{"total":146,"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":"2101.05930","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","created":"2021-01-15","cited_by_count":324,"area":null},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263,"area":null},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222,"area":"safety"},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2104.11315","title":"SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics","created":"2021-04-22","cited_by_count":130,"area":null},{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"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":"2105.10123","title":"Backdoor Attacks on Self-Supervised Learning","created":"2021-05-21","cited_by_count":90,"area":null},{"id":"2106.06361","title":"Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution","created":"2021-06-11","cited_by_count":89,"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":"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":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"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":"2112.01148","title":"FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis","created":"2021-12-02","cited_by_count":61,"area":null},{"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":"2205.08305","title":"A Study of the Attention Abnormality in Trojaned BERTs","created":"2022-05-13","cited_by_count":48,"area":null},{"id":"2303.12993","title":"Backdoor Defense via Adaptively Splitting Poisoned Dataset","created":"2023-03-23","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":"2402.08577","title":"Test-Time Backdoor Attacks on Multimodal Large Language Models","created":"2024-02-13","cited_by_count":40,"area":"mllm"},{"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":"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":"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":"2303.06818","title":"Backdoor Defense via Deconfounded Representation Learning","created":"2023-03-13","cited_by_count":38,"area":null},{"id":"2112.07668","title":"Dual-Key Multimodal Backdoors for Visual Question Answering","created":"2021-12-14","cited_by_count":37,"area":"safety"},{"id":"2106.06469","title":"Topological Detection of Trojaned Neural Networks","created":"2021-06-11","cited_by_count":34,"area":null},{"id":"2201.10055","title":"Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation","created":"2022-01-25","cited_by_count":32,"area":null},{"id":"2210.07346","title":"An Embarrassingly Simple Backdoor Attack on Self-supervised Learning","created":"2022-10-13","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":"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":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2304.01482","title":"Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning","created":"2023-04-04","cited_by_count":20,"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":"2209.05244","title":"Universal Backdoor Attacks Detection via Adaptive Adversarial Probe","created":"2022-09-12","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":"2210.05929","title":"Few-shot Backdoor Attacks via Neural Tangent Kernels","created":"2022-10-12","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":"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":"2402.01920","title":"Preference Poisoning Attacks on Reward Model Learning","created":"2024-02-02","cited_by_count":14,"area":"alignment"},{"id":"2206.08477","title":"Backdoor Attacks on Vision Transformers","created":"2022-06-16","cited_by_count":13,"area":"safety"},{"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},{"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":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"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":"2202.06312","title":"Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks","created":"2022-02-13","cited_by_count":11,"area":null},{"id":"2204.06273","title":"Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures","created":"2022-04-13","cited_by_count":11,"area":null},{"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":"2406.00588","title":"Generalization Bound and New Algorithm for Clean-Label Backdoor Attack","created":"2024-06-02","cited_by_count":11,"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":"2312.09057","title":"On the Difficulty of Defending Contrastive Learning against Backdoor Attacks","created":"2023-12-14","cited_by_count":9,"area":null},{"id":"2409.00399","title":"Rethinking Backdoor Detection Evaluation for Language Models","created":"2024-08-31","cited_by_count":9,"area":"lr"},{"id":"2310.00542","title":"Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense","created":"2023-10-01","cited_by_count":8,"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":"2406.09836","title":"Robustness Inspired Graph Backdoor Defense","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2105.14259","title":"Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations","created":"2021-05-29","cited_by_count":6,"area":null},{"id":"2208.04946","title":"Attention Hijacking in Trojan Transformers","created":"2022-08-09","cited_by_count":6,"area":null},{"id":"2210.06704","title":"COLLIDER: A Robust Training Framework for Backdoor Data","created":"2022-10-13","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":"2308.04406","title":"XGBD: Explanation-Guided Graph Backdoor Detection","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2310.00626","title":"GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning","created":"2023-10-01","cited_by_count":6,"area":"safety"},{"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":"2303.12054","title":"Influencer Backdoor Attack on Semantic Segmentation","created":"2023-03-21","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":"2410.02472","title":"Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language","created":"2024-10-03","cited_by_count":5,"area":null},{"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":"2503.21305","title":"DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data","created":"2025-03-27","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":"2206.09272","title":"DECK: Model Hardening for Defending Pervasive Backdoors","created":"2022-06-18","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":"2302.06801","title":"Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions","created":"2023-02-14","cited_by_count":4,"area":"safety"},{"id":"2406.09669","title":"Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models","created":"2024-06-14","cited_by_count":4,"area":"diffusion"},{"id":"2111.14309","title":"A General Framework for Defending Against Backdoor Attacks via Influence Graph","created":"2021-11-29","cited_by_count":3,"area":null},{"id":"2203.15506","title":"Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning","created":"2022-03-25","cited_by_count":3,"area":null},{"id":"2212.08121","title":"Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks","created":"2022-12-15","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":"2410.02384","title":"Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors","created":"2024-10-03","cited_by_count":3,"area":null},{"id":"2501.02373","title":"BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors","created":"2025-01-04","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":"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":"2312.07338","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2402.15653","title":"Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm","created":"2024-02-23","cited_by_count":2,"area":null},{"id":"2406.03409","title":"Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model","created":"2024-06-01","cited_by_count":2,"area":"distill"},{"id":"2411.19075","title":"LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm","created":"2024-11-28","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}],"next_cursor":"100"}