Understanding How Self-training Tolerates Data Backdoor Poisoning","created":"2023-01-20","cited_by_count":4,"area":null},{"id":"2601.11207","title":"LoRA as Oracle","created":"2026-01-16","cited_by_count":4,"area":"safety"},{"id":"2304.10985","title":"INK: Inheritable Natural Backdoor Attack Against Model Distillation","created":"2023-04-21","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":"2405.19990","title":"DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-World","created":"2024-05-30","cited_by_count":3,"area":"safety"},{"id":"2407.10052","title":"Augmented Neural Fine-Tuning for Efficient Backdoor Purification","created":"2024-07-14","cited_by_count":3,"area":null},{"id":"2411.04811","title":"Defending Deep Regression Models against Backdoor Attacks","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2411.07114","title":"TinyML Security: Exploring Vulnerabilities in Resource-Constrained Machine Learning Systems","created":"2024-11-11","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":"2504.11990","title":"Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets","created":"2025-04-16","cited_by_count":3,"area":"safety"}],"next_cursor":"100"}