{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/backdoor-attack/papers/3","list_of":"/task/backdoor-attack","task":"Backdoor Attack","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":6,"rows_per_page":100,"rows":[201,300],"of":523,"counts":{"archive_papers_tagged":523,"with_a_code_link":217,"where_syntology_ran_a_sample":88,"not_listed_spam_title":0,"listed":523,"listed_where_code_ran":88,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":67,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":67,"listed_every_run_a_failure_of_syntologys_instrument":21,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/backdoor-attack","prev":"/task/backdoor-attack/papers/2","next":"/task/backdoor-attack/papers/4","papers":[{"url":"/paper/sleeper-agent-scalable-hidden-trigger","slug":"sleeper-agent-scalable-hidden-trigger","title":"Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch","date":"2021-06-16","arxiv_id":"2106.08970","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sleeper-agent-scalable-hidden-trigger#ran","syntology_url":"https://syntology.ai/paper/2106.08970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08970"}},"official":{"repos":["hsouri/Sleeper-Agent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/defending-against-backdoor-attacks-in-natural","slug":"defending-against-backdoor-attacks-in-natural","title":"Defending Against Backdoor Attacks in Natural Language Generation","date":"2021-06-03","arxiv_id":"2106.01810","repositories_listed":1,"syntology":null},{"url":"/paper/stealthy-backdoors-as-compression-artifacts","slug":"stealthy-backdoors-as-compression-artifacts","title":"Stealthy Backdoors as Compression Artifacts","date":"2021-04-30","arxiv_id":"2104.15129","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stealthy-backdoors-as-compression-artifacts#ran","syntology_url":"https://syntology.ai/paper/2104.15129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.15129"}},"official":{"repos":["yulongtzzz/Stealthy-Backdoors-as-Compression-Artifacts"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/be-careful-about-poisoned-word-embeddings","slug":"be-careful-about-poisoned-word-embeddings","title":"Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models","date":"2021-03-29","arxiv_id":"2103.15543","repositories_listed":1,"syntology":null},{"url":"/paper/wanet-imperceptible-warping-based-backdoor-1","slug":"wanet-imperceptible-warping-based-backdoor-1","title":"WaNet -- Imperceptible Warping-based Backdoor Attack","date":"2021-02-20","arxiv_id":"2102.10369","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wanet-imperceptible-warping-based-backdoor-1#ran","syntology_url":"https://syntology.ai/paper/2102.10369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.10369"}},"official":{"repos":["VinAIResearch/Warping-based_Backdoor_Attack-release"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/red-alarm-for-pre-trained-models-universal","slug":"red-alarm-for-pre-trained-models-universal","title":"Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks","date":"2021-01-18","arxiv_id":"2101.06969","repositories_listed":1,"syntology":null},{"url":"/paper/wanet-imperceptible-warping-based-backdoor","slug":"wanet-imperceptible-warping-based-backdoor","title":"WaNet - Imperceptible Warping-based Backdoor Attack","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/input-aware-dynamic-backdoor-attack","slug":"input-aware-dynamic-backdoor-attack","title":"Input-Aware Dynamic Backdoor Attack","date":"2020-10-16","arxiv_id":"2010.08138","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/input-aware-dynamic-backdoor-attack#ran","syntology_url":"https://syntology.ai/paper/2010.08138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08138"}},"official":{"repos":["VinAIResearch/input-aware-backdoor-attack-release"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/practical-detection-of-trojan-neural-networks","slug":"practical-detection-of-trojan-neural-networks","title":"Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases","date":"2020-07-31","arxiv_id":"2007.15802","repositories_listed":1,"syntology":null},{"url":"/paper/backdoor-learning-a-survey","slug":"backdoor-learning-a-survey","title":"Backdoor Learning: A Survey","date":"2020-07-17","arxiv_id":"2007.08745","repositories_listed":1,"syntology":null},{"url":"/paper/defending-against-backdoors-in-federated","slug":"defending-against-backdoors-in-federated","title":"Defending against Backdoors in Federated Learning with Robust Learning Rate","date":"2020-07-07","arxiv_id":"2007.03767","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-framework-for-analyzing-and","slug":"a-unified-framework-for-analyzing-and","title":"Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?","date":"2020-06-26","arxiv_id":"2006.14871","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-examples-are-useful-too","slug":"adversarial-examples-are-useful-too","title":"Adversarial examples are useful too!","date":"2020-05-13","arxiv_id":"2005.06107","repositories_listed":1,"syntology":null},{"url":"/paper/clean-label-backdoor-attacks-on-video","slug":"clean-label-backdoor-attacks-on-video","title":"Clean-Label Backdoor Attacks on Video Recognition Models","date":"2020-03-06","arxiv_id":"2003.03030","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clean-label-backdoor-attacks-on-video#ran","syntology_url":"https://syntology.ai/paper/2003.03030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03030"}},"official":{"repos":["ShihaoZhaoZSH/Video-Backdoor-Attack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/defending-neural-backdoors-via-generative","slug":"defending-neural-backdoors-via-generative","title":"Defending Neural Backdoors via Generative Distribution Modeling","date":"2019-10-10","arxiv_id":"1910.04749","repositories_listed":1,"syntology":null},{"url":"/paper/neural-cleanse-identifying-and-mitigating","slug":"neural-cleanse-identifying-and-mitigating","title":"Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks","date":"2019-05-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-new-backdoor-attack-in-cnns-by-training-set","slug":"a-new-backdoor-attack-in-cnns-by-training-set","title":"A new Backdoor Attack in CNNs by training set corruption without label poisoning","date":"2019-02-12","arxiv_id":"1902.11237","repositories_listed":1,"syntology":null},{"url":null,"slug":"visualtrap-a-stealthy-backdoor-attack-on-gui","title":"VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation","date":"2025-07-09","arxiv_id":"2507.06899","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-training-time-poisoning-component","title":"Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning","date":"2025-07-07","arxiv_id":"2507.04883","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuba-controlled-untargeted-backdoor-attack","title":"CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks","date":"2025-06-20","arxiv_id":"2506.17350","repositories_listed":0,"syntology":null},{"url":null,"slug":"screen-hijack-visual-poisoning-of-vlm-agents","title":"Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments","date":"2025-06-16","arxiv_id":"2506.13205","repositories_listed":0,"syntology":null},{"url":null,"slug":"me-trigger-element-combination-backdoor","title":"ME: Trigger Element Combination Backdoor Attack on Copyright Infringement","date":"2025-06-12","arxiv_id":"2506.10776","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08346","title":"SPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Models","date":"2025-06-10","arxiv_id":"2506.08346","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-node-trigger-backdoor-attacks-in-graph","title":"Single-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems","date":"2025-06-10","arxiv_id":"2506.08401","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdoor-attack-on-vision-language-models","title":"Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation","date":"2025-06-08","arxiv_id":"2506.07214","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-graph-backdoor-attack","title":"Heterogeneous Graph Backdoor Attack","date":"2025-05-30","arxiv_id":"2506.00191","repositories_listed":0,"syntology":null},{"url":null,"slug":"poison-in-the-well-feature-embedding","title":"Poison in the Well: Feature Embedding Disruption in Backdoor Attacks","date":"2025-05-26","arxiv_id":"2505.19821","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdoors-in-drl-four-environments-focusing","title":"Backdoors in DRL: Four Environments Focusing on In-distribution Triggers","date":"2025-05-22","arxiv_id":"2505.17248","repositories_listed":0,"syntology":null},{"url":null,"slug":"baddepth-backdoor-attacks-against-monocular","title":"BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World","date":"2025-05-22","arxiv_id":"2505.16154","repositories_listed":0,"syntology":null},{"url":null,"slug":"badvla-towards-backdoor-attacks-on-vision","title":"BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization","date":"2025-05-22","arxiv_id":"2505.16640","repositories_listed":0,"syntology":null},{"url":null,"slug":"fighost-fluorescent-ink-based-stealthy-and","title":"FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition","date":"2025-05-17","arxiv_id":"2505.12045","repositories_listed":0,"syntology":null},{"url":null,"slug":"defending-the-edge-representative-attention","title":"Defending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning","date":"2025-05-15","arxiv_id":"2505.10297","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-reflection-backdoor-attack-on-vision","title":"Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving","date":"2025-05-09","arxiv_id":"2505.06413","repositories_listed":0,"syntology":null},{"url":null,"slug":"badlingual-a-novel-lingual-backdoor-attack","title":"BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models","date":"2025-05-06","arxiv_id":"2505.03501","repositories_listed":0,"syntology":null},{"url":null,"slug":"erased-but-not-forgotten-how-backdoors","title":"Erased but Not Forgotten: How Backdoors Compromise Concept Erasure","date":"2025-04-29","arxiv_id":"2504.21072","repositories_listed":0,"syntology":null},{"url":null,"slug":"sfiba-spatial-based-full-target-invisible","title":"SFIBA: Spatial-based Full-target Invisible Backdoor Attacks","date":"2025-04-29","arxiv_id":"2504.21052","repositories_listed":0,"syntology":null},{"url":null,"slug":"badmoe-backdooring-mixture-of-experts-llms","title":"BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts","date":"2025-04-24","arxiv_id":"2504.18598","repositories_listed":0,"syntology":null},{"url":null,"slug":"robo-troj-attacking-llm-based-task-planners","title":"Robo-Troj: Attacking LLM-based Task Planners","date":"2025-04-23","arxiv_id":"2504.17070","repositories_listed":0,"syntology":null},{"url":null,"slug":"badapex-backdoor-attack-based-on-adaptive","title":"BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models","date":"2025-04-18","arxiv_id":"2504.13775","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategic-planning-of-stealthy-backdoor","title":"Strategic Planning of Stealthy Backdoor Attacks in Markov Decision Processes","date":"2025-04-17","arxiv_id":"2504.13276","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-backdoor-attack-and-defense-for-llm","title":"Exploring Backdoor Attack and Defense for LLM-empowered Recommendations","date":"2025-04-15","arxiv_id":"2504.11182","repositories_listed":0,"syntology":null},{"url":null,"slug":"parasite-a-steganography-based-backdoor","title":"Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models","date":"2025-04-08","arxiv_id":"2504.05815","repositories_listed":0,"syntology":null},{"url":null,"slug":"shadowcot-cognitive-hijacking-for-stealthy","title":"ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs","date":"2025-04-08","arxiv_id":"2504.05605","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-channel-triggered-backdoor-attack-on","title":"A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction","date":"2025-03-31","arxiv_id":"2503.23866","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdoor-detection-through-replicated","title":"Backdoor Detection through Replicated Execution of Outsourced Training","date":"2025-03-31","arxiv_id":"2504.00170","repositories_listed":0,"syntology":null},{"url":null,"slug":"debackdoor-a-deductive-framework-for","title":"DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data","date":"2025-03-27","arxiv_id":"2503.21305","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semantic-and-clean-label-backdoor-attack","title":"A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks","date":"2025-03-19","arxiv_id":"2503.14922","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-backdoor-attacks-with-reasonable","title":"Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks","date":"2025-03-12","arxiv_id":"2503.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"c-2-attack-towards-representation-backdoor-on","title":"C^2 ATTACK: Towards Representation Backdoor on CLIP via Concept Confusion","date":"2025-03-12","arxiv_id":"2503.09095","repositories_listed":0,"syntology":null},{"url":null,"slug":"stealthy-patch-wise-backdoor-attack-in-3d","title":"Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness","date":"2025-03-12","arxiv_id":"2503.09336","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dual-purpose-framework-for-backdoor-defense","title":"A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models","date":"2025-02-26","arxiv_id":"2502.19047","repositories_listed":0,"syntology":null},{"url":"/paper/stealthy-backdoor-attack-in-self-supervised","slug":"stealthy-backdoor-attack-in-self-supervised","title":"Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models","date":"2025-02-25","arxiv_id":"2502.18290","repositories_listed":0,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/stealthy-backdoor-attack-in-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2502.18290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18290"}},"official":null}},{"url":null,"slug":"multi-target-federated-backdoor-attack-based","title":"Multi-Target Federated Backdoor Attack Based on Feature Aggregation","date":"2025-02-23","arxiv_id":"2502.16545","repositories_listed":0,"syntology":null},{"url":null,"slug":"elba-bench-an-efficient-learning-backdoor","title":"ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models","date":"2025-02-22","arxiv_id":"2502.18511","repositories_listed":0,"syntology":null},{"url":null,"slug":"show-me-your-code-kill-code-poisoning-a","title":"Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness","date":"2025-02-20","arxiv_id":"2502.15830","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robust-attack-displacement-backdoor-attack","title":"A Robust Attack: Displacement Backdoor Attack","date":"2025-02-14","arxiv_id":"2502.10490","repositories_listed":0,"syntology":null},{"url":null,"slug":"darkmind-latent-chain-of-thought-backdoor-in","title":"DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs","date":"2025-01-24","arxiv_id":"2501.18617","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrievals-can-be-detrimental-a-contrastive","title":"Retrievals Can Be Detrimental: A Contrastive Backdoor Attack Paradigm on Retrieval-Augmented Diffusion Models","date":"2025-01-23","arxiv_id":"2501.13340","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-decentralized-backdoor-attacks-on","title":"Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning","date":"2025-01-16","arxiv_id":"2501.09320","repositories_listed":0,"syntology":null},{"url":null,"slug":"a4o-all-trigger-for-one-sample","title":"A4O: All Trigger for One sample","date":"2025-01-13","arxiv_id":"2501.07192","repositories_listed":0,"syntology":null},{"url":null,"slug":"badtv-unveiling-backdoor-threats-in-third","title":"BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors","date":"2025-01-04","arxiv_id":"2501.02373","repositories_listed":0,"syntology":null},{"url":null,"slug":"honeypotnet-backdoor-attacks-against-model","title":"HoneypotNet: Backdoor Attacks Against Model Extraction","date":"2025-01-02","arxiv_id":"2501.01090","repositories_listed":0,"syntology":null},{"url":null,"slug":"stealthy-backdoor-attack-to-real-world-models","title":"Stealthy Backdoor Attack to Real-world Models in Android Apps","date":"2025-01-02","arxiv_id":"2501.01263","repositories_listed":0,"syntology":null},{"url":null,"slug":"injecting-bias-into-text-classification","title":"Injecting Bias into Text Classification Models using Backdoor Attacks","date":"2024-12-25","arxiv_id":"2412.18975","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-landmines-invisible-textual-backdoor","title":"Double Landmines: Invisible Textual Backdoor Attacks based on Dual-Trigger","date":"2024-12-23","arxiv_id":"2412.17531","repositories_listed":0,"syntology":null},{"url":null,"slug":"trading-devil-rl-backdoor-attack-via-stock","title":"Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning","date":"2024-12-23","arxiv_id":"2412.17908","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-backdoor-attack-scheme-with-invisible","title":"A Backdoor Attack Scheme with Invisible Triggers Based on Model Architecture Modification","date":"2024-12-22","arxiv_id":"2412.16905","repositories_listed":0,"syntology":null},{"url":null,"slug":"badsad-clean-label-backdoor-attacks-against","title":"BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection","date":"2024-12-17","arxiv_id":"2412.13324","repositories_listed":0,"syntology":null},{"url":null,"slug":"stealthy-and-robust-backdoor-attack-against","title":"Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features","date":"2024-12-10","arxiv_id":"2412.07511","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-effective-and-resilient-backdoor-attack","title":"An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers","date":"2024-12-09","arxiv_id":"2412.06149","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdooring-outlier-detection-methods-a-novel","title":"Backdooring Outlier Detection Methods: A Novel Attack Approach","date":"2024-12-06","arxiv_id":"2412.05010","repositories_listed":0,"syntology":null},{"url":null,"slug":"megatron-evasive-clean-label-backdoor-attacks","title":"Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer","date":"2024-12-06","arxiv_id":"2412.04776","repositories_listed":0,"syntology":null},{"url":null,"slug":"laserguider-a-laser-based-physical-backdoor","title":"LaserGuider: A Laser Based Physical Backdoor Attack against Deep Neural Networks","date":"2024-12-05","arxiv_id":"2412.03993","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavior-backdoor-for-deep-learning-models","title":"Behavior Backdoor for Deep Learning Models","date":"2024-12-02","arxiv_id":"2412.01369","repositories_listed":0,"syntology":null},{"url":null,"slug":"ladder-multi-objective-backdoor-attack-via","title":"LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm","date":"2024-11-28","arxiv_id":"2411.19075","repositories_listed":0,"syntology":null},{"url":null,"slug":"streamlined-federated-unlearning-unite-as-one","title":"Streamlined Federated Unlearning: Unite as One to Be Highly Efficient","date":"2024-11-28","arxiv_id":"2412.00126","repositories_listed":0,"syntology":null},{"url":null,"slug":"badscan-an-architectural-backdoor-attack-on","title":"BadScan: An Architectural Backdoor Attack on Visual State Space Models","date":"2024-11-26","arxiv_id":"2411.17283","repositories_listed":0,"syntology":null},{"url":null,"slug":"badsfl-backdoor-attack-against-scaffold","title":"BadSFL: Backdoor Attack against Scaffold Federated Learning","date":"2024-11-25","arxiv_id":"2411.16167","repositories_listed":0,"syntology":null},{"url":null,"slug":"lobam-lora-based-backdoor-attack-on-model","title":"LoBAM: LoRA-Based Backdoor Attack on Model Merging","date":"2024-11-23","arxiv_id":"2411.16746","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-backdoor-attacks-on-neural-networks","title":"Memory Backdoor Attacks on Neural Networks","date":"2024-11-21","arxiv_id":"2411.14516","repositories_listed":0,"syntology":null},{"url":null,"slug":"detrigger-a-gradient-centric-approach-to","title":"DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning","date":"2024-11-19","arxiv_id":"2411.12220","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-backdoors-speak-understanding-llm","title":"When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations","date":"2024-11-19","arxiv_id":"2411.12701","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-poisoned-sample-detection-against","title":"Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization","date":"2024-11-18","arxiv_id":"2411.11525","repositories_listed":0,"syntology":null},{"url":null,"slug":"trojanrobot-backdoor-attacks-against-robotic","title":"TrojanRobot: Physical-World Backdoor Attacks Against VLM-based Robotic Manipulation","date":"2024-11-18","arxiv_id":"2411.11683","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlearn-to-relearn-backdoors-deferred","title":"Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models","date":"2024-11-10","arxiv_id":"2411.14449","repositories_listed":0,"syntology":null},{"url":null,"slug":"act-in-collusion-a-persistent-distributed","title":"Act in Collusion: A Persistent Distributed Multi-Target Backdoor in Federated Learning","date":"2024-11-06","arxiv_id":"2411.03926","repositories_listed":0,"syntology":null},{"url":null,"slug":"flashy-backdoor-real-world-environment","title":"Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras","date":"2024-11-05","arxiv_id":"2411.03022","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdoor-attack-against-vision-transformers","title":"Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosion","date":"2024-10-30","arxiv_id":"2410.22678","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdoor-in-seconds-unlocking-vulnerabilities","title":"Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing","date":"2024-10-23","arxiv_id":"2410.18267","repositories_listed":0,"syntology":null},{"url":null,"slug":"securing-federated-learning-against-novel-and","title":"Securing Federated Learning against Backdoor Threats with Foundation Model Integration","date":"2024-10-23","arxiv_id":"2410.17573","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdoored-retrievers-for-prompt-injection","title":"Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models","date":"2024-10-18","arxiv_id":"2410.14479","repositories_listed":0,"syntology":null},{"url":null,"slug":"trojan-prompt-attacks-on-graph-neural","title":"Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks","date":"2024-10-17","arxiv_id":"2410.13974","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-tailed-backdoor-attack-using-dynamic","title":"Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations","date":"2024-10-16","arxiv_id":"2410.12955","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdoor-attack-on-vertical-federated-graph","title":"Backdoor Attack on Vertical Federated Graph Neural Network Learning","date":"2024-10-15","arxiv_id":"2410.11290","repositories_listed":0,"syntology":null},{"url":null,"slug":"cat-concept-level-backdoor-attacks-for","title":"CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models","date":"2024-10-07","arxiv_id":"2410.04823","repositories_listed":0,"syntology":null},{"url":null,"slug":"defense-as-a-service-black-box-shielding","title":"Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models","date":"2024-10-07","arxiv_id":"2410.04916","repositories_listed":0,"syntology":null},{"url":null,"slug":"badhmp-backdoor-attack-against-human-motion","title":"BadHMP: Backdoor Attack against Human Motion Prediction","date":"2024-09-29","arxiv_id":"2409.19638","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-backdoor-defense-in-multimodal","title":"Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats","date":"2024-09-29","arxiv_id":"2409.19526","repositories_listed":0,"syntology":null},{"url":null,"slug":"psychometrics-for-hypnopaedia-aware-machinery","title":"Psychometrics for Hypnopaedia-Aware Machinery via Chaotic Projection of Artificial Mental Imagery","date":"2024-09-29","arxiv_id":"2410.05284","repositories_listed":0,"syntology":null},{"url":null,"slug":"trojvlm-backdoor-attack-against-vision","title":"TrojVLM: Backdoor Attack Against Vision Language Models","date":"2024-09-28","arxiv_id":"2409.19232","repositories_listed":0,"syntology":null}],"record_sha256":"abb24809ef8e9bed28f72cbb69e49cb44eadee5b5bfd1c08ccc47f698b2b48ae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}